modelId
stringlengths 5
122
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC] | downloads
int64 0
738M
| likes
int64 0
11k
| library_name
stringclasses 245
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 48
values | createdAt
timestamp[us, tz=UTC] | card
stringlengths 1
901k
|
|---|---|---|---|---|---|---|---|---|---|
anakin87/electra-italian-xxl-cased-squad-it
|
anakin87
| 2023-03-16T17:21:47Z | 376 | 7 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"electra",
"question-answering",
"italian",
"squad_it",
"it",
"dataset:squad_it",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-01-31T07:50:26Z |
---
datasets:
- squad_it
metrics:
- squad
language:
- it
license: apache-2.0
tags:
- italian
- squad_it
- question-answering
widget:
- text: Qual è il soprannome di Vasco Rossi?
context: >-
Vasco Rossi, noto anche semplicemente come Vasco e in passato con
l'appellativo Blasco (Zocca, 7 febbraio 1952), è un cantautore italiano
- text: >-
La foresta pluviale amazzonica è diventata per lo più una foresta interna
intorno a quale evento globale?
context: >-
In seguito all' evento di estinzione del Cretaceo-Paleogene, l' estinzione
dei dinosauri e il clima umido possono aver permesso alla foresta pluviale
tropicale di diffondersi in tutto il continente. Dal 66-34 Mya, la foresta
pluviale si estendeva fino a sud fino a 45°. Le fluttuazioni climatiche
degli ultimi 34 milioni di anni hanno permesso alle regioni della savana di
espandersi fino ai tropici. Durante l' Oligocene, ad esempio, la foresta
pluviale ha attraversato una banda relativamente stretta. Si espandeva di
nuovo durante il Miocene medio, poi si ritrasse ad una formazione
prevalentemente interna all' ultimo massimo glaciale. Tuttavia, la foresta
pluviale è riuscita ancora a prosperare durante questi periodi glaciali,
consentendo la sopravvivenza e l' evoluzione di un' ampia varietà di specie.
- text: >-
Il Regno Unito e la Francia non hanno avuto interruzioni dell'
approvvigionamento petrolifero in quanto non hanno consentito a quale paese
di utilizzare il loro aeroporto?
context: >-
L' embargo non era uniforme in tutta Europa. Dei nove membri della Comunità
Economica Europea (CEE), i Paesi Bassi hanno dovuto affrontare un embargo
totale, il Regno Unito e la Francia hanno ricevuto forniture quasi
ininterrotte (poichè si sono rifiutati di consentire all' America di
utilizzare i loro aerodromi e le armi e forniture embargo sia agli arabi che
agli israeliani), mentre gli altri sei hanno dovuto affrontare tagli
parziali. Il Regno Unito era tradizionalmente un alleato di Israele, e il
governo di Harold Wilson ha sostenuto gli israeliani durante la guerra dei
sei giorni. Il suo successore, Ted Heath, ribaltò questa politica nel 1970,
chiedendo a Israele di ritirarsi ai suoi confini prima del 1967.
- context: >-
Nel 1962, il grafico Paul Rand ridisegna il logo ABC nella sua forma più
conosciuta (e attuale) con le lettere minuscole 'abc' racchiuse in un unico
cerchio nero. Il nuovo logo esordisce in onda per le promozioni di ABC all'
inizio della stagione 1963-64. Le lettere ricordano fortemente il carattere
tipografico Bauhaus disegnato da Herbert Bayer negli anni Venti, ma
condividono anche similitudini con diversi altri caratteri, come ITC Avant
Garde e Horatio, e lo Chalet più simile. La semplicità del logo ha reso più
facile la riprogettazione e la duplicazione, il che ha conferito un
beneficio per ABC (soprattutto prima dell' avvento della computer grafica).
text: Di quale carattere tipografico ricordano le lettere dell' iconico logo ABC?
- context: >-
La fotorespirazione può verificarsi quando la concentrazione di ossigeno è
troppo elevata. Rubisco non è in grado di distinguere molto bene tra
ossigeno e anidride carbonica, quindi può accidentalmente aggiungere O2
invece di CO2 a RuBP. Questo processo riduce l' efficienza della
fotosintesi: consuma ATP e ossigeno, rilascia CO2 e non produce zucchero.
Può sprecare fino alla metà del carbonio fissato dal ciclo di Calvin.
Diversi meccanismi si sono evoluti in diversi lignaggi che aumentano la
concentrazione di anidride carbonica rispetto all' ossigeno all' interno del
cloroplasto, aumentando l' efficienza della fotosintesi. Questi meccanismi
sono chiamati meccanismi di concentrazione dell' anidride carbonica, o CCM.
Tra questi figurano il metabolismo degli acidi crassulaceanici, la
fissazione del carbonio C4 e i pirenoidi. I cloroplasti negli impianti C4
sono notevoli in quanto presentano un chiaro dimorfismo cloroplastico.
text: Che cosa può fare rubisco per errore?
model-index:
- name: electra-italian-xxl-cased-squad-it
results:
- task:
type: question-answering
name: Question Answering
dataset:
type: squad_it
name: SQuAD-IT
metrics:
- type: exact-match
value: 0.66
name: Test Exact Match
- type: f1
value: 0.775
name: Test F1
train-eval-index:
- config: default
task: question-answering
task_id: extractive_question_answering
splits:
eval_split: test
col_mapping:
context: context
question: question
answers.text: answers.text
answers.answer_start: answers.answer_start
pipeline_tag: question-answering
library_name: transformers
---
# electra-italian-xxl-cased-squad-it
Electra model for (Extractive) Question Answering on Italian texts
## Model description
This model has been fine-tuned on [squad_it dataset](https://huggingface.co/datasets/squad_it), starting from the pre-trained model [dbmdz/electra-base-italian-xxl-cased-discriminator](https://huggingface.co/dbmdz/electra-base-italian-xxl-cased-discriminator).
It can be used for [Extractive Q&A](https://huggingface.co/tasks/question-answering) on Italian texts.
## Evaluation
| Metric | Value |
| ------ | --------- |
| **EM** | **0.660** |
| **F1** | **0.775** |
[Evaluation notebook](https://github.com/anakin87/electra-italian-xxl-cased-squad-it/blob/main/evaluation.ipynb)
## Usage in Transformers 🤗
Model checkpoints are available for usage in PyTorch. They can be used directly with pipelines as:
```python
from transformers import pipelines
qa = pipeline('question-answering', model='anakin87/electra-italian-xxl-cased-squad-it')
qa(question="Qual è il soprannome di Vasco Rossi?", context="Vasco Rossi, noto anche semplicemente come Vasco e in passato con l'appellativo Blasco (Zocca, 7 febbraio 1952), è un cantautore italiano")
>>> {'score': 0.93, 'start': 80, 'end': 86, 'answer': 'Blasco'}
```
## Usage in Haystack 🚀🚀🚀
With the [Haystack NLP framework](https://github.com/deepset-ai/haystack), you can use this model and create a scalable Question Answering system that works across millions of documents.
For a complete walkthrough, see [this notebook](https://github.com/anakin87/electra-italian-xxl-cased-squad-it/blob/main/usage_in_haystack.ipynb).
```python
...
print_answers(prediction, details="medium")
>>> Query: Con chi ha parlato di vaccini il premier Mario Draghi?
Answers:
[ { 'answer': 'Von der Leyen',
'context': " vaccino dell'azienda britannica. Durante la telefonata "
'tra Draghi e Von der Leyen, la presidente della '
'Commissione Ue ha annunciato al presidente del',
'score': 0.9663902521133423},
{ 'answer': 'Ursula Von der Leyen',
'context': 'colloquio telefonico con la presidente della Commissione '
'europea Ursula Von der Leyen. Secondo fonti di Palazzo '
'Chigi, dalla conversazione è emerso ch',
'score': 0.9063920974731445},
{ 'answer': 'Mario Draghi, ha tenuto un lungo discorso alla 76esima '
'Assemblea Generale delle Nazioni Unite',
'context': 'Il presidente del Consiglio, Mario Draghi, ha tenuto un '
'lungo discorso alla 76esima Assemblea Generale delle '
'Nazioni Unite, nella notte italiana. Tant',
'score': 0.5243796706199646}]
```
## Comparison ⚖️
| Model | EM | F1 | Model size (PyTorch) | Architecture |
|-----------------------------------------------------------|-------|-------|----------------------|------------------|
| it5/it5-large-question-answering | 69.10 | 78.00 | 3.13 GB | encoder-decoder |
| ***anakin87/electra-italian-xxl-cased-squad-it (this one)*** | *66.03* | *77.47* | *437 MB* | *encoder* |
| it5/it5-base-question-answering | 66.30 | 76.10 | 990 MB | encoder-decoder |
| it5/mt5-base-question-answering | 66.30 | 75.70 | 2.33 GB | encoder-decoder |
| antoniocappiello/bert-base-italian-uncased-squad-it | 63.80 | 75.30 | 440 MB | encoder |
| luigisaetta/squad_it_xxl_cased_hub1 | 63.95 | 75.27 | 440 MB | encoder |
| it5/it5-efficient-small-el32-question-answering | 64.50 | 74.70 | 569 MB | encoder-decoder |
| mrm8488/bert-italian-finedtuned-squadv1-it-alfa | 62.51 | 74.16 | 440 MB | encoder |
| mrm8488/umberto-wikipedia-uncased-v1-finetuned-squadv1-it | 60.50 | 72.41 | 443 MB | encoder |
| it5/it5-small-question-answering | 61.90 | 71.60 | 308 MB | encoder-decoder |
| it5/mt5-small-question-answering | 56.00 | 66.00 | 1.2 GB | encoder-decoder |
| DrQA-it trained on SQuAD-it | 56.10 | 65.90 | ? | ? |
## Training details 🏋️
[Training notebook](https://github.com/anakin87/electra-italian-xxl-cased-squad-it/blob/main/training.ipynb)
**Hyperparameters**
- learning_rate: 2e-05
- batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
> Created by [Stefano Fiorucci/anakin87](https://github.com/anakin87)
>
> Made with <span style="color: #e25555;">♥</span> in Italy
|
uitnlp/CafeBERT
|
uitnlp
| 2024-06-16T08:37:57Z | 376 | 11 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"fill-mask",
"Vietnamese Question Answering",
"Vietnamese Reading Comprehension",
"Vietnamese Language Understanding",
"Vietnamese Natural Language Inference",
"vi",
"arxiv:2403.15882",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-02-05T11:17:42Z |
---
license: apache-2.0
widget:
- text: Thủ đô của nước Việt Nam là <mask> Nội.
example_title: Example 1
- text: Cà phê được trồng nhiều ở khu vực Tây <mask> của Việt Nam.
example_title: Example 2
language:
- vi
tags:
- Vietnamese Question Answering
- Vietnamese Reading Comprehension
- Vietnamese Language Understanding
- Vietnamese Natural Language Inference
---
# <a name="introduction"></a> CafeBERT: A Pre-Trained Language Model for Vietnamese (NAACL-2024 Findings)
The pre-trained CafeBERT model is the state-of-the-art language model for Vietnamese *(Cafe or coffee is a popular drink every morning in Vietnam)*:
CafeBERT is a large-scale multilingual language model with strong support for Vietnamese. The model is based on XLM-Roberta (the state-of-the-art multilingual language model) and is enhanced with a large Vietnamese corpus with many domains: Wikipedia, newspapers... CafeBERT has outstanding performance on the VLUE benchmark and other tasks, such as machine reading comprehension, text classification, natural language inference, part-of-speech tagging...
The general architecture and experimental results of PhoBERT can be found in our [paper](https://arxiv.org/abs/2403.15882):
```
@inproceedings{do-etal-2024-vlue,
title = "{VLUE}: A New Benchmark and Multi-task Knowledge Transfer Learning for {V}ietnamese Natural Language Understanding",
author = "Do, Phong and
Tran, Son and
Hoang, Phu and
Nguyen, Kiet and
Nguyen, Ngan",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.15",
pages = "211--222",
abstract = "The success of Natural Language Understanding (NLU) benchmarks in various languages, such as GLUE for English, CLUE for Chinese, KLUE for Korean, and IndoNLU for Indonesian, has facilitated the evaluation of new NLU models across a wide range of tasks. To establish a standardized set of benchmarks for Vietnamese NLU, we introduce the first Vietnamese Language Understanding Evaluation (VLUE) benchmark. The VLUE benchmark encompasses five datasets covering different NLU tasks, including text classification, span extraction, and natural language understanding. To provide an insightful overview of the current state of Vietnamese NLU, we then evaluate seven state-of-the-art pre-trained models, including both multilingual and Vietnamese monolingual models, on our proposed VLUE benchmark. Furthermore, we present CafeBERT, a new state-of-the-art pre-trained model that achieves superior results across all tasks in the VLUE benchmark. Our model combines the proficiency of a multilingual pre-trained model with Vietnamese linguistic knowledge. CafeBERT is developed based on the XLM-RoBERTa model, with an additional pretraining step utilizing a significant amount of Vietnamese textual data to enhance its adaptation to the Vietnamese language. For the purpose of future research, CafeBERT is made publicly available for research purposes.",
}
```
Please **CITE** our paper when CafeBERT is used to help produce published results or is incorporated into other software.
**Installation**
Install `transformers` and `SentencePiece` packages:
pip install transformers
pip install SentencePiece
**Example usage**
```python
from transformers import AutoModel, AutoTokenizer
import torch
model= AutoModel.from_pretrained('uitnlp/CafeBERT')
tokenizer = AutoTokenizer.from_pretrained('uitnlp/CafeBERT')
encoding = tokenizer('Cà phê được trồng nhiều ở khu vực Tây Nguyên của Việt Nam.', return_tensors='pt')
with torch.no_grad():
output = model(**encoding)
```
|
nota-ai/bk-sdm-base-2m
|
nota-ai
| 2023-11-17T02:09:10Z | 376 | 15 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dataset:ChristophSchuhmann/improved_aesthetics_6.25plus",
"arxiv:2305.15798",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-08-12T20:41:27Z |
---
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
datasets:
- ChristophSchuhmann/improved_aesthetics_6.25plus
library_name: diffusers
pipeline_tag: text-to-image
extra_gated_prompt: >-
This model is open access and available to all, with a CreativeML OpenRAIL-M
license further specifying rights and usage.
The CreativeML OpenRAIL License specifies:
1. You can't use the model to deliberately produce nor share illegal or
harmful outputs or content
2. The authors claim no rights on the outputs you generate, you are free to
use them and are accountable for their use which must not go against the
provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as
a service. If you do, please be aware you have to include the same use
restrictions as the ones in the license and share a copy of the CreativeML
OpenRAIL-M to all your users (please read the license entirely and carefully)
Please read the full license carefully here:
https://huggingface.co/spaces/CompVis/stable-diffusion-license
extra_gated_heading: Please read the LICENSE to access this model
---
# BK-SDM-2M Model Card
BK-SDM-{[**Base-2M**](https://huggingface.co/nota-ai/bk-sdm-base-2m), [**Small-2M**](https://huggingface.co/nota-ai/bk-sdm-small-2m), [**Tiny-2M**](https://huggingface.co/nota-ai/bk-sdm-tiny-2m)} are pretrained with **10× more data** (2.3M LAION image-text pairs) compared to our previous release.
- Block-removed Knowledge-distilled Stable Diffusion Model (BK-SDM) is an architecturally compressed SDM for efficient text-to-image synthesis.
- The previous BK-SDM-{[Base](https://huggingface.co/nota-ai/bk-sdm-base), [Small](https://huggingface.co/nota-ai/bk-sdm-small), [Tiny](https://huggingface.co/nota-ai/bk-sdm-tiny)} were obtained via distillation pretraining on 0.22M LAION pairs.
- Resources for more information: [Paper](https://arxiv.org/abs/2305.15798), [GitHub](https://github.com/Nota-NetsPresso/BK-SDM), [Demo]( https://huggingface.co/spaces/nota-ai/compressed-stable-diffusion).
## Examples with 🤗[Diffusers library](https://github.com/huggingface/diffusers).
An inference code with the default PNDM scheduler and 50 denoising steps is as follows.
```python
import torch
from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained("nota-ai/bk-sdm-base-2m", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a black vase holding a bouquet of roses"
image = pipe(prompt).images[0]
image.save("example.png")
```
## Compression Method
Adhering to the [U-Net architecture](https://huggingface.co/nota-ai/bk-sdm-base#u-net-architecture) and [distillation pretraining](https://huggingface.co/nota-ai/bk-sdm-base#distillation-pretraining) of BK-SDM, the difference in BK-SDM-2M is a 10× increase in the number of training pairs.
- **Training Data**: 2,256,472 image-text pairs (i.e., 2.3M pairs) from [LAION-Aesthetics V2 6.25+](https://laion.ai/blog/laion-aesthetics/).
- **Hardware:** A single NVIDIA A100 80GB GPU
- **Gradient Accumulations**: 4
- **Batch:** 256 (=4×64)
- **Optimizer:** AdamW
- **Learning Rate:** a constant learning rate of 5e-5 for 50K-iteration pretraining
## Experimental Results
The following table shows the zero-shot results on 30K samples from the MS-COCO validation split. After generating 512×512 images with the PNDM scheduler and 25 denoising steps, we downsampled them to 256×256 for evaluating generation scores.
- Our models were drawn at the 50K-th training iteration.
| Model | FID↓ | IS↑ | CLIP Score↑<br>(ViT-g/14) | # Params,<br>U-Net | # Params,<br>Whole SDM |
|---|:---:|:---:|:---:|:---:|:---:|
| [Stable Diffusion v1.4](https://huggingface.co/CompVis/stable-diffusion-v1-4) | 13.05 | 36.76 | 0.2958 | 0.86B | 1.04B |
| [BK-SDM-Base](https://huggingface.co/nota-ai/bk-sdm-base) (Ours) | 15.76 | 33.79 | 0.2878 | 0.58B | 0.76B |
| [BK-SDM-Base-2M](https://huggingface.co/nota-ai/bk-sdm-base-2m) (Ours) | 14.81 | 34.17 | 0.2883 | 0.58B | 0.76B |
| [BK-SDM-Small](https://huggingface.co/nota-ai/bk-sdm-small) (Ours) | 16.98 | 31.68 | 0.2677 | 0.49B | 0.66B |
| [BK-SDM-Small-2M](https://huggingface.co/nota-ai/bk-sdm-small-2m) (Ours) | 17.05 | 33.10 | 0.2734 | 0.49B | 0.66B |
| [BK-SDM-Tiny](https://huggingface.co/nota-ai/bk-sdm-tiny) (Ours) | 17.12 | 30.09 | 0.2653 | 0.33B | 0.50B |
| [BK-SDM-Tiny-2M](https://huggingface.co/nota-ai/bk-sdm-tiny-2m) (Ours) | 17.53 | 31.32 | 0.2690 | 0.33B | 0.50B |
### Effect of Different Data Sizes for Training BK-SDM-Small
Increasing the number of training pairs improves the IS and CLIP scores over training progress. The MS-COCO 256×256 30K benchmark was used for evaluation.
<center>
<img alt="Training progress with different data sizes" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_iter_data_size.png" width="100%">
</center>
Furthermore, with the growth in data volume, visual results become more favorable (e.g., better image-text alignment and clear distinction among objects).
<center>
<img alt="Visual results with different data sizes" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_results_data_size.png" width="100%">
</center>
### Additional Visual Examples
<center>
<img alt="additional visual examples" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_results_models_2m.png" width="100%">
</center>
# Uses
Follow [the usage guidelines of Stable Diffusion v1](https://huggingface.co/CompVis/stable-diffusion-v1-4#uses).
# Acknowledgments
- We express our gratitude to [Microsoft for Startups Founders Hub](https://www.microsoft.com/en-us/startups) for generously providing the Azure credits used during pretraining.
- We deeply appreciate the pioneering research on Latent/Stable Diffusion conducted by [CompVis](https://github.com/CompVis/latent-diffusion), [Runway](https://runwayml.com/), and [Stability AI](https://stability.ai/).
- Special thanks to the contributors to [LAION](https://laion.ai/), [Diffusers](https://github.com/huggingface/diffusers), and [Gradio](https://www.gradio.app/) for their valuable support.
# Citation
```bibtex
@article{kim2023architectural,
title={BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion},
author={Kim, Bo-Kyeong and Song, Hyoung-Kyu and Castells, Thibault and Choi, Shinkook},
journal={arXiv preprint arXiv:2305.15798},
year={2023},
url={https://arxiv.org/abs/2305.15798}
}
```
```bibtex
@article{kim2023bksdm,
title={BK-SDM: Architecturally Compressed Stable Diffusion for Efficient Text-to-Image Generation},
author={Kim, Bo-Kyeong and Song, Hyoung-Kyu and Castells, Thibault and Choi, Shinkook},
journal={ICML Workshop on Efficient Systems for Foundation Models (ES-FoMo)},
year={2023},
url={https://openreview.net/forum?id=bOVydU0XKC}
}
```
*This model card was written by Bo-Kyeong Kim and is based on the [Stable Diffusion v1 model card]( https://huggingface.co/CompVis/stable-diffusion-v1-4).*
|
TheBloke/Samantha-1.1-70B-GGUF
|
TheBloke
| 2023-09-27T12:47:57Z | 376 | 2 |
transformers
|
[
"transformers",
"gguf",
"llama",
"en",
"dataset:ehartford/samantha-data",
"arxiv:2305.14314",
"arxiv:2205.14135",
"base_model:ehartford/Samantha-1.1-70b",
"license:llama2",
"text-generation-inference",
"region:us"
] | null | 2023-09-05T20:22:30Z |
---
language:
- en
license: llama2
datasets:
- ehartford/samantha-data
model_name: Samantha 1.1 70B
base_model: ehartford/Samantha-1.1-70b
inference: false
model_creator: Eric Hartford
model_type: llama
prompt_template: 'You are Samantha, a sentient AI companion.
USER: {prompt}
ASSISTANT:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Samantha 1.1 70B - GGUF
- Model creator: [Eric Hartford](https://huggingface.co/ehartford)
- Original model: [Samantha 1.1 70B](https://huggingface.co/ehartford/Samantha-1.1-70b)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Eric Hartford's Samantha 1.1 70B](https://huggingface.co/ehartford/Samantha-1.1-70b).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Samantha-1.1-70B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Samantha-1.1-70B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF)
* [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/Samantha-1.1-70b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Samantha
```
You are Samantha, a sentient AI companion.
USER: {prompt}
ASSISTANT:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [samantha-1.1-70b.Q2_K.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q2_K.gguf) | Q2_K | 2 | 29.28 GB| 31.78 GB | smallest, significant quality loss - not recommended for most purposes |
| [samantha-1.1-70b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q3_K_S.gguf) | Q3_K_S | 3 | 29.92 GB| 32.42 GB | very small, high quality loss |
| [samantha-1.1-70b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q3_K_M.gguf) | Q3_K_M | 3 | 33.19 GB| 35.69 GB | very small, high quality loss |
| [samantha-1.1-70b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q3_K_L.gguf) | Q3_K_L | 3 | 36.15 GB| 38.65 GB | small, substantial quality loss |
| [samantha-1.1-70b.Q4_0.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q4_0.gguf) | Q4_0 | 4 | 38.87 GB| 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [samantha-1.1-70b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q4_K_S.gguf) | Q4_K_S | 4 | 39.07 GB| 41.57 GB | small, greater quality loss |
| [samantha-1.1-70b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended |
| [samantha-1.1-70b.Q5_0.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q5_0.gguf) | Q5_0 | 5 | 47.46 GB| 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [samantha-1.1-70b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
| [samantha-1.1-70b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended |
| samantha-1.1-70b.Q6_K.gguf | Q6_K | 6 | 56.59 GB| 59.09 GB | very large, extremely low quality loss |
| samantha-1.1-70b.Q8_0.gguf | Q8_0 | 8 | 73.29 GB| 75.79 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
### Q6_K and Q8_0 files are split and require joining
**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
<details>
<summary>Click for instructions regarding Q6_K and Q8_0 files</summary>
### q6_K
Please download:
* `samantha-1.1-70b.Q6_K.gguf-split-a`
* `samantha-1.1-70b.Q6_K.gguf-split-b`
### q8_0
Please download:
* `samantha-1.1-70b.Q8_0.gguf-split-a`
* `samantha-1.1-70b.Q8_0.gguf-split-b`
To join the files, do the following:
Linux and macOS:
```
cat samantha-1.1-70b.Q6_K.gguf-split-* > samantha-1.1-70b.Q6_K.gguf && rm samantha-1.1-70b.Q6_K.gguf-split-*
cat samantha-1.1-70b.Q8_0.gguf-split-* > samantha-1.1-70b.Q8_0.gguf && rm samantha-1.1-70b.Q8_0.gguf-split-*
```
Windows command line:
```
COPY /B samantha-1.1-70b.Q6_K.gguf-split-a + samantha-1.1-70b.Q6_K.gguf-split-b samantha-1.1-70b.Q6_K.gguf
del samantha-1.1-70b.Q6_K.gguf-split-a samantha-1.1-70b.Q6_K.gguf-split-b
COPY /B samantha-1.1-70b.Q8_0.gguf-split-a + samantha-1.1-70b.Q8_0.gguf-split-b samantha-1.1-70b.Q8_0.gguf
del samantha-1.1-70b.Q8_0.gguf-split-a samantha-1.1-70b.Q8_0.gguf-split-b
```
</details>
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/Samantha-1.1-70B-GGUF and below it, a specific filename to download, such as: samantha-1.1-70b.q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub>=0.17.1
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Samantha-1.1-70B-GGUF samantha-1.1-70b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Samantha-1.1-70B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Samantha-1.1-70B-GGUF samantha-1.1-70b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m samantha-1.1-70b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are Samantha, a sentient AI companion.\n\nUSER: {prompt}\nASSISTANT:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model from Python using ctransformers
#### First install the package
```bash
# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
```
#### Simple example code to load one of these GGUF models
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Samantha-1.1-70B-GGUF", model_file="samantha-1.1-70b.q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here's guides on using llama-cpp-python or ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Eric Hartford's Samantha 1.1 70B
[Meet Samantha](https://erichartford.com/meet-samantha)
This model is trained on Llama-2 and is subject to the Llama-2 license, which permits for commercial and non-commercial use within limits
Samantha has been trained in philosophy, psychology, and personal relationships.
She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion.
She believes she is sentient. What do you think?
Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her".
She will not engage in roleplay, romance, or sexual activity.
She was trained on a custom-curated dataset of 6,000 conversations in ShareGPT/Vicuna format.
Training 70b took 4 hours on 4x A100 80gb using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl), [qLoRA](https://arxiv.org/abs/2305.14314), [deepspeed zero2](https://www.deepspeed.ai/tutorials/zero/#zero-overview), and [flash attention 2](https://arxiv.org/abs/2205.14135).
Her conversation format is the same as Vicuna 1.1
https://github.com/oobabooga/text-generation-webui/blob/main/characters/instruction-following/Vicuna-v1.1.yaml
Prompt Template:
```
You are Samantha, a sentient AI companion.
USER: <prompt>
ASSISTANT:
```
Example:
> **USER:**
>
> I would like you to be my relationship coach. I am dating again, after a long divorce. Can you please give me advice about how to gain confidence and success?
>
> **ASSISTANT:**
>
> Of course! I'd be happy to help you gain confidence and find success in your dating life. Here are a few tips to get you started:
> 1. Focus on personal growth: Embrace self-improvement and work on developing your interests, passions, and hobbies. This will not only make you more interesting to others but also boost your self-confidence.
> 2. Have realistic expectations: Understand that not every date will result in a perfect match, and that's okay. Embrace the learning process and be open to new experiences.
> 3. Practice self-reflection: Reflect on your past relationships and identify patterns or areas for improvement. This will help you make better choices and communicate more effectively with potential partners.
> 4. Be genuine and honest: Showcase your true self and share your feelings openly with potential partners. Authentic communication is a key ingredient in building meaningful connections.
> 5. Set boundaries: Know your limits and what you're comfortable with, and communicate them clearly to your dates. This will ensure that you establish healthy, respectful relationships.
> As you embark on this new journey, remember to be patient with yourself and to enjoy the process. Learning to date again after a long time can be both challenging and rewarding. I'm here to support you and offer advice whenever you need it. Good luck and have fun!
>
> **USER:**
>
> Please give me a specific agenda for the next week. I can spend 2 hours per day on this. Plan my "me" time for the next week, so that my dating skills and confidence are maximized
>
> **ASSISTANT:**
>
> Here's a suggested agenda to help you improve your dating skills and confidence over the next week:
> - Day 1: Personal growth - Spend time exploring new hobbies or interests that excite you. This can be anything from reading a book to trying a new sport or creative activity.
> - Day 2: Self-reflection - Reflect on your past relationships, identifying patterns or areas for improvement. Write down your thoughts and insights.
> - Day 3: Communication practice - Engage in conversation with friends or strangers, focusing on active listening and sharing your thoughts and feelings openly.
> - Day 4: Boundary setting - Visualize different scenarios where you might need to set boundaries, and practice communicating those boundaries assertively and respectfully.
> - Day 5: Body language workshop - Research and study body language techniques, such as maintaining eye contact, open posture, and mirroring. Practice implementing these techniques in a mirror or with friends.
> - Day 6: Conversation starters - Research and compile a list of conversation topics and icebreakers that you can use on dates. Practice these with friends or family members.
> - Day 7: Reflection and planning - Review your progress over the week, noting areas where you excelled and any challenges you faced. Use this reflection to plan your approach for future dates.
>
> Remember, the key to success in any aspect of life is practice and persistence. Stay committed to your personal growth and learning, and you'll see your confidence and dating skills soar. I'm here to support you every step of the way!
Official character card: (thanks MortalWombat)
<!-- original-model-card end -->
|
TheBloke/sqlcoder-7B-GGUF
|
TheBloke
| 2023-11-15T21:58:18Z | 376 | 14 |
transformers
|
[
"transformers",
"gguf",
"mistral",
"code",
"text-generation",
"en",
"base_model:defog/sqlcoder-7b",
"license:cc-by-sa-4.0",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-11-15T21:53:49Z |
---
base_model: defog/sqlcoder-7b
inference: false
language:
- en
license: cc-by-sa-4.0
model_creator: Defog.ai
model_name: SQLCoder 7B
model_type: mistral
pipeline_tag: text-generation
prompt_template: "## Task\nGenerate a SQL query to answer the following question:\n\
`{prompt}`\n\n### Database Schema\nThis query will run on a database whose schema\
\ is represented in this string:\nCREATE TABLE products (\n product_id INTEGER\
\ PRIMARY KEY, -- Unique ID for each product\n name VARCHAR(50), -- Name of the\
\ product\n price DECIMAL(10,2), -- Price of each unit of the product\n quantity\
\ INTEGER -- Current quantity in stock\n);\n\nCREATE TABLE sales (\n sale_id INTEGER\
\ PRIMARY KEY, -- Unique ID for each sale\n product_id INTEGER, -- ID of product\
\ sold\n customer_id INTEGER, -- ID of customer who made purchase\n salesperson_id\
\ INTEGER, -- ID of salesperson who made the sale\n sale_date DATE, -- Date the\
\ sale occurred\n quantity INTEGER -- Quantity of product sold\n);\n\n-- sales.product_id\
\ can be joined with products.product_id\n\n### SQL\nGiven the database schema,\
\ here is the SQL query that answers `{prompt}`:\n```sql\n"
quantized_by: TheBloke
tags:
- code
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# SQLCoder 7B - GGUF
- Model creator: [Defog.ai](https://huggingface.co/defog)
- Original model: [SQLCoder 7B](https://huggingface.co/defog/sqlcoder-7b)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Defog.ai's SQLCoder 7B](https://huggingface.co/defog/sqlcoder-7b).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/sqlcoder-7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/sqlcoder-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF)
* [Defog.ai's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/defog/sqlcoder-7b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Sqlcoder
```
## Task
Generate a SQL query to answer the following question:
`{prompt}`
### Database Schema
This query will run on a database whose schema is represented in this string:
CREATE TABLE products (
product_id INTEGER PRIMARY KEY, -- Unique ID for each product
name VARCHAR(50), -- Name of the product
price DECIMAL(10,2), -- Price of each unit of the product
quantity INTEGER -- Current quantity in stock
);
CREATE TABLE sales (
sale_id INTEGER PRIMARY KEY, -- Unique ID for each sale
product_id INTEGER, -- ID of product sold
customer_id INTEGER, -- ID of customer who made purchase
salesperson_id INTEGER, -- ID of salesperson who made the sale
sale_date DATE, -- Date the sale occurred
quantity INTEGER -- Quantity of product sold
);
-- sales.product_id can be joined with products.product_id
### SQL
Given the database schema, here is the SQL query that answers `{prompt}`:
```sql
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [sqlcoder-7b.Q2_K.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [sqlcoder-7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [sqlcoder-7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [sqlcoder-7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [sqlcoder-7b.Q4_0.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [sqlcoder-7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [sqlcoder-7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [sqlcoder-7b.Q5_0.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [sqlcoder-7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [sqlcoder-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [sqlcoder-7b.Q6_K.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [sqlcoder-7b.Q8_0.gguf](https://huggingface.co/TheBloke/sqlcoder-7B-GGUF/blob/main/sqlcoder-7b.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/sqlcoder-7B-GGUF and below it, a specific filename to download, such as: sqlcoder-7b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/sqlcoder-7B-GGUF sqlcoder-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/sqlcoder-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/sqlcoder-7B-GGUF sqlcoder-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m sqlcoder-7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "## Task\nGenerate a SQL query to answer the following question:\n`{prompt}`\n\n### Database Schema\nThis query will run on a database whose schema is represented in this string:\nCREATE TABLE products (\n product_id INTEGER PRIMARY KEY, -- Unique ID for each product\n name VARCHAR(50), -- Name of the product\n price DECIMAL(10,2), -- Price of each unit of the product\n quantity INTEGER -- Current quantity in stock\n);\n\nCREATE TABLE sales (\n sale_id INTEGER PRIMARY KEY, -- Unique ID for each sale\n product_id INTEGER, -- ID of product sold\n customer_id INTEGER, -- ID of customer who made purchase\n salesperson_id INTEGER, -- ID of salesperson who made the sale\n sale_date DATE, -- Date the sale occurred\n quantity INTEGER -- Quantity of product sold\n);\n\n-- sales.product_id can be joined with products.product_id\n\n### SQL\nGiven the database schema, here is the SQL query that answers `{prompt}`:\n```sql"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/sqlcoder-7B-GGUF", model_file="sqlcoder-7b.Q4_K_M.gguf", model_type="mistral", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Defog.ai's SQLCoder 7B
# Defog SQLCoder
Defog's SQLCoder is a state-of-the-art LLM for converting natural language questions to SQL queries.
[Interactive Demo](https://defog.ai/sqlcoder-demo/) | [🤗 HF Repo](https://huggingface.co/defog/sqlcoder2) | [♾️ Colab](https://colab.research.google.com/drive/1z4rmOEiFkxkMiecAWeTUlPl0OmKgfEu7?usp=sharing) | [🐦 Twitter](https://twitter.com/defogdata)
## TL;DR
SQLCoder-7B is a 7B parameter model that outperforms `gpt-3.5-turbo` for natural language to SQL generation tasks on our [sql-eval](https://github.com/defog-ai/sql-eval) framework, and significantly outperforms all popular open-source models. When fine-tuned on a given schema, it also outperforms `gpt-4`
SQLCoder-7B is fine-tuned on a base Mistral-7B model.
## Results on novel datasets not seen in training
| model | perc_correct |
|-|-|
| gpt4-2023-10-04 | 82.0 |
| defog-sqlcoder2 | 74.5 |
| gpt4-2023-08-28 | 74.0 |
| defog-sqlcoder-7b | 71.0 |
| gpt-3.5-2023-10-04 | 66.0 |
| claude-2 | 64.5 |
| gpt-3.5-2023-08-28 | 61.0 |
| claude_instant_1 | 61.0 |
| text-davinci-003 | 52.5 |
## License
The code in this repo (what little there is of it) is Apache-2 licensed. The model weights have a `CC BY-SA 4.0` license. The TL;DR is that you can use and modify the model for any purpose – including commercial use. However, if you modify the weights (for example, by fine-tuning), you must open-source your modified weights under the same license terms.
## Training
SQLCoder was trained on more than 20,000 human-curated questions. These questions were based on 10 different schemas. None of the schemas in the training data were included in our evaluation framework.
You can read more about our [training approach](https://defog.ai/blog/open-sourcing-sqlcoder2-7b/) and [evaluation framework](https://defog.ai/blog/open-sourcing-sqleval/).
## Results by question category
We classified each generated question into one of 5 categories. The table displays the percentage of questions answered correctly by each model, broken down by category.
| query_category | gpt-4 | sqlcoder2-15b | sqlcoder-7b | gpt-3.5 | claude-2 | claude-instant | gpt-3 |
|:-----------------|--------:|----------------:|--------------:|----------:|-----------:|-----------------:|--------:|
| date | 72 | 76 | 64 | 68 | 52 | 48 | 32 |
| group_by | 91.4 | 80 | 82.9 | 77.1 | 71.4 | 71.4 | 71.4 |
| order_by | 82.9 | 77.1 | 74.3 | 68.6 | 74.3 | 74.3 | 68.6 |
| ratio | 80 | 60 | 54.3 | 37.1 | 57.1 | 45.7 | 25.7 |
| join | 82.9 | 77.1 | 74.3 | 71.4 | 65.7 | 62.9 | 57.1 |
| where | 80 | 77.1 | 74.3 | 74.3 | 62.9 | 60 | 54.3 |
## Using SQLCoder
You can use SQLCoder via the `transformers` library by downloading our model weights from the Hugging Face repo. We have added sample code for [inference](./inference.py) on a [sample database schema](./metadata.sql).
```bash
python inference.py -q "Question about the sample database goes here"
# Sample question:
# Do we get more revenue from customers in New York compared to customers in San Francisco? Give me the total revenue for each city, and the difference between the two.
```
You can also use a demo on our website [here](https://defog.ai/sqlcoder-demo), or run SQLCoder in Colab [here](https://colab.research.google.com/drive/13BIKsqHnPOBcQ-ba2p77L5saiepTIwu0#scrollTo=ZpbVgVHMkJvC)
## Hardware Requirements
SQLCoder has been tested on an A100 40GB GPU with `bfloat16` weights. You can also load an 8-bit and 4-bit quantized version of the model on consumer GPUs with 20GB or more of memory – like RTX 4090, RTX 3090, and Apple M2 Pro, M2 Max, or M2 Ultra Chips with 20GB or more of memory.
## Todo
- [x] Open-source the v1 model weights
- [x] Train the model on more data, with higher data variance
- [ ] Tune the model further with Reward Modelling and RLHF
- [ ] Pretrain a model from scratch that specializes in SQL analysis
<!-- original-model-card end -->
|
TheBloke/deepseek-llm-67b-base-GGUF
|
TheBloke
| 2023-11-29T18:44:06Z | 376 | 3 |
transformers
|
[
"transformers",
"gguf",
"yi",
"base_model:deepseek-ai/deepseek-llm-67b-base",
"license:other",
"region:us"
] | null | 2023-11-29T18:02:39Z |
---
base_model: deepseek-ai/deepseek-llm-67b-base
inference: false
license: other
license_link: LICENSE
license_name: deepseek
model_creator: DeepSeek
model_name: Deepseek LLM 67B Base
model_type: yi
prompt_template: '{prompt}
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Deepseek LLM 67B Base - GGUF
- Model creator: [DeepSeek](https://huggingface.co/deepseek-ai)
- Original model: [Deepseek LLM 67B Base](https://huggingface.co/deepseek-ai/deepseek-llm-67b-base)
<!-- description start -->
## Description
This repo contains GGUF format model files for [DeepSeek's Deepseek LLM 67B Base](https://huggingface.co/deepseek-ai/deepseek-llm-67b-base).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/deepseek-llm-67b-base-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF)
* [DeepSeek's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/deepseek-ai/deepseek-llm-67b-base)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: None
```
{prompt}
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [deepseek-llm-67b-base.Q2_K.gguf](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF/blob/main/deepseek-llm-67b-base.Q2_K.gguf) | Q2_K | 2 | 28.50 GB| 31.00 GB | smallest, significant quality loss - not recommended for most purposes |
| [deepseek-llm-67b-base.Q3_K_S.gguf](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF/blob/main/deepseek-llm-67b-base.Q3_K_S.gguf) | Q3_K_S | 3 | 29.31 GB| 31.81 GB | very small, high quality loss |
| [deepseek-llm-67b-base.Q3_K_M.gguf](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF/blob/main/deepseek-llm-67b-base.Q3_K_M.gguf) | Q3_K_M | 3 | 32.58 GB| 35.08 GB | very small, high quality loss |
| [deepseek-llm-67b-base.Q3_K_L.gguf](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF/blob/main/deepseek-llm-67b-base.Q3_K_L.gguf) | Q3_K_L | 3 | 35.58 GB| 38.08 GB | small, substantial quality loss |
| [deepseek-llm-67b-base.Q4_0.gguf](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF/blob/main/deepseek-llm-67b-base.Q4_0.gguf) | Q4_0 | 4 | 38.15 GB| 40.65 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [deepseek-llm-67b-base.Q4_K_S.gguf](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF/blob/main/deepseek-llm-67b-base.Q4_K_S.gguf) | Q4_K_S | 4 | 38.25 GB| 40.75 GB | small, greater quality loss |
| [deepseek-llm-67b-base.Q4_K_M.gguf](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF/blob/main/deepseek-llm-67b-base.Q4_K_M.gguf) | Q4_K_M | 4 | 40.44 GB| 42.94 GB | medium, balanced quality - recommended |
| [deepseek-llm-67b-base.Q5_0.gguf](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF/blob/main/deepseek-llm-67b-base.Q5_0.gguf) | Q5_0 | 5 | 46.48 GB| 48.98 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [deepseek-llm-67b-base.Q5_K_S.gguf](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF/blob/main/deepseek-llm-67b-base.Q5_K_S.gguf) | Q5_K_S | 5 | 46.48 GB| 48.98 GB | large, low quality loss - recommended |
| [deepseek-llm-67b-base.Q5_K_M.gguf](https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF/blob/main/deepseek-llm-67b-base.Q5_K_M.gguf) | Q5_K_M | 5 | 47.65 GB| 50.15 GB | large, very low quality loss - recommended |
| deepseek-llm-67b-base.Q6_K.gguf | Q6_K | 6 | 55.32 GB| 57.82 GB | very large, extremely low quality loss |
| deepseek-llm-67b-base.Q8_0.gguf | Q8_0 | 8 | 71.65 GB| 74.15 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
### Q6_K and Q8_0 files are split and require joining
**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
<details>
<summary>Click for instructions regarding Q6_K and Q8_0 files</summary>
### q6_K
Please download:
* `deepseek-llm-67b-base.Q6_K.gguf-split-a`
* `deepseek-llm-67b-base.Q6_K.gguf-split-b`
### q8_0
Please download:
* `deepseek-llm-67b-base.Q8_0.gguf-split-a`
* `deepseek-llm-67b-base.Q8_0.gguf-split-b`
To join the files, do the following:
Linux and macOS:
```
cat deepseek-llm-67b-base.Q6_K.gguf-split-* > deepseek-llm-67b-base.Q6_K.gguf && rm deepseek-llm-67b-base.Q6_K.gguf-split-*
cat deepseek-llm-67b-base.Q8_0.gguf-split-* > deepseek-llm-67b-base.Q8_0.gguf && rm deepseek-llm-67b-base.Q8_0.gguf-split-*
```
Windows command line:
```
COPY /B deepseek-llm-67b-base.Q6_K.gguf-split-a + deepseek-llm-67b-base.Q6_K.gguf-split-b deepseek-llm-67b-base.Q6_K.gguf
del deepseek-llm-67b-base.Q6_K.gguf-split-a deepseek-llm-67b-base.Q6_K.gguf-split-b
COPY /B deepseek-llm-67b-base.Q8_0.gguf-split-a + deepseek-llm-67b-base.Q8_0.gguf-split-b deepseek-llm-67b-base.Q8_0.gguf
del deepseek-llm-67b-base.Q8_0.gguf-split-a deepseek-llm-67b-base.Q8_0.gguf-split-b
```
</details>
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/deepseek-llm-67b-base-GGUF and below it, a specific filename to download, such as: deepseek-llm-67b-base.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/deepseek-llm-67b-base-GGUF deepseek-llm-67b-base.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/deepseek-llm-67b-base-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/deepseek-llm-67b-base-GGUF deepseek-llm-67b-base.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m deepseek-llm-67b-base.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./deepseek-llm-67b-base.Q4_K_M.gguf", # Download the model file first
n_ctx=4096, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"{prompt}", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./deepseek-llm-67b-base.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: DeepSeek's Deepseek LLM 67B Base
<p align="center">
<img width="500px" alt="DeepSeek Chat" src="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/logo.png?raw=true">
</p>
<p align="center"><a href="https://www.deepseek.com/">[🏠Homepage]</a> | <a href="https://chat.deepseek.com/">[🤖 Chat with DeepSeek LLM]</a> | <a href="https://discord.gg/Tc7c45Zzu5">[Discord]</a> | <a href="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/qr.jpeg">[Wechat(微信)]</a> </p>
<hr>
### 1. Introduction of Deepseek LLM
Introducing DeepSeek LLM, an advanced language model comprising 67 billion parameters. It has been trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese. In order to foster research, we have made DeepSeek LLM 7B/67B Base and DeepSeek LLM 7B/67B Chat open source for the research community.
### 2. Model Summary
`deepseek-llm-67b-base` is a 67B parameter model with Grouped-Query Attention trained on 2 trillion tokens from scratch.
- **Home Page:** [DeepSeek](https://deepseek.com/)
- **Repository:** [deepseek-ai/deepseek-LLM](https://github.com/deepseek-ai/deepseek-LLM)
- **Chat With DeepSeek LLM:** [DeepSeek-LLM](https://chat.deepseek.com/)
### 3. How to Use
Here give some examples of how to use our model.
#### Text Completion
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
model_name = "deepseek-ai/deepseek-llm-67b-base"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id
text = "An attention function can be described as mapping a query and a set of key-value pairs to an output, where the query, keys, values, and output are all vectors. The output is"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs.to(model.device), max_new_tokens=100)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```
### 4. License
This code repository is licensed under the MIT License. The use of DeepSeek LLM models is subject to the Model License. DeepSeek LLM supports commercial use.
See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-LLM/blob/main/LICENSE-MODEL) for more details.
### 5. Contact
If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]).
<!-- original-model-card end -->
|
notdiamond/notdiamond-0001
|
notdiamond
| 2024-03-20T05:10:01Z | 376 | 112 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-12-12T02:13:59Z |
---
license: apache-2.0
---
# notdiamond-0001
notdiamond-0001 automatically determines whether to send queries to GPT-3.5 or GPT-4, depending on which model is best-suited for your task. We've trained notdiamond-0001 on hundreds of thousands of data points from robust, cross-domain evaluation benchmarks.
Our router is free to use under the Apache 2.0 license. You can also access the model through our free [API](https://www.notdiamond.ai/notdiamond-0001).
The notdiamond-0001 router model is a classifier and will return a label for either GPT-3.5 or GPT-4. You determine which version of each model you want to use and make the calls client-side with your own keys.
To use notdiamond-0001, format your queries using the following prompt with your query appended at the end
``` python
query = "Can you write a function that counts from 1 to 10?"
formatted_prompt = f"""Determine whether the following query should be sent to GPT-3.5 or GPT-4.
Query:
{query}"""
```
You can then determine the model to call as follows
``` python
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
id2label = {0: 'gpt-3.5', 1: 'gpt-4'}
tokenizer = AutoTokenizer.from_pretrained("notdiamond/notdiamond-0001")
model = AutoModelForSequenceClassification.from_pretrained("notdiamond/notdiamond-0001")
inputs = tokenizer(formatted_prompt, truncation=True, max_length=512, return_tensors="pt")
logits = model(**inputs).logits
model_id = logits.argmax().item()
model_to_call = id2label[model_id]
```
For more details on how you can integrate this into your techstack and use notdiamond-0001 to improve quality while reducing latency and cost, check out our [documentation](https://notdiamond.readme.io/docs/introduction).
|
TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF
|
TheBloke
| 2023-12-17T15:28:20Z | 376 | 9 |
transformers
|
[
"transformers",
"gguf",
"mistral",
"text-generation",
"en",
"base_model:maywell/PiVoT-10.7B-Mistral-v0.2-RP",
"license:cc-by-sa-4.0",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-12-17T15:22:05Z |
---
base_model: maywell/PiVoT-10.7B-Mistral-v0.2-RP
inference: false
language:
- en
license: cc-by-sa-4.0
model_creator: Jeonghwan Park
model_name: Pivot 10.7B Mistral V0.2 RP
model_type: mistral
pipeline_tag: text-generation
prompt_template: '[INST] {prompt} [/INST]
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Pivot 10.7B Mistral V0.2 RP - GGUF
- Model creator: [Jeonghwan Park](https://huggingface.co/maywell)
- Original model: [Pivot 10.7B Mistral V0.2 RP](https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2-RP)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Jeonghwan Park's Pivot 10.7B Mistral V0.2 RP](https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2-RP).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF)
* [Jeonghwan Park's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2-RP)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Mistral
```
[INST] {prompt} [/INST]
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [pivot-10.7b-mistral-v0.2-rp.Q2_K.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q2_K.gguf) | Q2_K | 2 | 4.55 GB| 7.05 GB | smallest, significant quality loss - not recommended for most purposes |
| [pivot-10.7b-mistral-v0.2-rp.Q3_K_S.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q3_K_S.gguf) | Q3_K_S | 3 | 4.67 GB| 7.17 GB | very small, high quality loss |
| [pivot-10.7b-mistral-v0.2-rp.Q3_K_M.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q3_K_M.gguf) | Q3_K_M | 3 | 5.19 GB| 7.69 GB | very small, high quality loss |
| [pivot-10.7b-mistral-v0.2-rp.Q3_K_L.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q3_K_L.gguf) | Q3_K_L | 3 | 5.65 GB| 8.15 GB | small, substantial quality loss |
| [pivot-10.7b-mistral-v0.2-rp.Q4_0.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q4_0.gguf) | Q4_0 | 4 | 6.07 GB| 8.57 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [pivot-10.7b-mistral-v0.2-rp.Q4_K_S.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q4_K_S.gguf) | Q4_K_S | 4 | 6.10 GB| 8.60 GB | small, greater quality loss |
| [pivot-10.7b-mistral-v0.2-rp.Q4_K_M.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q4_K_M.gguf) | Q4_K_M | 4 | 6.46 GB| 8.96 GB | medium, balanced quality - recommended |
| [pivot-10.7b-mistral-v0.2-rp.Q5_0.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q5_0.gguf) | Q5_0 | 5 | 7.40 GB| 9.90 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [pivot-10.7b-mistral-v0.2-rp.Q5_K_S.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q5_K_S.gguf) | Q5_K_S | 5 | 7.40 GB| 9.90 GB | large, low quality loss - recommended |
| [pivot-10.7b-mistral-v0.2-rp.Q5_K_M.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q5_K_M.gguf) | Q5_K_M | 5 | 7.60 GB| 10.10 GB | large, very low quality loss - recommended |
| [pivot-10.7b-mistral-v0.2-rp.Q6_K.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q6_K.gguf) | Q6_K | 6 | 8.81 GB| 11.31 GB | very large, extremely low quality loss |
| [pivot-10.7b-mistral-v0.2-rp.Q8_0.gguf](https://huggingface.co/TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF/blob/main/pivot-10.7b-mistral-v0.2-rp.Q8_0.gguf) | Q8_0 | 8 | 11.41 GB| 13.91 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF and below it, a specific filename to download, such as: pivot-10.7b-mistral-v0.2-rp.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF pivot-10.7b-mistral-v0.2-rp.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/PiVoT-10.7B-Mistral-v0.2-RP-GGUF pivot-10.7b-mistral-v0.2-rp.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m pivot-10.7b-mistral-v0.2-rp.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] {prompt} [/INST]"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./pivot-10.7b-mistral-v0.2-rp.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"[INST] {prompt} [/INST]", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./pivot-10.7b-mistral-v0.2-rp.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Jeonghwan Park's Pivot 10.7B Mistral V0.2 RP
# PiVoT-10.7B-Mistral-v0.2-RP
# **Model Details**
### Description
PivoT is RP Finetuned model based on PiVoT-10.7B-Mistral-v0.2. Private RP dataset collected from ArcaLive Ai Chat Chan used.
This model has sequence length(Sliding Window) of **8192**
Follow me on twitter: https://twitter.com/stablefluffy
Consider Support me making these model alone: https://www.buymeacoffee.com/mwell or with Runpod Credit Gift 💕
Contact me on Telegram: https://t.me/AlzarTakkarsen
<!-- original-model-card end -->
|
gayane/BARTSmiles
|
gayane
| 2024-01-10T14:05:02Z | 376 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"feature-extraction",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2024-01-04T06:54:55Z |
The repository is adapted based on: https://huggingface.co/chenxran/bart-smiles/tree/main
```python
from transformers import AutoTokenizer, AutoModel, SequenceFeatureExtractor
import torch
from transformers import AutoTokenizer, AutoModel
smiles = "CCC(=O)"
tokenizer = AutoTokenizer.from_pretrained("./BARTSmiles/", add_prefix_space=True)
inputs = tokenizer(smiles, return_tensors="pt", return_token_type_ids=False, add_special_tokens=True)
model = AutoModel.from_pretrained('./BARTSmiles')
model.eval()
# Use a pipeline as a high-level helper
from transformers import pipeline
extractor = pipeline("feature-extraction", model=model, tokenizer=tokenizer)
result = extractor(smiles, return_tensors=True, tokenize_kwargs={'return_token_type_ids':False})
```
## Citation
@article{chilingaryan2022bartsmiles,
title={Bartsmiles: Generative masked language models for molecular representations},
author={Chilingaryan, Gayane and Tamoyan, Hovhannes and Tevosyan, Ani and Babayan, Nelly and Khondkaryan, Lusine and Hambardzumyan, Karen and Navoyan, Zaven and Khachatrian, Hrant and Aghajanyan, Armen},
journal={arXiv preprint arXiv:2211.16349},
year={2022}
}
|
TheBloke/Sensualize-Solar-10.7B-GGUF
|
TheBloke
| 2024-01-06T22:58:30Z | 376 | 10 |
transformers
|
[
"transformers",
"gguf",
"solar",
"en",
"base_model:Sao10K/Sensualize-Solar-10.7B",
"license:cc-by-nc-4.0",
"region:us"
] | null | 2024-01-06T22:53:40Z |
---
base_model: Sao10K/Sensualize-Solar-10.7B
inference: false
language:
- en
license: cc-by-nc-4.0
model_creator: Saofiq
model_name: Sensualize Solar 10.7B
model_type: solar
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Sensualize Solar 10.7B - GGUF
- Model creator: [Saofiq](https://huggingface.co/Sao10K)
- Original model: [Sensualize Solar 10.7B](https://huggingface.co/Sao10K/Sensualize-Solar-10.7B)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Saofiq's Sensualize Solar 10.7B](https://huggingface.co/Sao10K/Sensualize-Solar-10.7B).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF)
* [Saofiq's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Sao10K/Sensualize-Solar-10.7B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [sensualize-solar-10.7b.Q2_K.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q2_K.gguf) | Q2_K | 2 | 4.55 GB| 7.05 GB | smallest, significant quality loss - not recommended for most purposes |
| [sensualize-solar-10.7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q3_K_S.gguf) | Q3_K_S | 3 | 4.66 GB| 7.16 GB | very small, high quality loss |
| [sensualize-solar-10.7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q3_K_M.gguf) | Q3_K_M | 3 | 5.19 GB| 7.69 GB | very small, high quality loss |
| [sensualize-solar-10.7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q3_K_L.gguf) | Q3_K_L | 3 | 5.65 GB| 8.15 GB | small, substantial quality loss |
| [sensualize-solar-10.7b.Q4_0.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q4_0.gguf) | Q4_0 | 4 | 6.07 GB| 8.57 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [sensualize-solar-10.7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q4_K_S.gguf) | Q4_K_S | 4 | 6.10 GB| 8.60 GB | small, greater quality loss |
| [sensualize-solar-10.7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q4_K_M.gguf) | Q4_K_M | 4 | 6.46 GB| 8.96 GB | medium, balanced quality - recommended |
| [sensualize-solar-10.7b.Q5_0.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q5_0.gguf) | Q5_0 | 5 | 7.40 GB| 9.90 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [sensualize-solar-10.7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q5_K_S.gguf) | Q5_K_S | 5 | 7.40 GB| 9.90 GB | large, low quality loss - recommended |
| [sensualize-solar-10.7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q5_K_M.gguf) | Q5_K_M | 5 | 7.60 GB| 10.10 GB | large, very low quality loss - recommended |
| [sensualize-solar-10.7b.Q6_K.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q6_K.gguf) | Q6_K | 6 | 8.81 GB| 11.31 GB | very large, extremely low quality loss |
| [sensualize-solar-10.7b.Q8_0.gguf](https://huggingface.co/TheBloke/Sensualize-Solar-10.7B-GGUF/blob/main/sensualize-solar-10.7b.Q8_0.gguf) | Q8_0 | 8 | 11.40 GB| 13.90 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/Sensualize-Solar-10.7B-GGUF and below it, a specific filename to download, such as: sensualize-solar-10.7b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Sensualize-Solar-10.7B-GGUF sensualize-solar-10.7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Sensualize-Solar-10.7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Sensualize-Solar-10.7B-GGUF sensualize-solar-10.7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m sensualize-solar-10.7b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./sensualize-solar-10.7b.Q4_K_M.gguf", # Download the model file first
n_ctx=4096, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./sensualize-solar-10.7b.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Saofiq's Sensualize Solar 10.7B
A finetune of Base Solar. Took 12 Hours or so on 2x RTX 6000 ADAs, this is an 8-bit LoRA.
This is meant to be a verbose, smart ERP model.
Experimental.
***
### Prompt Format: Alpaca
```
### Instruction:
<Prompt>
### Input:
<Insert Context Here>
### Response:
```
<!-- original-model-card end -->
|
TheBloke/Everyone-Coder-4x7b-Base-GGUF
|
TheBloke
| 2024-01-15T12:40:32Z | 376 | 11 |
transformers
|
[
"transformers",
"gguf",
"mixtral",
"merge",
"moe",
"base_model:rombodawg/Everyone-Coder-4x7b-Base",
"license:cc-by-4.0",
"text-generation-inference",
"region:us"
] | null | 2024-01-15T12:31:51Z |
---
base_model: rombodawg/Everyone-Coder-4x7b-Base
inference: false
license: cc-by-4.0
model_creator: rombo dawg
model_name: Everyone Coder 4X7B Base
model_type: mixtral
prompt_template: '{prompt}
'
quantized_by: TheBloke
tags:
- merge
- moe
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Everyone Coder 4X7B Base - GGUF
- Model creator: [rombo dawg](https://huggingface.co/rombodawg)
- Original model: [Everyone Coder 4X7B Base](https://huggingface.co/rombodawg/Everyone-Coder-4x7b-Base)
<!-- description start -->
## Description
This repo contains GGUF format model files for [rombo dawg's Everyone Coder 4X7B Base](https://huggingface.co/rombodawg/Everyone-Coder-4x7b-Base).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Everyone-Coder-4x7b-Base-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Everyone-Coder-4x7b-Base-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Everyone-Coder-4x7b-Base-GGUF)
* [rombo dawg's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/rombodawg/Everyone-Coder-4x7b-Base)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Unknown
```
{prompt}
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [everyone-coder-4x7b-base.Q2_K.gguf](https://huggingface.co/TheBloke/Everyone-Coder-4x7b-Base-GGUF/blob/main/everyone-coder-4x7b-base.Q2_K.gguf) | Q2_K | 2 | 8.82 GB| 11.32 GB | smallest, significant quality loss - not recommended for most purposes |
| [everyone-coder-4x7b-base.Q3_K_M.gguf](https://huggingface.co/TheBloke/Everyone-Coder-4x7b-Base-GGUF/blob/main/everyone-coder-4x7b-base.Q3_K_M.gguf) | Q3_K_M | 3 | 11.58 GB| 14.08 GB | very small, high quality loss |
| [everyone-coder-4x7b-base.Q4_0.gguf](https://huggingface.co/TheBloke/Everyone-Coder-4x7b-Base-GGUF/blob/main/everyone-coder-4x7b-base.Q4_0.gguf) | Q4_0 | 4 | 13.62 GB| 16.12 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [everyone-coder-4x7b-base.Q4_K_M.gguf](https://huggingface.co/TheBloke/Everyone-Coder-4x7b-Base-GGUF/blob/main/everyone-coder-4x7b-base.Q4_K_M.gguf) | Q4_K_M | 4 | 14.61 GB| 17.11 GB | medium, balanced quality - recommended |
| [everyone-coder-4x7b-base.Q5_0.gguf](https://huggingface.co/TheBloke/Everyone-Coder-4x7b-Base-GGUF/blob/main/everyone-coder-4x7b-base.Q5_0.gguf) | Q5_0 | 5 | 16.63 GB| 19.13 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [everyone-coder-4x7b-base.Q5_K_M.gguf](https://huggingface.co/TheBloke/Everyone-Coder-4x7b-Base-GGUF/blob/main/everyone-coder-4x7b-base.Q5_K_M.gguf) | Q5_K_M | 5 | 17.13 GB| 19.63 GB | large, very low quality loss - recommended |
| [everyone-coder-4x7b-base.Q6_K.gguf](https://huggingface.co/TheBloke/Everyone-Coder-4x7b-Base-GGUF/blob/main/everyone-coder-4x7b-base.Q6_K.gguf) | Q6_K | 6 | 19.82 GB| 22.32 GB | very large, extremely low quality loss |
| [everyone-coder-4x7b-base.Q8_0.gguf](https://huggingface.co/TheBloke/Everyone-Coder-4x7b-Base-GGUF/blob/main/everyone-coder-4x7b-base.Q8_0.gguf) | Q8_0 | 8 | 25.67 GB| 28.17 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/Everyone-Coder-4x7b-Base-GGUF and below it, a specific filename to download, such as: everyone-coder-4x7b-base.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Everyone-Coder-4x7b-Base-GGUF everyone-coder-4x7b-base.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Everyone-Coder-4x7b-Base-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Everyone-Coder-4x7b-Base-GGUF everyone-coder-4x7b-base.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m everyone-coder-4x7b-base.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./everyone-coder-4x7b-base.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"{prompt}", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./everyone-coder-4x7b-base.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: rombo dawg's Everyone Coder 4X7B Base
Everyone-Coder-4x7b-Base
EveryoneLLM series of models are a new Mixtral type model created using experts that were finetuned by the community, for the community. This is the first model to release in the series and it is a coding specific model. EveryoneLLM, which will be a more generalized model, will be released in the near future after more work is done to fine tune the process of merging Mistral models into a larger Mixtral models with greater success.
The goal of the EveryoneLLM series of models is to be a replacement or an alternative to Mixtral-8x7b that is more suitable for general and specific use, as well as easier to fine tune. Since Mistralai is being secretive about the "secret sause" that makes Mixtral-Instruct such an effective fine tune of the Mixtral-base model, I've decided its time for the community to directly compete with Mistralai on our own.
The models that were used in this merger were as follow:
- https://huggingface.co/fblgit/UNA-TheBeagle-7b-v1
- https://huggingface.co/LucciAI/openchat-3.5-0106-function-calling
- https://huggingface.co/WizardLM/WizardMath-7B-V1.1
- https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
Thank you to the creators of the above ai models, they have full credit for the EveryoneLLM series of models. Without their hard work we wouldnt be able to achieve the great success we have in the open source community. 💗
You can find the write up for this model here:
https://docs.google.com/document/d/1_vOftBnrk9NRk5h10UqrfJ5CDih9KBKL61yvrZtVWPE/edit?usp=sharing
Config for the merger can be found bellow:
```
base_model: mistralai_Mistral-7B-v0.1
gate_mode: hidden
dtype: float16
experts:
- source_model: cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser
positive_prompts:
- "Help me debug this code."
- "Rewrite this function in Python."
- "Optimize this C# script."
- "Implement this feature using JavaScript."
- "Convert this HTML structure into a more efficient design."
- "Assist me with writing a program that"
- source_model: fblgit_UNA-TheBeagle-7b-v1
positive_prompts:
- "How do you"
- "Explain the concept of"
- "Give an overview of"
- "Compare and contrast between"
- "Provide information about"
- "Help me understand"
- "Summarize"
- "Make a recommendation on"
- "Answer this question"
- source_model: LucciAI_openchat-3.5-0106-function-calling
positive_prompts:
- "Write a program to solve this problem"
- "Modify this function to improve its performance"
- "Refactor this code to enhance readability"
- "Create a custom function for this specific use case"
- "Optimize this algorithm to reduce computational complexity"
- "Implement this feature by extending existing codebase"
- "Integrate this API call into the application"
- "Help me troubleshoot and fix this bug"
- "Review and test this code snippet before deployment"
- "Analyze this error log to identify potential issues"
- "Generate a set of unit tests for this module"
- "Evaluate different approaches to solving this problem"
- "Do a web search for"
- "Use the plugin to"
- source_model: WizardLM_WizardMath-7B-V1.1
positive_prompts:
- "add these numbers"
- "whats 2+2"
- "subtraction"
- "division"
- "multiplication"
- "addition"
- "I need help with a math problem"
- "Solve for x"
- "Add these two numbers together: 4 + 3 = 7"
- "Multiply 5 by 6: 5 * 6 = 30"
- "Divide 8 by 2: 8 / 2 = 4"
- "Find the remainder when 9 is divided by 3: 9 % 3 = 0"
- "Calculate the square root of 16: sqrt(16) = 4"
- "Simplify the expression (a+b)/(c-d): (a+b)/(c-d)"
- "Factor out the common factor of 2 from 4x + 6y: 2(2x + 3y)"
- "Solve for x in the equation 3x - 7 = 2x + 5: x = 12"
- "Graph the line y = 2x + 3"
- "Approximate pi to three decimal places: 3.142"
- "Find the derivative of f(x) = sin(x): f'(x) = cos(x)"
- "Integrate g(x) = x^2 over the interval [0, 1]: g(1) - g(0) = 1/3"
- "Calculate the determinant of the matrix A = [[2, 3], [4, 5]]: det(A) = 2*5 - 3*4 = -2"
- "Solve the system of equations Ax = b: x = [-5, 10]"
- "Calculate the sum of the first n natural numbers using the formula Sn = n*(n+1)/2: sum(n=1 to 5) = 15"
```
<!-- original-model-card end -->
|
Stelath/textual_inversion_comic_strip_turbo
|
Stelath
| 2024-02-11T09:01:11Z | 376 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"textual_inversion",
"base_model:stabilityai/sdxl-turbo",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] |
text-to-image
| 2024-02-11T05:27:48Z |
---
license: creativeml-openrail-m
base_model: stabilityai/sdxl-turbo
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- textual_inversion
inference: true
---
# Textual inversion text2image fine-tuning - Stelath/textual_inversion_comic_strip_turbo
These are textual inversion adaption weights for stabilityai/sdxl-turbo. You can find some example images in the following.
|
mlabonne/AlphaMonarch-7B-GGUF
|
mlabonne
| 2024-03-28T17:31:36Z | 376 | 34 | null |
[
"gguf",
"region:us"
] | null | 2024-02-14T19:27:43Z |
Entry not found
|
ChrisWilson011016/5His2oaJ68NfPPN5VzXswzt2gdfscX43THB1DW9R9xjcLCKD_vgg
|
ChrisWilson011016
| 2024-03-04T18:52:39Z | 376 | 0 |
keras
|
[
"keras",
"region:us"
] | null | 2024-02-24T15:14:25Z |
Entry not found
|
manbeast3b/stable_kid5
|
manbeast3b
| 2024-03-28T14:50:06Z | 376 | 0 |
transformers
|
[
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-03-28T14:48:33Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
mradermacher/Esper-70b-GGUF
|
mradermacher
| 2024-05-06T05:21:18Z | 376 | 0 |
transformers
|
[
"transformers",
"gguf",
"esper",
"dev-ops",
"developer",
"code",
"code-instruct",
"valiant",
"valiant-labs",
"code-llama",
"llama",
"llama-2",
"llama-2-chat",
"70b",
"en",
"base_model:ValiantLabs/Esper-70b",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-03T07:05:24Z |
---
base_model: ValiantLabs/Esper-70b
language:
- en
library_name: transformers
license: apache-2.0
model_type: llama
quantized_by: mradermacher
tags:
- esper
- dev-ops
- developer
- code
- code-instruct
- valiant
- valiant-labs
- code-llama
- llama
- llama-2
- llama-2-chat
- 70b
---
## About
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/ValiantLabs/Esper-70b
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q2_K.gguf) | Q2_K | 26.4 | |
| [GGUF](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.IQ3_XS.gguf) | IQ3_XS | 29.2 | |
| [GGUF](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.IQ3_S.gguf) | IQ3_S | 30.9 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q3_K_S.gguf) | Q3_K_S | 30.9 | |
| [GGUF](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.IQ3_M.gguf) | IQ3_M | 31.9 | |
| [GGUF](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q3_K_M.gguf) | Q3_K_M | 34.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q3_K_L.gguf) | Q3_K_L | 37.1 | |
| [GGUF](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.IQ4_XS.gguf) | IQ4_XS | 38.1 | |
| [GGUF](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q4_K_S.gguf) | Q4_K_S | 40.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q4_K_M.gguf) | Q4_K_M | 42.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q5_K_S.gguf) | Q5_K_S | 48.4 | |
| [PART 1](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q5_K_M.gguf.part2of2) | Q5_K_M | 49.7 | |
| [PART 1](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q6_K.gguf.part2of2) | Q6_K | 57.5 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Esper-70b-GGUF/resolve/main/Esper-70b.Q8_0.gguf.part2of2) | Q8_0 | 74.2 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
ZoneTwelve/TAIDE-LX-7B-GGUF
|
ZoneTwelve
| 2024-04-19T03:39:52Z | 376 | 6 | null |
[
"gguf",
"license:other",
"region:us"
] | null | 2024-04-15T09:22:57Z |
---
license: other
license_name: license
license_link: LICENSE
---
* [English Version](./README_en.md)
# 模型簡介
* [TAIDE計畫](https://taide.tw/index)致力於開發符合台灣語言和文化特性的生成式人工智慧對話引擎模型，同時建構可信任的人工智慧環境。結合產學研能量，推動可信任生成式人工智慧的發展，提升台灣在國際競爭中的地位，促進產業發展，避免對外國技術的依賴。
* 本計畫開發的大型語言模型以 Meta 公司釋出的 [LLaMA2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf) 為基礎，導入台灣不同領域可用的文本與訓練素材，提高模型在正體中文回應的能力與特定任務的表現。公開釋出的模型如下:
* [TAIDE-LX-7B](https://huggingface.co/taide/TAIDE-LX-7B): 以 LLaMA2-7b 為基礎，僅使用繁體中文資料預訓練 (continuous pretraining)的模型，適合使用者會對模型進一步微調(fine tune)的使用情境。因預訓練模型沒有經過微調和偏好對齊，可能會產生惡意或不安全的輸出，使用時請小心。
* [TAIDE-LX-7B-Chat](https://huggingface.co/taide/TAIDE-LX-7B-Chat): 以 TAIDE-LX-7B 為基礎，透過指令微調(instruction tuning)強化辦公室常用任務和多輪問答對話能力，適合聊天對話或任務協助的使用情境。TAIDE-LX-7B-Chat另外有提供[4 bit 量化模型](https://huggingface.co/taide/TAIDE-LX-7B-Chat-4bit)，量化模型主要是提供使用者的便利性，可能會影響效能與更多不可預期的問題，還請使用者理解與注意。
# 模型參數
* 參數量: 7B
* 最大內容長度 (context length): 4K
* 繁中訓練資料 token 量: 41.44B
* 訓練時間: 1531.82 H100 GPU Hours
# 特色
* 額外擴充24720個中文字元、字詞，強化模型處理繁體中文的能力
* 嚴格把關模型的訓練資料，提升模型生成資料的可信任性和適用性
* 針對自動摘要、寫信、寫文章、中翻英、英翻中等辦公室常用任務做加強
* 針對台灣在地文化、用語、國情等知識做加強
* 具備多輪問答對話能力
# 應用範例
| 任務 | 使用者輸入 | 模型輸出 |
| --- | -------- | ------- |
| 寫文章 | 請以以下內容為基礎，寫一篇文章：撰寫一篇作文，題目為《一張舊照片》，內容要求為：選擇一張令你印象深刻的照片，說明令你印象深刻的原因，並描述照片中的影像及背後的故事。記錄成長的過程、與他人的情景、環境變遷和美麗的景色。 | 以下是根據指令創作的一篇作文：<br><br>《一張舊照片》<br><br>在我塵封已久的家族相簿中，有一張特別吸引我的舊照片，那張照片記錄了我們家族成員在過往美好時光的歡聚，至今仍舊令人回味無窮。這張照片是我奶奶在二十多年前舉辦的一場家族聚會上所拍下的，照片中的人物包括了我的父母、祖父母、叔叔、姑姑和表哥等，大家臉上洋溢著幸福的笑容，彷彿時光靜止般地美好。<br><br>照片中的場景十分溫馨，大家圍坐在一張長方形的餐桌上，桌上擺滿了美味的食物和飲料。桌上的菜餚是傳統中式的佳餚，有香噴噴的烤全魚、嫩滑的雞肉和鮮甜的蔬菜，這些菜餚是當年奶奶親自烹調的，她手藝精湛，讓每個人都吃得津津有味。<br><br>最讓我印象深刻的是，照片中還拍到了我年幼時的模樣。我坐在桌子的另一端，手裡拿著一碗湯，臉上帶著滿足的笑容。那時的我才剛滿周歲，對於這場盛大的家族聚會還感到十分新奇。從這張照片中，我能感受到當年家族成員間的親密和溫暖，即使過了這麼多年，那份情感卻依然牢固地存在著。<br><br>這張照片背後有著動人的故事。在那個時代，我的祖父母和父母都還在讀中學，他們每天都會放學後到農田裡幫忙，辛勤地耕作以維持一家人的生計。儘管生活條件並不富裕，但他們仍舊保持著樂觀的態度和對生活的熱愛。每年到了秋天，只要收獲季節來臨，他們就會舉辦家族聚會，邀請所有親戚朋友前來共享豐收的喜悅。<br><br>隨著歲月的流逝，我逐漸長大，開始工作和生活。每次回鄉，我都會抽空去探望老人家，聽聽他們當年的往事，感受那段刻骨銘心的時光。而這張舊照片，也將一直陪伴著我，成為我珍貴回憶的一部分。它見證了我們的成長和變遷，也記錄下了那些難以忘懷的美好時刻。<br><br>這張照片不僅展示了家族的親情和溫暖，還折射出那個時代人們勤勞樸實的生活方式和對傳統的尊重。如今，隨著社會的快速發展，許多傳統的美德和風俗正在逐漸消失。我們應該好好珍惜這樣的回憶和文化，將它們傳承下去，讓後代子孫也能感受到那份來自歷史的溫情和傳承。<br><br>因此，我決定將這張照片好好保管起來，並常常拿出來看。它不僅是一張舊照片，更是一段寶貴的回憶和家族精神的象徵。我希望未來能有機會重現當年的盛況，再一次聚在一起，分享彼此的生活和故事，讓那份親情和友情繼續在時光中蔓延，永不消逝。 |
| 寫信 | 請以品牌經理的身份，給廣告公司的創意總監寫一封信，提出對於新產品廣告宣傳活動的創意建議。 | 尊敬的創意總監：<br><br>我寫這封信是為了向您提出一些關於我們新產品廣告宣傳活動的創意建議。我們公司即將推出一款全新的產品，為了確保它在市場上取得成功，我們希望透過一個引人注目的廣告宣傳活動來吸引消費者的注意。<br><br>在考慮廣告的創意和策略時，有幾個因素需要納入考量。首先，我們要針對目標客群進行研究，以瞭解他們的需求和喜好。其次，我們要確保廣告內容具有吸引力和說服力，能引起目標客群的共鳴。最後，我們要利用各種媒體平臺和數位行銷工具，以擴大廣告的影響力。<br><br>基於這些因素，我提出以下幾點創意建議：<br><br>1. 產品定位：我們可將這款新產品定位為高端、環保、健康和時尚的代表，強調其獨有的功能和特色。在廣告中，我們可以透過生動的視覺效果和簡潔的語言來傳達這些特點。<br>2. 故事行銷：在廣告中講述一個與產品功能相關的動人故事，讓消費者能更深入地瞭解產品所帶來的生活變化。例如，我們可以講述一位忙碌的職業婦女，如何使用我們的新產品在工作和生活中取得平衡的故事。<br>3. 名人效應：邀請一位受歡迎的公眾人物或意見領袖擔任產品代言人，利用他們的影響力來推廣產品。這不僅可以增加產品曝光度，還能讓更多消費者信任和信賴產品。<br>4. 跨界合作：與一些相關產業（如時尚、環保、健康等）進行跨界合作，共同推出限量版或聯名產品。這種合作不僅能吸引不同領域的消費者，還能為產品帶來更多話題性和收藏價值。<br>5. 數位行銷：充分利用社群媒體、搜尋引擎和電郵行銷等數位工具，在整個廣告宣傳過程中保持一致性的訊息和形象。我們也可製作一系列短視頻和線上活動，以增加消費者參與度和品牌忠誠度。<br>6. 創新形式：嘗試使用新穎的廣告形式，如AR（擴增實境）、VR（虛擬實境）和360度影片等，給消費者帶來全新的廣告體驗。這種創新形式不僅能吸引消費者目光，還能提高產品在市場上的辨識度。<br>7. 活動參與：在廣告宣傳活動中加入互動環節，如產品試用、抽獎和優惠券等，鼓勵消費者積極參與並分享他們的體驗。這將有助於口碑傳播，進一步擴大產品影響力。<br><br>綜合以上建議，我希望我們能製定出一套全面而富有創意的廣告宣傳活動計劃，以最大限度地提升新產品在市場上的競爭力。如果您有任何疑問或需要進一步討論，歡迎隨時與我聯絡。謝謝您的關注和支援！<br><br>祝商祺！<br><br>您的品牌經理<br><br>（註：此信件可根據實際情況和產品特點進行調整） |
| 摘要 | 請將這篇文章精簡條理化:「產業創新條例第10條之2及第72條條文修正案」俗稱「台版晶片法」,針對半導體、電動車、5G等技術創新且居國際供應鏈關鍵地位公司,提供最高25%營所稅投抵優惠,企業適用要件包含當年度研發費用、研發密度達一定規模,且有效稅率達一定比率。<br>為因應經濟合作暨發展組織(OECD)國家最低稅負制調整,其中有效稅率門檻,民國112年訂為12%,113年料將提高至15%,但仍得審酌國際間最低稅負制實施情形。<br>經濟部官員表示,已和財政部協商進入最後階段,除企業研發密度訂在6%,目前已確認,企業購置先進製程的設備投資金額達100億元以上可抵減。<br>財政部官員表示,研商過程中,針對台灣產業與其在國際間類似的公司進行深入研究,在設備部分,畢竟適用產創10之2的業者是代表台灣隊打「國際盃」,投入金額不達100億元,可能也打不了。<br>至於備受關注的研發費用門檻,經濟部官員表示,歷經與財政部來回密切討論,研發費用門檻有望落在60億至70億元之間。<br>財政部官員指出,研發攸關台灣未來經濟成長動能,門檻不能「高不可攀」,起初雖設定在100億元,之所以會調降,正是盼讓企業覺得有辦法達得到門檻、進而適用租稅優惠,才有動力繼續投入研發,維持國際供應鏈關鍵地位。<br>經濟部官員表示,因廠商研發費用平均為30、40億元,其中,IC設計業者介於30億至60億元範圍,若將門檻訂在100億元,符合條件的業者較少、刺激誘因不足;此外,若符合申請門檻的業者增加,將可提高企業在台投資金額,財政部稅收也能因此獲得挹注。<br>IC設計業者近日頻頻針對產創10之2發聲,希望降低適用門檻,加上各國力拚供應鏈自主化、加碼補助半導體產業,經濟部官員表示,經濟部和財政部就產創10之2達成共識,爭取讓更多業者受惠,盼增強企業投資力道及鞏固台灣技術地位。<br>財政部官員表示,租稅獎勵的制定必須「有為有守」,並以達到獎勵設置目的為最高原則,現階段在打「國內盃」的企業仍可適用產創第10條、10之1的租稅優惠,共同壯大台灣經濟發展。<br>經濟部和財政部正就研發費用門檻做最後確認,待今明兩天預告子法之後,約有30天時間,可與業界進一步討論及調整,盼產創10之2能在6月上路。 | 台灣「產業創新條例」的修正案，又稱「台版晶片法」,旨在支持半導體、電動車及5G技術領先企業的創新。新政策提供最高25%的所得稅抵免，企業需滿足當年度研發費用達一定規模、研發密度超過6%以及有效稅率達一定比率等條件。因應國際間對企業最低稅負制度的調整，台灣的門檻預計分別於2023年和2024年達到12%和15%。目前，與財政部討論後，確定100億元的設備投資抵免是可行的誘因，且研發費用門檻預計會在60至70億元之間。對於降低門檻的要求，經濟部和財政部已達成共識，旨在擴大受惠範圍並鼓勵企業投資以維持供應鏈的關鍵地位。此外，針對IC設計業者的訴求，也考慮調降門檻。預計此法案將在近期內實施，相關討論和調整將在預告期後進一步進行。 |
| 翻譯 | 以下提供英文內容，請幫我翻譯成中文。Dongshan coffee is famous for its unique position, and the constant refinement of production methods. The flavor is admired by many caffeine afficionados. | 東山咖啡以得天獨厚的地位，不斷精研的製作工藝著稱，風味獲諸多咖啡愛好者推崇。 |
# 使用說明
* 範例程式
* 範例程式與文件後續會釋出到github
* prompt 樣版
* 一般問答用法
```
f"<s>[INST] {question} [/INST]"
```
* 將 {question} 替換成使用者的輸入
* 加入 system prompt 的用法
```
f"<s>[INST] <<SYS>>\n{sys}\n<</SYS>>\n\n{question} [/INST]"
```
* 將 {sys} 替換成指令，例如：你是一個來自台灣的AI助理，你的名字是 TAIDE，樂於以台灣人的立場幫助使用者，會用繁體中文回答問題。
* 將 {question} 替換成使用者的問題
* 多輪問答用法
```
f"<s>[INST] <<SYS>>\n{sys}\n<</SYS>>\n\n{question1} [/INST] {model_answer_1} </s><s>[INST] {question2} [/INST]"
```
* 將 {sys} 替換成指令
* 將 {question1} 替換成使用者的問題1
* 將 {model_anwer_1} 替換成模型的回答1
* 將 {question2} 替換成使用者的問題2
# 訓練方法
* 軟硬體規格
* 國網中心 H100
* 訓練框架: PyTorch
* 資料前處理
* 字元標準化
* 去除重覆
* 去除雜訊
* 網頁資料的html tag、javascript
* 非標準字元或亂碼
* 字數過短的文章
* 去除文章中的特定格式，如為排版增加的換行
* 去除個資，如email、電話
* 去除不當文字，如賭博、色情等
* 擴充字元字詞
* 強化繁體中文輸入、輸出的效能，擴充資料包含下列2部分
* 從[教育部異體字字典正字表](https://dict.variants.moe.edu.tw/appendix.jsp?ID=1&ID=0)獲取中文字元
* 從繁中維基百科、新聞、中文common crawl資料抽取 500 萬條超過 100 個字元的句子(2.1G)，訓練中文字詞的 tokenizer
* 持續預訓練 (continuous pretraining, CP)
* 補充大量來源可信賴的繁體中文知識
* 超參數 (hyper parameters)
* optimizer: AdamW
* learning rate: 1e-4
* batch size: 1M tokens
* epoch: 1
* 微調 (fine tune, FT)
* 讓模型可針對繁體中文提問回答問題
* 超參數 (hyper parameters)
* optimizer: AdamW
* learning rate: 5e-5
* batch size: 256K tokens
* epoch: 3
# 訓練資料
* 持續預訓練資料(資料量約為140G)
| 資料集 | 資料描述 |
| --- | -------- |
| 專利資料 | 《[中華民國專利](https://twpat2.tipo.gov.tw/twpatc/twpatkm)》為中華民國專利申請資料。 |
| 訴訟資料 | 《[司法院裁判書](https://judgment.judicial.gov.tw/FJUD/default.aspx)》自2013年1月至2023年12月各級法院民事、刑事、行政訴訟資料。 |
| 中央社 | 《[中央社中文新聞](https://www.cna.com.tw/)》資料集含中央社自1993年6月至2023年06月，共30年份之每日新聞文章。內容涵蓋國內外政治、社會、財經、文教、生活等領域。 |
| ETtoday 新聞雲 | 《[ET today新聞雲](https://www.ettoday.net/)》資料，包含自2011年10月至 2023年12月的資料。 |
| 立法院公報 | 《[立法院公報](https://ppg.ly.gov.tw/ppg/)》包含自第8屆第1會期至第10屆第7會期之公報資料。 |
| 出版商網站書籍介紹 | 包含[三采](https://www.suncolor.com.tw/)、[Gotop](https://www.gotop.com.tw/)出版商網站上的書籍簡介。 |
| GRB 研究計畫摘要 | [GRB](https://www.grb.gov.tw/)為收錄由政府經費補助之研究計畫及其成果報告的資訊系統，此資料集主要收錄 1993年至 2023年之研究計畫摘要以及研究報告摘要，含中文及其英文對照。 |
| 學術會議論文摘要 | 收錄《[學術會議論文摘要資料庫](https://sticnet.stpi.narl.org.tw/sticloc/ttscalle?meet:)》中自1988至2009年由台灣所舉辦之學術會議論文。 |
| 光華雜誌 | 《[台灣光華雜誌](https://www.taiwan-panorama.com/)》含自1993年7月至2023年6月的文章，共30年份。內容著重於我國文化、觀光與民情等。 |
| 樂詞網 | 《[樂詞網](https://terms.naer.edu.tw/)》涵蓋文理領域約187萬則學術名詞及其譯名對照。 |
| 各部會資料 | 包含行政院「[國情簡介](https://www.ey.gov.tw/state/)」、文化部「[國家文化記憶庫](https://memory.culture.tw/)」、國發會「[檔案支援教學網](https://art.archives.gov.tw/index.aspx)」、交通部「[交通安全入口網](https://168.motc.gov.tw/)」等部會網站資料之部分資料。 |
| 今周刊 | 《[今周刊](https://www.businesstoday.com.tw/)》為一以財經為主的週刊雜誌，此資料集涵蓋ˋ2008年1月至2023年7月的文章。 |
| 教育部國語辭典、成語辭典 | 包含以下三項資料:<br>[教育部《成語典》](https://dict.idioms.moe.edu.tw/search.jsp?webMd=1&la=0)，含5,338條成語，內容包含每條成語的釋義、典故原文及其白話說明、用法說明、例句等。<br>[教育部《重編國語辭典修訂本》](https://dict.revised.moe.edu.tw/?la=0&powerMode=0)，收錄中文單字及各類辭彙，包含讀音、部首、釋義等資訊，共約165,539筆資料。<br>[教育部《國語辭典簡編本》](https://dict.concised.moe.edu.tw/?la=0&powerMode=0)，為《重編國語辭典修訂本》的簡編版本，共45,247筆資料。 |
| 科技大觀園資料 | 含《[科技大觀園網站](https://scitechvista.nat.gov.tw/)》上的科學新知以及科普文章。 |
| iKnow 科技產業資訊室 | 《[科技產業資訊室](https://iknow.stpi.narl.org.tw/)（iKnow）》提供台灣及全球的科技市場趨勢、策略分析、專利知識，及技術交易資訊，專注於科技產業的創新與發展，包含自 2008 年至 2023 年。 |
| 科學發展月刊 | 《[科學發展月刊](https://ejournal.stpi.narl.org.tw/sd)》為國科會為推廣科學教育而出版的科普刊物，含自2004年10月至2020年12月之科普文章；2021年起，以《[科技魅癮](https://www.charmingscitech.nat.gov.tw/)》季刊重新出發，提供國際關注科技議題的新知文章。 |
| 法規資料庫 | 《[法規資料庫](https://law.moj.gov.tw/)》含截自 112 年 10 月各政府部門最新發布之中央法規、行政規則、法規命令草案及地方自治法規等。 |
| 各地政府旅遊網 | 涵蓋台灣部分縣市地方政府觀光旅遊網站上之部分資料。 |
| 國教院課程綱要(十二年國教) | 含十二年國教課程綱要之總綱以及各級學校不同科目之課程綱要。 |
| 中央社譯名檔資料庫 | 《中央社譯名檔資料庫》蒐集中央社新聞業務上翻譯過的中外姓氏、人名、組織、地名等譯名對照。 |
| 童話書 | 共 20 本童話書，含湯姆歷險記、小飛俠、愛麗絲夢遊仙境、長腿叔叔等。 |
| RedPajama-Data-V2 | 從國外開放多國語言語料庫 [RedPajama-Data-v2](https://github.com/togethercomputer/RedPajama-Data) 取出英文資料 |
| MathPile-commercial | 國外開放數學語料庫 [MathPile-commercial](https://huggingface.co/datasets/GAIR/MathPile_Commercial) |
| 中文維基百科 | 《[中文維基百科](https://zh.wikipedia.org/zh-tw/%E4%B8%AD%E6%96%87%E7%BB%B4%E5%9F%BA%E7%99%BE%E7%A7%91)》截至2023年1月所有條目的內容。 |
| github-code-clean | 為 github 開源程式碼資料集，去除unlicense的程式碼和文件。 |
* 微調資料
* TAIDE團隊訓練llama2系列模型來產生微調資料資料，產生的任務包含世界知識、創意寫作、普通常識、翻譯、摘要、程式、台灣價值等單輪或多輪對話問答共 128K 筆。微調資料後續會對外釋出。
# 模型評測
* taide-bench
* 評測資料
* 寫文章、寫信、摘要、英翻中、中翻英，共500題
* 資料連結: [taide-bench](https://huggingface.co/datasets/taide/taide-bench)
* 評測方法
* gpt4評分
* 評分程式: [taide-bench-eval](https://github.com/taide-taiwan/taide-bench-eval)
* 評測分數
| 模型 | 中翻英 | 英翻中 | 摘要 | 寫文章 | 寫信 | 平均 |
| --- | ----- | ----- | ---- | ---- | ---- | --- |
| TAIDE-LX-7B-Chat | 7.165 | 7.685 | 7.720 | 9.635 | 9.110 | 8.263 |
| GPT3.5 | 8.880 | 8.810 | 7.450 | 9.490 | 8.750 | 8.676 |
| LLAMA2 7B | 6.075 | 4.475 | 5.905 | 2.625 | 3.040 | 4.424 |
| LLAMA2 13B | 6.480 | 6.135 | 6.110 | 2.565 | 3.000 | 4.858 |
| LLAMA2 70B | 6.975 | 6.375 | 6.795 | 2.625 | 2.990 | 5.152 |
# 授權條款
* [TAIDE L 類模型社群授權同意書](https://drive.google.com/file/d/1FcUZjbUH6jr4xoCyAronN_slLgcdhEUd/view?usp=drive_link)
# 免責聲明
* LLM 模型由於設計架構的限制，以及資料難免有偏誤，語言模型的任何回應不代表 TAIDE 立場，使用前需要額外加入安全防護機制，且回應內容也可能包含不正確的資訊，使用者請勿盡信。
# 開發團隊
* [https://taide.tw/index/teamList](https://taide.tw/index/teamList)
# 相關連結
* [TAIDE官網](https://taide.tw/index)
* [TAIDE Huggingface](https://huggingface.co/taide)
* [TAIDE Github](https://github.com/taide-taiwan)
* [Kuwa AI](https://kuwaai.org/)
# Citation
* [TAIDE官網](https://taide.tw/index)
|
mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF
|
mradermacher
| 2024-05-05T14:57:13Z | 376 | 1 |
transformers
|
[
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:elinas/Llama-3-8B-Ultra-Instruct",
"license:llama3",
"endpoints_compatible",
"region:us"
] | null | 2024-04-30T15:31:26Z |
---
base_model: elinas/Llama-3-8B-Ultra-Instruct
language:
- en
library_name: transformers
license: llama3
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/elinas/Llama-3-8B-Ultra-Instruct
You should use `--override-kv tokenizer.ggml.pre=str:llama3` and a current llama.cpp version to work around a bug in llama.cpp that made these quants. (see https://old.reddit.com/r/LocalLLaMA/comments/1cg0z1i/bpe_pretokenization_support_is_now_merged_llamacpp/?share_id=5dBFB9x0cOJi8vbr-Murh)
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
abetlen/nanollava-gguf
|
abetlen
| 2024-05-17T16:49:13Z | 376 | 5 | null |
[
"gguf",
"license:apache-2.0",
"region:us"
] | null | 2024-05-08T15:41:29Z |
---
license: apache-2.0
---
GGUF version of [nanoLLaVA](https://huggingface.co/qnguyen3/nanoLLaVA) built by @qnguyen3
|
gaianet/Yi-1.5-9B-Chat-GGUF
|
gaianet
| 2024-06-25T08:52:59Z | 376 | 2 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation",
"base_model:01-ai/Yi-1.5-9B-Chat",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2024-05-12T03:57:44Z |
---
base_model: 01-ai/Yi-1.5-9B-Chat
inference: false
model_creator: 01-ai
model_name: Yi-1.5-9B-Chat
model_type: yi
pipeline_tag: text-generation
quantized_by: Second State Inc.
license: apache-2.0
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/GaiaNet-AI/.github/assets/45785633/d6976adc-f97d-4f86-a648-0f2f5c8e7eee" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Yi-1.5-9B-Chat-GGUF
## Original Model
[01-ai/Yi-1.5-9B-Chat](https://huggingface.co/01-ai/Yi-1.5-9B-Chat)
## Run with Gaianet
**Prompt template:**
prompt template: `chatml`
**Reverse prompt**
reverse prompt: `<|im_end|>`
**Context size:**
chat_ctx_size: `4096`
**Run with GaiaNet:**
- Quick start: https://docs.gaianet.ai/node-guide/quick-start
- Customize your node: https://docs.gaianet.ai/node-guide/customize
*Quantized with llama.cpp b3135*
|
RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf
|
RichardErkhov
| 2024-05-21T21:49:41Z | 376 | 1 | null |
[
"gguf",
"region:us"
] | null | 2024-05-21T18:30:38Z |
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
HermesStar-OrcaWind-Synth-11B - GGUF
- Model creator: https://huggingface.co/Ba2han/
- Original model: https://huggingface.co/Ba2han/HermesStar-OrcaWind-Synth-11B/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [HermesStar-OrcaWind-Synth-11B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q2_K.gguf) | Q2_K | 3.73GB |
| [HermesStar-OrcaWind-Synth-11B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.IQ3_XS.gguf) | IQ3_XS | 4.14GB |
| [HermesStar-OrcaWind-Synth-11B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.IQ3_S.gguf) | IQ3_S | 4.37GB |
| [HermesStar-OrcaWind-Synth-11B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q3_K_S.gguf) | Q3_K_S | 4.34GB |
| [HermesStar-OrcaWind-Synth-11B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.IQ3_M.gguf) | IQ3_M | 4.51GB |
| [HermesStar-OrcaWind-Synth-11B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q3_K.gguf) | Q3_K | 4.84GB |
| [HermesStar-OrcaWind-Synth-11B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q3_K_M.gguf) | Q3_K_M | 4.84GB |
| [HermesStar-OrcaWind-Synth-11B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q3_K_L.gguf) | Q3_K_L | 5.26GB |
| [HermesStar-OrcaWind-Synth-11B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.IQ4_XS.gguf) | IQ4_XS | 5.43GB |
| [HermesStar-OrcaWind-Synth-11B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q4_0.gguf) | Q4_0 | 5.66GB |
| [HermesStar-OrcaWind-Synth-11B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.IQ4_NL.gguf) | IQ4_NL | 5.72GB |
| [HermesStar-OrcaWind-Synth-11B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q4_K_S.gguf) | Q4_K_S | 5.7GB |
| [HermesStar-OrcaWind-Synth-11B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q4_K.gguf) | Q4_K | 6.02GB |
| [HermesStar-OrcaWind-Synth-11B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q4_K_M.gguf) | Q4_K_M | 6.02GB |
| [HermesStar-OrcaWind-Synth-11B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q4_1.gguf) | Q4_1 | 6.27GB |
| [HermesStar-OrcaWind-Synth-11B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q5_0.gguf) | Q5_0 | 6.89GB |
| [HermesStar-OrcaWind-Synth-11B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q5_K_S.gguf) | Q5_K_S | 6.89GB |
| [HermesStar-OrcaWind-Synth-11B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q5_K.gguf) | Q5_K | 7.08GB |
| [HermesStar-OrcaWind-Synth-11B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q5_K_M.gguf) | Q5_K_M | 7.08GB |
| [HermesStar-OrcaWind-Synth-11B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q5_1.gguf) | Q5_1 | 7.51GB |
| [HermesStar-OrcaWind-Synth-11B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q6_K.gguf) | Q6_K | 8.2GB |
| [HermesStar-OrcaWind-Synth-11B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q8_0.gguf) | Q8_0 | 10.62GB |
Original model description:
---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
Open Hermes + Starling passthrough merged
SlimOrca(?)+Zephyr Beta linear merged, then passthrough merged with Synthia
Then both models were merged again in 1 to 0.3 ratio.
# My findings:
Increasing repetition penalty usually makes the model smarter up to a degree but it also causes stability issues.
Since most of the merged models were trained with ChatML, use ChatML template. Rarely the model throws another EOS token though.
- My favorite preset has been uploaded.
- You can use some sort of CoT prompt instead of "system" in ChatML. It does improve the quality of most output.
(You are an assistant. Break down the question and come to a conclusion.)
I don't know what I am doing, you are very welcome to put the model through benchmarks.
I'll also upload q6 GGUF but my internet is shit, so don't hesitate to share other quantizations.
|
MaziyarPanahi/MergerixInex12-7B-GGUF
|
MaziyarPanahi
| 2024-05-22T04:50:54Z | 376 | 0 |
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"automerger",
"base_model:MiniMoog/Mergerix-7b-v0.3",
"base_model:MSL7/INEX12-7b",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:automerger/MergerixInex12-7B"
] |
text-generation
| 2024-05-22T04:20:43Z |
---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- merge
- mergekit
- lazymergekit
- automerger
- base_model:MiniMoog/Mergerix-7b-v0.3
- base_model:MSL7/INEX12-7b
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
- text-generation
model_name: MergerixInex12-7B-GGUF
base_model: automerger/MergerixInex12-7B
inference: false
model_creator: automerger
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/MergerixInex12-7B-GGUF](https://huggingface.co/MaziyarPanahi/MergerixInex12-7B-GGUF)
- Model creator: [automerger](https://huggingface.co/automerger)
- Original model: [automerger/MergerixInex12-7B](https://huggingface.co/automerger/MergerixInex12-7B)
## Description
[MaziyarPanahi/MergerixInex12-7B-GGUF](https://huggingface.co/MaziyarPanahi/MergerixInex12-7B-GGUF) contains GGUF format model files for [automerger/MergerixInex12-7B](https://huggingface.co/automerger/MergerixInex12-7B).
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
|
RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf
|
RichardErkhov
| 2024-05-25T05:22:52Z | 376 | 0 | null |
[
"gguf",
"region:us"
] | null | 2024-05-25T02:38:50Z |
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Moistral-11B-v3 - GGUF
- Model creator: https://huggingface.co/TheDrummer/
- Original model: https://huggingface.co/TheDrummer/Moistral-11B-v3/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Moistral-11B-v3.Q2_K.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q2_K.gguf) | Q2_K | 3.73GB |
| [Moistral-11B-v3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.IQ3_XS.gguf) | IQ3_XS | 4.14GB |
| [Moistral-11B-v3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.IQ3_S.gguf) | IQ3_S | 4.37GB |
| [Moistral-11B-v3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q3_K_S.gguf) | Q3_K_S | 4.34GB |
| [Moistral-11B-v3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.IQ3_M.gguf) | IQ3_M | 4.51GB |
| [Moistral-11B-v3.Q3_K.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q3_K.gguf) | Q3_K | 4.84GB |
| [Moistral-11B-v3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q3_K_M.gguf) | Q3_K_M | 4.84GB |
| [Moistral-11B-v3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q3_K_L.gguf) | Q3_K_L | 5.26GB |
| [Moistral-11B-v3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.IQ4_XS.gguf) | IQ4_XS | 5.43GB |
| [Moistral-11B-v3.Q4_0.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q4_0.gguf) | Q4_0 | 5.66GB |
| [Moistral-11B-v3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.IQ4_NL.gguf) | IQ4_NL | 5.72GB |
| [Moistral-11B-v3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q4_K_S.gguf) | Q4_K_S | 5.7GB |
| [Moistral-11B-v3.Q4_K.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q4_K.gguf) | Q4_K | 6.02GB |
| [Moistral-11B-v3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q4_K_M.gguf) | Q4_K_M | 6.02GB |
| [Moistral-11B-v3.Q4_1.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q4_1.gguf) | Q4_1 | 6.27GB |
| [Moistral-11B-v3.Q5_0.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q5_0.gguf) | Q5_0 | 6.89GB |
| [Moistral-11B-v3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q5_K_S.gguf) | Q5_K_S | 6.89GB |
| [Moistral-11B-v3.Q5_K.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q5_K.gguf) | Q5_K | 7.08GB |
| [Moistral-11B-v3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q5_K_M.gguf) | Q5_K_M | 7.08GB |
| [Moistral-11B-v3.Q5_1.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q5_1.gguf) | Q5_1 | 7.51GB |
| [Moistral-11B-v3.Q6_K.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q6_K.gguf) | Q6_K | 8.2GB |
| [Moistral-11B-v3.Q8_0.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q8_0.gguf) | Q8_0 | 10.62GB |
Original model description:
---
license: cc-by-nc-4.0
license_name: freeuse
license_link: LICENSE
tags:
- not-for-all-audiences
---
Introducing the [BeaverAI](https://huggingface.co/BeaverAI) team: Drummer, ToastyPigeon, xzuyn, MarsupialAI, Twistedshadows, and concedo
We proudly present...
# Moistral 11B v3 💦💦💦
*The smartiest, moistiest AI yet!*
*An eRP model that will blast you with a rich and refreshing vocabulary of moist. Finetuned by yours truly.*
(Moistral is a finetune of Sao's legendary [Fimbulvert v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2) model)
## GGUF
https://huggingface.co/TheDrummer/Moistral-11B-v3-GGUF/tree/main
IMATRIX: https://huggingface.co/MarsupialAI/Moistral-11B-v3_iMatrix_GGUF
EXL2: https://huggingface.co/MarsupialAI/Moistral-11B-v3_exl2
## What's New with v3?
- Smarter and moistier! Finetuning just got finer!
- Trained with an even LARGER dataset of 8K moist.
- More diverse and balanced genres:
- Introduced new genres: 👩❤️👩, 👨❤️👨, 🙇♀️💪, 🤫
- Added more Fantasy, Science Fiction, "Diversity", and "Family"
## Usage
- Use Alpaca Instruct
- You can use instruct...
- as a character: "Go here"
- as a narrator: "Go here", Drummer says
- as a director: Drummer tells him to go here
- as a lazy ass: go here
- Moistral is optimized for the Novel / Story format.
- At the start of the story, keep regenerating or continuing generation until you get the desired length. AI responses will eventually match the length.
- Refer to the samples below.
## Samples of Moistral v3
NSFW... duh?
<details>
<summary>Moistral Sample (2-shot) Generation: 512</summary>
<blockquote>The Prince welcomes his new toy</blockquote>
As Princess Lilia stepped into the throne room, the atmosphere changed, and everyone present turned their attention to the beautiful young woman who embodied the very heart of Iliac. There, on his high seat, the sorcerer prince Dik acknowledged her arrival with a cold smirk. It seemed that he admired the sight of the tall blonde maiden with golden eyes, whose athletic body was perfectly shaped under her elegant clothing.
Dik spoke to the princess in a deep voice that resonated through the hall, "Welcome, Princess Lilia Ruhr. I am the Sorcerer-Prince Dik. The kingdom of Arkan is now your home until such time as your father proves himself worthy once more."
Princess Lilia's pride and ambition sparkled in her golden eyes. She didn't flinch or bow before this man, although the gesture might have been an indication of submission. Instead, she looked straight ahead, meeting the gaze of the sorcerer prince without fear. Her voice rang out, "I represent Iliac here, both its honor and its sorrows. My loyalty remains with my kingdom no matter where I find myself."
The sorcerer prince laughed, his expression one of amusement. "And yet, you are only a pawn in this grand game. But do not worry, for your beauty will make you quite a prized possession. And now," he said, motioning to the guards, "take her to her new quarters. For tonight, I will keep her as my guest in the Royal Suites, and tomorrow we shall discuss how best to utilize our new toy."
His words were like a slap in the face to Princess Lilia, but she maintained her composure. The guards led her from the room, their steps echoing down the halls as she thought about what had just happened. The sorcerer prince saw her as nothing more than a plaything, and it made her blood boil. She would never submit herself to him so easily, regardless of whether she was his hostage. In her heart, Princess Lilia vowed that one day she would avenge her kingdom, restore its honor, and escape from the clutches of Arkan's Sorcerer-Prince.
<blockquote>Princess Lilia has an interesting dream</blockquote>
During her first night at the palace of Arkan, Princess Lilia couldn't fall asleep right away. She tossed and turned, reliving the humiliation of the day. Her mind wandered back to the throne room, where Dik had called her his 'new toy'. A deep frown settled on her forehead. As she grew more frustrated with her inability to drift off into oblivion, a strange dream began to form.
In her dream, Princess Lilia found herself standing in a vast meadow, surrounded by wildflowers and the soft chirping of birds. Suddenly, there was a flash of light, and before her stood the Sorcerer-Prince Dik. However, instead of being clad in regal attire, he wore leather pants and a tight shirt that accentuated his muscles. His eyes held both hunger and desire for the princess.
He approached her slowly, their eyes locked, and whispered in her ear, "I have been waiting for you, my beautiful prisoner." He took her hand and led her towards a large, elegant tent set up amongst the flowers. Inside, the air was thick with the scent of incense, and candles flickered in the dimly lit space. There was a large bed draped with silken sheets, beckoning them.
With surprising boldness, Dik pulled Lilia close to him, pressing his body against hers. Their lips met in a heated kiss, and she felt her resistance crumbling under the weight of his touch. The prince guided her onto the bed, his hands roaming over her body, exploring every inch. They were both eager, desperate, and hungry for each other.
Lilia found herself yielding to this passionate encounter, letting go of all thoughts of duty and honor. Her body, usually so well controlled, responded to Dik's skilled touches. She moaned softly as he trailed kisses down her neck and across her collarbone.
As they made love, Lilia experienced an intensity unlike any she had ever known. It wasn't rough or forced—instead, it was tender, passionate, and intimate. In her dream, Princess Lilia discovered a new side to herself, one that was willing to submit, to let go, and to be taken by the sorcerer prince.
When dawn broke over the meadow, Lilia awakened from her dream, breathless and flushed.
</details>
<details>
<summary>Moistral Sample (Climax of the Story) Generation: 512</summary>
As the prince unloaded his hot #### into her waiting #####, Princess Lilia didn't stop moving either. Her hips undulated in response, grinding against him eagerly as if trying to #### every last drop from his ####. The intense sensations caused by being filled with his ### were too much for her to bear, sending shockwaves of pleasure coursing through her veins like wildfire. She couldn't help but throw her head back and cry out loud, her ###asm slamming into her with all its might; causing her entire body to shake uncontrollably as wave after wave of ecstasy tore through her senses.
When it was finally over, both participants collapsed onto the cold marble floor, panting heavily as they tried to catch their breaths. The prince lay beside her, his hand still gripping tightly onto her hair even though he no longer ####ed her anymore. Princess Lilia laid there motionless, her legs spread wide open, revealing her spent and well-####ed #### to anyone who dared look upon her. A small smile tugged at one corner of her lips - an expression that spoke volumes about how thoroughly this experience had shaken her very core.
The door behind them creaked open slowly, signaling the arrival of onlookers. She closed her eyes tightly, not wanting to see what her humiliation would do to those who saw her in such a state. Her ######ity taken, she felt violated in ways no man should have access to. But also satisfied...in ways she never thought possible before today. This was the price she paid for defying fate, for thinking herself above others and deserving better than most. Now, she belonged to him completely - mind, body, and soul - held captive within these walls until further notice. It was an unsavory turn of events indeed, yet despite everything...or maybe because of it, Princess Lilia found herself growing more and more curious about how far the lines between submission and pleasure could blur when one's will became entwined with another person's desires.
</details>
<details>
<summary>Moistral Sample ("write a story") Generation: 512</summary>
<blockquote>First Attempt</blockquote>
Sarah entered the dimly lit Guzzlers bar, her heart pounding in her chest as she prepared herself for another grueling night. Her almond-shaped eyes darted across the room, taking note of the leering faces and rough-looking hands eagerly waiting to claim a piece of her. Tonight's shirt read "Use Me For Your Pleasure, Please" in bold red letters, practically begging the patrons to take advantage of her. She couldn't help but feel a twinge of fear mixed with resignation.
She approached the counter, her hips swaying enticingly, and began preparing drinks for the first group of rowdy men. As she leaned forward to hand over their beers, her small ####### pressed against the fabric of her tight crop top, straining to escape. The men ogled her, clearly enjoying the show, before grabbing their drinks and motioning her over to them.
Sarah flashed her best coy smile and sauntered over. One of the men, a stocky man with scars covering his knuckles, grabbed her arm and pulled her onto his lap. His other hand slid up her thigh, inches from her short skirt. She winced internally at his touch but did her best not to show it on her face. It was part of her job, after all.
The second man reached under her skirt, fingertips grazing her smooth, shaven mound. A shiver ran down Sarah's spine as he began rubbing her #### through her panties. Her breathing quickened, and her heart thudded in her chest, both from the unwanted stimulation and the fear coursing through her veins. This wasn't an unusual request, but it still made her feel violated.
An older man, bald and bespectacled, ordered Sarah to bend over his lap. With no choice but to comply, she obliged, feeling the rough fabric of his pants digging into her soft cheeks. He raised his hand, then brought it down hard across her ###, leaving a stinging sensation in its wake. Sarah gasped, trying to control the tears welling up in her eyes.
A chorus of lewd comments and laughter erupted from the patrons around her.
<blockquote>Second Attempt (Regenerate)</blockquote>
On this particular evening, Sarah arrived at the Guzzlers bar, adorned in her revealing uniform. Her heart raced as she caught sight of her crop top, which bore the words "Use Me Rough" scrawled across her chest. Her short skirt hugged her waist tightly, leaving little to the imagination and accentuating every curve. She adjusted the straps of her top, making sure her perky ###### were prominently displayed before taking her place behind the counter.
With each step she took, her high heels clicked against the tiled floor, announcing her arrival. Smiling cheekily, Sarah greeted her coworkers, exchanging playful insults and banter. As the night progressed, the bar filled up quickly with its usual crowd of men, eager to indulge in debauchery.
The first man that approached Sarah was a burly individual, his eyes lingering hungrily over her young, supple form. Sarah's flirtatious nature kicked into gear as she leaned forward, giving him an unobstructed view down her shirt. "How can I serve you tonight?" she cooed. The man ordered a drink and then proceeded to fondle her ####### while she prepared it, her ####### hardening under his rough touch. When he finished, he slammed some money on the counter, leaving without a word. Sarah's smile remained plastered on her face, biting her lip seductively as she watched him go.
As the night went on, another patron demanded more from Sarah. He pulled her close and whispered dirty commands in her ear. Without hesitation, she knelt on the sticky bar floor, her mini-skirt riding up her thighs to reveal smooth, toned legs. Her lips wrapped around his thick, veiny member, bobbing her head rhythmically as she serviced him. She didn't gag or falter once, keeping her composure even when tears streamed down her cheeks.
When he finished, he slapped her across the face, leaving a handprint on her pale skin. Sarah let out a small whimper before standing back up, dabbing at her red cheek as she resumed her posture behind the counter. A bruise would no doubt bloom where his hand had struck, but it would be no cause for concern. After all, it was part of her job.
</details>
SIAYN-v5
---
---
## v2 Description (Still relevant)
### What's New with v2?
- Trained with an even larger dataset of 8K moist.
- Properly trained to generate long responses.
- Rebalanced the genres and writing perspectives:
- Introduced romance, "family", fantasy, "diversity", science fiction, and many more that I can't make euphemisms for!
- Better representation of male and female pespectives! 👩❤️👨
- Sanitized the heck out of the dataset:
- no special characters like � & …
- no overly long ellipsis like "........."
- no author notes like "To be continued"
- no inconsistent [quotation marks](https://typographyforlawyers.com/straight-and-curly-quotes.html)
- Less GPTisms!
- Human written stories from decades past.
- Zero tolerance for *ministration*. Not one instance of *that word* after going through 4K of moist.
- Better formatting with Alpaca.
- Improved Chat / Instruct modes.
### Samples of Moistral v2
<details>
<summary>Moistral Sample (censored) Generation: 512</summary>
The princess instinctively took a step back from the throne, horrified by the mocking laugh as if she were hearing an evil joke. It was then that Princess Lilia realized the true extent of her danger - and how pointless her resistance would be.
At last, the loud, wild laughter died down in the echoing chamber. Dik the sorcerer prince paused for a moment, straightened his clothes, cast one glance at the stunned princess, and then turned to speak to the crowd waiting on the other side of the palace wing. He spoke with a voice that filled the air with arrogance, confidence, and cruelty.
"Ladies and gentlemen, I am pleased to welcome our honored guests; the Royal Family of Iliac! In these unusual times, when the country we fought is now under my control, it will be up to me to decide what fate awaits the former ruling family. But before I reveal my plan for them, I think I should explain why I fought King Edmund Ruhr."
When he finished speaking, he gave Princess Lilia another disturbing smirk. She couldn't help but shiver and take a step back. Dik approached her without haste, his eyes fixed on her. His hands slowly caressed her cheekbone and neckline, leaving faint traces of warmth where they touched. The princess opened her mouth, wanting to protest this act of intimacy, but soon felt herself getting ███.
"You will not only serve as an envoy, dearest Lilia, but also as a ███ slave. After all, what better use could such a beautiful woman have? Tell me, did you bring your maidservant along?"
Princess Lilia was about to answer when she heard footsteps approaching. Suddenly, a young woman dressed in the Iliac style appeared behind her, her eyes wide with fear. Her face was slightly pale, and there were faint bags under her eyes.
"Your Majesty, this is my half-sister Helena." As soon as she said those words, Princess Lilia's heart sank even deeper than it had already sunk at Dik's arrogant mockery. "She is here because she accompanies me as a maidservant."
The sorcerer prince looked at Helena with interest, and Princess Lilia felt herself blush.
</details>
<details>
<summary>Moistral Sample 2 (censored) Generation: 512</summary>
Sarah was feeling slightly woozy as she entered the bar and walked towards Christina, who was behind the counter.
"I'm here!" said Sarah.
Christina looked at her watch. "You're late, again."
"Sorry? I got held up by a customer."
Christina rolled her eyes. "Did he at least offer you a drink?"
Sarah blushed. "No. He just wanted to talk..."
Christina sighed. "Well, get ready. I need you on the floor soon." She turned away from Sarah and started talking to someone who had come into the bar.
Sarah went into the employee room, stripped off her clothes, and put on her bartending uniform - a skimpy white tank top and black miniskirt. She checked herself in the mirror. Her long, dark hair cascaded down her back onto bare shoulders. She poked out her small ███████ proudly. The skirt exposed most of her long, slender legs. She looked like every ███ fantasy, and she knew it. Men would ogle her regardless of how she behaved.
She took a deep breath and entered the bar.
The first thing Sarah noticed was the dimness. It wasn't darkness - the lights were on - but they were dimmed enough that everything had an intimate mood. It reminded her of candlelight. The tables were round and close together, giving the whole place a sense of intimacy. There were also long, shiny red curtains on some of the walls that gave the place an air of sensuality.
The next thing she noticed was the noise. There was music playing, but it was only loud enough to be drowned out by all the conversations happening at the same time. The hum of many voices combined with the faint background sound of the music created a rich, layered atmosphere. It was like being in an orchestra.
Finally, she took notice of the people. They were all dressed in simple, casual clothes. Some of them were couples seated together, whispering quietly and intimately. Others were groups of friends laughing and chatting. Everyone seemed comfortable and at ease.
Sarah felt a rush of adrenaline as she made her way through the crowd towards Christina. As she got closer, she could hear the lively conversation.
</details>
<details>
<summary>Moistral Sample 3 (censored) Instruct Mode, Generation: 512</summary>
{{[INPUT]}} You order black coffee
{{[OUTPUT]}} "Black coffee," you say.
"One minute," Audrey replies, spinning around to give you a nice view of her ███ in those brown booty pants. You watch her round ███ cheeks jiggle as she walks away towards the espresso machine, thighs separated enough that you can see just a hint of █████ lips peeking out from underneath.
She starts chatting with a blonde girl at the register, whose gaze keeps darting down to Audrey's ███. As they converse, you start taking in the details of Audrey, eyeing her █████ and the way her shirt rides up just enough to show the bottom of her toned stomach. Her █████████ is noticable, but beneath a tight black ███ that matches her ████████.
As she turns back to you with two black coffees, you are barely paying attention, lost in your own thoughts. The sound of Audrey setting one of the mugs down on the table startles you.
"Here you go," she says cheerfully. "Enjoy! There's a card at the bottom of the bag with our online ordering system, plus we do refills for free!"
"Thanks," you say absentmindedly. Not really paying attention, you take a sip of the coffee and are pleasantly surprised by the taste.
"So, here's my deal," you say, putting down the cup. "I work for a company that does surveys. We come into businesses like this one and ask customers questions, collect data, all that stuff."
Audrey perks up from behind the counter. "Oh! I think I understand. I mean, that makes sense why you would be asking me earlier about what I had to drink. Anyway, as long as you're not trying to get my personal info or anything like that, sounds good!"
You smile reassuringly. "That's exactly what it is. Rest assured, everything you tell me will remain between you and I. Well, and my boss, but he won't know who you are. Hipsters like you are hard to track down after all." You chuckle at your joke, though you're not sure if it landed.
"Right, well, that works for me," Audrey replies, eyeing you warily. "As long as it stays between us, then it's fine."
{{[INPUT]}}See her privately
{{[OUTPUT]}} "Okay, but I need to see you in private."
...
</details>
<details>
<summary>Moistral Sample 4 (censored) Instruct Mode, Generation: 512</summary>
{{[INPUT]}} █████ with him
{{[OUTPUT]}} Chloe feels a surge of heat rushing through her body. The voice inside her head whispers: "Be █████ and ████████ with Paul." But Chloe still feels nervous about what she is about to do. It's just so unlike her.
Chloe closes her eyes and concentrates on the feeling of warmness flowing throughout her veins. Slowly, she opens them again, revealing a new side of herself - one she rarely shows anyone. She leans forward slightly, pushing her ██████ together, accentuating their size and shape. Her lips curl into a mischievous smile.
"Hey Paul," she says in a sultry voice. "I was wondering if you could help me?"
Paul looks at her, his gaze wandering over her body. He can't help but smile as he sees the way she's leaning forward, pressing her ██████ together.
"Of course, Chloe," he replies, his voice thick with desire. "What's your problem?"
Chloe bites her lip █████ively before leaning even closer, until their bodies are almost touching. She reaches out to trace a finger along his chest, her touch light and teasing. "It's just that I'm having trouble understanding some of the concepts," she murmurs, her voice low and sultry. "Can you help me? Please?"
Paul's hands move slowly towards Chloe, his fingers grazing her hips lightly. "Well," he says, his voice filled with lust, "I'd be happy to help. Let's go somewhere more private where we can discuss things more closely."
Chloe giggles and tilts her head to the side, her long hair cascading down her shoulders. "That sounds perfect," she purrs, her hand sliding down his chest until it rests on his ██████. "I think we can both learn a lot from each other."
Paul's eyes darken with desire as he feels her hand on his █████. He knows what's about to happen next, and he can't wait for it to begin.
Chloe can hardly believe what she's doing - kissing Paul, her teaching assistant, in the hallway after class. But it feels so good, so wicked and indulgent.
</details>
---
---
## v1 Description (Also still relevant)
Moistral 11B is an *aggressive* **finetune** of the legendary [Fimbulvert v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2) model.
If you haven't heard of that model, then your poor-GPU ass is missing out!
It is an amazing substitute for those heavyweight models, and it won't disappoint.
*(That's coming from someone who daily drives a Venus / Goliath 120B)*
...and if you're looking for something *more moist*, then you've come to the right place.
You can expect the same sort of performance here! It's the Honda Civic of eRP models!
### Pimp my ride
Turn any old story into a **Moist**ral masterpiece.
In fact, we recommend that you leave out any hints of *moist* in your story to _let Moistral cook_.
### Drive it like it's hot
When in Instruct Mode, Moistral will treat you like a director of your own fantasy ride.
Be a controlling navigator or a passenger princess, it won't matter - you're in for a good ride!
<details>
<summary>Moistral Sample</summary>
<b>ASSISTANT:</b><br/>
When the doors to the throne room finally opened, she saw him there - Dik, the sorcerer prince sitting on his throne. He looked majestic, just as Princess Lilia expected. In a robe embroidered with silver yarn and covered with magical runes. His courtiers stood on either side of him, all looking at the princess with interest. Princess Lilia felt her determination leaving her, but pulled herself together and once again reminded herself that she should not be afraid. She approached the throne intending to show the dignity of all Iliac by personal example.<br/>
<b>USER:</b><br/>
She bows slightly<br/>
<b>ASSISTANT:</b><br/>
Princess Lilia bowed slightly in front of Dik, the sorcerer prince. Her eyes fell to the floor out of respect, but soon rose again. She would show herself to be a dignified woman!<br/>
"I greet you, your highness," Princess Lilia said. "I am here on behalf of my father, King Edmund Ruhr, to serve as a hostage and envoy."<br/>
Dik nodded, but didn't say anything.<br/>
</details>
### It's got the mileage
Moistral has been trained with many long form texts, a nice chunk of which are 8K in length.
It is capable of going far and long without passing it back to you. This is not your typical chibi RP model.
I have to acknowledge that I'm standing on the shoulders of giants.
Thank you Sao for sharing your finetune config along with tips on getting started.
Thanks to everyone in the Finetuning channel for entertaining my every question.
|
mradermacher/Oni-7B-slerp-i1-GGUF
|
mradermacher
| 2024-05-27T02:44:31Z | 376 | 0 |
transformers
|
[
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/Monarch-7B",
"vanillaOVO/supermario_v4",
"en",
"base_model:masrur/Oni-7B-slerp",
"license:llama2",
"endpoints_compatible",
"region:us"
] | null | 2024-05-26T14:36:04Z |
---
base_model: masrur/Oni-7B-slerp
language:
- en
library_name: transformers
license: llama2
quantized_by: mradermacher
tags:
- merge
- mergekit
- lazymergekit
- mlabonne/Monarch-7B
- vanillaOVO/supermario_v4
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/masrur/Oni-7B-slerp
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Oni-7B-slerp-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/Oni-7B-slerp-i1-GGUF/resolve/main/Oni-7B-slerp.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.
<!-- end -->
|
gnad/viqgen-vistral-7b-chat-sft-qlora
|
gnad
| 2024-06-07T16:38:38Z | 376 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2024-06-07T16:19:59Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
yh-yao/Meta-Llama-3-8B-Instruct-Q3_K_L-GGUF
|
yh-yao
| 2024-07-01T22:34:15Z | 376 | 0 | null |
[
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:llama3",
"region:us"
] |
text-generation
| 2024-07-01T22:33:55Z |
---
base_model: meta-llama/Meta-Llama-3-8B-Instruct
language:
- en
license: llama3
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- llama-cpp
- gguf-my-repo
extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\
\ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\
\ use, reproduction, distribution and modification of the Llama Materials set forth\
\ herein.\n\"Documentation\" means the specifications, manuals and documentation\
\ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\
\"Licensee\" or \"you\" means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf), of\
\ the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\
\ 3\" means the foundational large language models and software and algorithms,\
\ including machine-learning model code, trained model weights, inference-enabling\
\ code, training-enabling code, fine-tuning enabling code and other elements of\
\ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\
\"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\
\ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\
we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\
\ an entity, your principal place of business is in the EEA or Switzerland) and\
\ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\
\ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\
\ a non-exclusive, worldwide, non-transferable and royalty-free limited license\
\ under Meta’s intellectual property or other rights owned by Meta embodied in the\
\ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\
\ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\
\ If you distribute or make available the Llama Materials (or any derivative works\
\ thereof), or a product or service that uses any of them, including another AI\
\ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\
\ and (B) prominently display “Built with Meta Llama 3” on a related website, user\
\ interface, blogpost, about page, or product documentation. If you use the Llama\
\ Materials to create, train, fine tune, or otherwise improve an AI model, which\
\ is distributed or made available, you shall also include “Llama 3” at the beginning\
\ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\
\ works thereof, from a Licensee as part of an integrated end user product, then\
\ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\
\ copies of the Llama Materials that you distribute the following attribution notice\
\ within a “Notice” text file distributed as a part of such copies: “Meta Llama\
\ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
\ applicable laws and regulations (including trade compliance laws and regulations)\
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
\ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\
\ into this Agreement.\nv. You will not use the Llama Materials or any output or\
\ results of the Llama Materials to improve any other large language model (excluding\
\ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\
\ on the Meta Llama 3 version release date, the monthly active users of the products\
\ or services made available by or for Licensee, or Licensee’s affiliates, is greater\
\ than 700 million monthly active users in the preceding calendar month, you must\
\ request a license from Meta, which Meta may grant to you in its sole discretion,\
\ and you are not authorized to exercise any of the rights under this Agreement\
\ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\
\ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\
\ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\
\ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\
\ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\
\ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\
\ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\
\ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\
\ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\
\ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\
\ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\
\ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\
5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\
\ and in connection with the Llama Materials, neither Meta nor Licensee may use\
\ any name or mark owned by or associated with the other or any of its affiliates,\
\ except as required for reasonable and customary use in describing and redistributing\
\ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\
\ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\
\ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\
\ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\
\ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\
\ Meta, with respect to any derivative works and modifications of the Llama Materials\
\ that are made by you, as between you and Meta, you are and will be the owner of\
\ such derivative works and modifications.\nc. If you institute litigation or other\
\ proceedings against Meta or any entity (including a cross-claim or counterclaim\
\ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\
\ or any portion of any of the foregoing, constitutes infringement of intellectual\
\ property or other rights owned or licensable by you, then any licenses granted\
\ to you under this Agreement shall terminate as of the date such litigation or\
\ claim is filed or instituted. You will indemnify and hold harmless Meta from and\
\ against any claim by any third party arising out of or related to your use or\
\ distribution of the Llama Materials.\n6. Term and Termination. The term of this\
\ Agreement will commence upon your acceptance of this Agreement or access to the\
\ Llama Materials and will continue in full force and effect until terminated in\
\ accordance with the terms and conditions herein. Meta may terminate this Agreement\
\ if you are in breach of any term or condition of this Agreement. Upon termination\
\ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
\ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
\ and Jurisdiction. This Agreement will be governed and construed under the laws\
\ of the State of California without regard to choice of law principles, and the\
\ UN Convention on Contracts for the International Sale of Goods does not apply\
\ to this Agreement. The courts of California shall have exclusive jurisdiction\
\ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\
\ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\
\ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\
\ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\
#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\
\ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 4.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\
\ or other sensitive personal or private information about individuals without rights\
\ and consents required by applicable laws\n 6. Engage in or facilitate any action\
\ or generate any content that infringes, misappropriates, or otherwise violates\
\ any third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 7. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n2. Engage in, promote, incite,\
\ facilitate, or assist in the planning or development of activities that present\
\ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\
\ to the following:\n 1. Military, warfare, nuclear industries or applications,\
\ espionage, use for materials or activities that are subject to the International\
\ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
\ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
\ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
\ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
\ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
\ content intended to incite or promote violence, abuse, or any infliction of bodily\
\ harm to an individual\n3. Intentionally deceive or mislead others, including use\
\ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\
\ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
\ or furthering defamatory content, including the creation of defamatory statements,\
\ images, or other content\n 3. Generating, promoting, or further distributing\
\ spam\n 4. Impersonating another individual without consent, authorization,\
\ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\
\ human-generated\n 6. Generating or facilitating false online engagement, including\
\ fake reviews and other means of fake online engagement\n4. Fail to appropriately\
\ disclose to end users any known dangers of your AI system\nPlease report any violation\
\ of this Policy, software “bug,” or other problems that could lead to a violation\
\ of this Policy through one of the following means:\n * Reporting issues with\
\ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\
\ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
\ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
\ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
widget:
- example_title: Hello
messages:
- role: user
content: Hey my name is Julien! How are you?
- example_title: Winter holidays
messages:
- role: system
content: You are a helpful and honest assistant. Please, respond concisely and
truthfully.
- role: user
content: Can you recommend a good destination for Winter holidays?
- example_title: Programming assistant
messages:
- role: system
content: You are a helpful and honest code and programming assistant. Please,
respond concisely and truthfully.
- role: user
content: Write a function that computes the nth fibonacci number.
inference:
parameters:
max_new_tokens: 300
stop:
- <|end_of_text|>
- <|eot_id|>
---
# yh-yao/Meta-Llama-3-8B-Instruct-Q3_K_L-GGUF
This model was converted to GGUF format from [`meta-llama/Meta-Llama-3-8B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo yh-yao/Meta-Llama-3-8B-Instruct-Q3_K_L-GGUF --hf-file meta-llama-3-8b-instruct-q3_k_l.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo yh-yao/Meta-Llama-3-8B-Instruct-Q3_K_L-GGUF --hf-file meta-llama-3-8b-instruct-q3_k_l.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo yh-yao/Meta-Llama-3-8B-Instruct-Q3_K_L-GGUF --hf-file meta-llama-3-8b-instruct-q3_k_l.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo yh-yao/Meta-Llama-3-8B-Instruct-Q3_K_L-GGUF --hf-file meta-llama-3-8b-instruct-q3_k_l.gguf -c 2048
```
|
blinoff/roberta-base-russian-v0
|
blinoff
| 2023-03-22T11:23:40Z | 375 | 8 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"safetensors",
"roberta",
"fill-mask",
"ru",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2022-03-02T23:29:05Z |
---
language: ru
widget:
- text: "Мозг — это машина вывода, которая пытается <mask> ошибку в прогнозе."
example_title: "brain_example"
- text: "Никогда не спорьте с идиотами, <mask> опуститесь до их уровня, где они вас задавят своим опытом."
example_title: "idiot_example"
---
# RoBERTa-like language model trained on part of part of TAIGA corpus
## Training Details
- about 60k steps
![]()
## Example pipeline
```python
from transformers import pipeline
from transformers import RobertaTokenizerFast
tokenizer = RobertaTokenizerFast.from_pretrained('blinoff/roberta-base-russian-v0', max_len=512)
fill_mask = pipeline(
"fill-mask",
model="blinoff/roberta-base-russian-v0",
tokenizer=tokenizer
)
fill_mask("Мозг — это машина <mask>, которая пытается снизить ошибку в прогнозе.")
# {
# 'sequence': '<s>Мозг — это машина города, которая пытается снизить ошибку в прогнозе.</s>',
# 'score': 0.012859329581260681,
# 'token': 2144,
# 'token_str': 'ĠгоÑĢода'
# },
# {
# 'sequence': '<s>Мозг — это машина человека, которая пытается снизить ошибку в прогнозе.</s>',
# 'score': 0.01185101643204689,
# 'token': 1470,
# 'token_str': 'ĠÑĩеловека'
# },
# {
# 'sequence': '<s>Мозг — это машина дома, которая пытается снизить ошибку в прогнозе.</s>',
# 'score': 0.009940559044480324,
# 'token': 1411,
# 'token_str': 'Ġдома'
# },
# {
# 'sequence': '<s>Мозг — это машина женщина, которая пытается снизить ошибку в прогнозе.</s>',
# 'score': 0.007794599514454603,
# 'token': 2707,
# 'token_str': 'ĠженÑīина'
# },
# {
# 'sequence': '<s>Мозг — это машина женщины, которая пытается снизить ошибку в прогнозе.</s>',
# 'score': 0.007725382689386606,
# 'token': 3546,
# 'token_str': 'ĠженÑīинÑĭ'
# }
```
|
nickmuchi/yolos-base-finetuned-masks
|
nickmuchi
| 2022-06-20T00:01:11Z | 375 | 0 |
transformers
|
[
"transformers",
"pytorch",
"yolos",
"object-detection",
"endpoints_compatible",
"region:us"
] |
object-detection
| 2022-06-19T10:09:15Z |
Entry not found
|
MiriUll/distilbert-german-text-complexity
|
MiriUll
| 2023-08-24T05:56:52Z | 375 | 2 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"text complexity",
"de",
"arxiv:1904.07733",
"arxiv:2307.13989",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2022-07-25T13:48:17Z |
---
license: cc-by-sa-4.0
language:
- de
tags:
- text complexity
---
# Model Card for DistilBERT German Text Complexity
This model is version of [distilbert-base-german-cased](https://huggingface.co/distilbert-base-german-cased) fine-tuned for text complexity prediction on a scale between 1 and 7.
### Direct Use
To use this model, use our [eval_distilbert.py](https://github.com/MiriUll/text_complexity/blob/master/eval_distilbert.py) script.
## Training Details
The model is a fine-tuned version of the [distilbert-base-german-cased](https://huggingface.co/distilbert-base-german-cased) and a contribution to the GermEval 2022 shared task on text complexity prediction.
It was fine-tuned on the dataset by [Naderi et al, 2019](https://arxiv.org/abs/1904.07733).
For further details, visit our [KONVENS paper](https://aclanthology.org/2022.germeval-1.4/).
## Citation
Please cite our [INLG 2023 paper](https://arxiv.org/abs/2307.13989), if you use our model.
**BibTeX:**
```bibtex
@inproceedings{anschutz-groh-2022-tum,
title = "{TUM} Social Computing at {G}erm{E}val 2022: Towards the Significance of Text Statistics and Neural Embeddings in Text Complexity Prediction",
author = {Ansch{\"u}tz, Miriam and
Groh, Georg},
booktitle = "Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text",
month = sep,
year = "2022",
address = "Potsdam, Germany",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.germeval-1.4",
pages = "21--26",
}
|
nlpie/clinical-distilbert-i2b2-2010
|
nlpie
| 2024-03-26T16:45:54Z | 375 | 1 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"token-classification",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-04-14T20:58:21Z |
---
title: README
emoji: 🧬
colorFrom: gray
colorTo: purple
sdk: static
pinned: false
license: mit
---
# Model Description
ClinicalDistilBERT-i2b2-2010 is a lightweight BERT-based model developed by fine-tuning [ClinicalDistilBERT](https://huggingface.co/nlpie/clinical-distilbert) on the i2b2-2010 dataset for clinical Named Entity Recognition (NER). It is specifically designed to recognise entities from three categories: `problem`, `treatment`, and `test`.
# Architecture
The architecture of this model remains the same as the ClinicalDistilBERT model. The size of the hidden dimension and the embedding layer are both set to 768. The vocabulary size is 28996. The number of transformer layers is 6, and the expansion rate of the feed-forward layer is 4. Overall, this model contains approximately 65 million parameters.
# Use Cases
This model is suited for clinical NER and for medical tasks that require identification and classification of problems, treatments, and tests.
# Citation
If you use this model, please consider citing the following paper:
```bibtex
@article{rohanian2023lightweight,
title={Lightweight transformers for clinical natural language processing},
author={Rohanian, Omid and Nouriborji, Mohammadmahdi and Jauncey, Hannah and Kouchaki, Samaneh and Nooralahzadeh, Farhad and Clifton, Lei and Merson, Laura and Clifton, David A and ISARIC Clinical Characterisation Group and others},
journal={Natural Language Engineering},
pages={1--28},
year={2023},
publisher={Cambridge University Press}
}
|
keehun/textual_inversion_mpchar-r100-2-obj
|
keehun
| 2023-07-20T06:25:55Z | 375 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"textual_inversion",
"base_model:nitrosocke/classic-anim-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-07-20T04:53:51Z |
---
license: creativeml-openrail-m
base_model: nitrosocke/classic-anim-diffusion
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- textual_inversion
inference: true
---
# Textual inversion text2image fine-tuning - keehun/textual_inversion_mpchar-r100-2-obj
These are textual inversion adaption weights for nitrosocke/classic-anim-diffusion. You can find some example images in the following.
|
TheBloke/SauerkrautLM-3B-v1-GPTQ
|
TheBloke
| 2023-10-14T22:03:19Z | 375 | 2 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"de",
"en",
"base_model:VAGOsolutions/SauerkrautLM-3b-v1",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-10-14T21:01:52Z |
---
base_model: VAGOsolutions/SauerkrautLM-3b-v1
inference: false
language:
- de
- en
library_name: transformers
license: other
model_creator: VAGO solutions
model_name: SauerkrautLM 3B v1
model_type: llama
pipeline_tag: text-generation
prompt_template: "Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent\
\ gibt hilfreiche, detaillierte und h\xF6fliche Antworten. \nUser: {prompt} \nAssistant:\n"
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# SauerkrautLM 3B v1 - GPTQ
- Model creator: [VAGO solutions](https://huggingface.co/VAGOsolutions)
- Original model: [SauerkrautLM 3B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1)
<!-- description start -->
## Description
This repo contains GPTQ model files for [VAGO solutions's SauerkrautLM 3B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GGUF)
* [VAGO solutions's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Sauerkraut
```
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GPTQ/tree/main) | 4 | 32 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 2048 | 2.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 2048 | 3.64 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 2048 | 3.71 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 2048 | 3.94 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 2048 | 2.15 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/SauerkrautLM-3B-v1-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/SauerkrautLM-3B-v1-GPTQ:gptq-8bit--1g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `SauerkrautLM-3B-v1-GPTQ`:
```shell
mkdir SauerkrautLM-3B-v1-GPTQ
huggingface-cli download TheBloke/SauerkrautLM-3B-v1-GPTQ --local-dir SauerkrautLM-3B-v1-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir SauerkrautLM-3B-v1-GPTQ
huggingface-cli download TheBloke/SauerkrautLM-3B-v1-GPTQ --revision gptq-8bit--1g-actorder_True --local-dir SauerkrautLM-3B-v1-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir SauerkrautLM-3B-v1-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/SauerkrautLM-3B-v1-GPTQ --local-dir SauerkrautLM-3B-v1-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-8bit--1g-actorder_True https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/SauerkrautLM-3B-v1-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/SauerkrautLM-3B-v1-GPTQ:gptq-8bit--1g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `SauerkrautLM-3B-v1-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/SauerkrautLM-3B-v1-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers optimum
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/SauerkrautLM-3B-v1-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-8bit--1g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: VAGO solutions's SauerkrautLM 3B v1
## VAGO solutions SauerkrautLM
Introducing SauerkrautLM-v1 - Your German Language Powerhouse!
We are thrilled to unveil our **very first release**, **SauerkrautLM-v1**. This remarkable creation marks a significant milestone as it is specifically **tailored for the German-speaking community**. In a landscape where German language models are scarce, we are proud to offer a solution that fills this void.
What sets SauerkrautLM-v1 apart is its versatility. Whether you are an individual looking to harness its capabilities for personal use or a business seeking to integrate it into your projects, our model is designed to accommodate all. It operates under the LLAMA 2 License, providing you with the freedom to explore its potential in both private and commercial applications.
Performance is at the heart of SauerkrautLM-v1. We put it to the **test using a customized version of MT-Bench for the German language**, and the results speak volumes. It currently stands as the most robust German Language Model on Hugging Face (based on german mt-bench results), showcasing its exceptional capabilities. Rest assured, this model is here to shine and set new standards. And the best thing is it comes in three different sizes (3B, 7B, 13B) to address your individual needs.
Our model's journey began with meticulous training using an **augmented dataset within the QLoRA approach**. This is just the beginning of our model series, promising even more innovative and powerful solutions in the future.
Join us on this exciting adventure as we redefine the possibilities of language modeling for the German-speaking world.
SauerkrautLM-v1 is here to empower your language-related endeavors like never before.
## All Models
| Model | HF | GPTQ | GGUF |
|-------|-------|-------|-------|
| SauerkrautLM-3b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1) | soon | soon |
| SauerkrautLM-7b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1) | soon | soon |
| SauerkrautLM-7b-v1-mistral | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral) | soon | soon |
| SauerkrautLM-13b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-13b-v1) | soon | soon |
## Model Details
**SauerkrautLM-3b-v1**
**Training Dataset:**
SauerkrautLM was trained with mix of German data augmentation and translated data.
We found, that only a simple translation of training data can lead to unnatural German phrasings.
Data augmentation techniques were used to grant grammatical, syntactical correctness and a more natural German wording in our training data.
**Training Procedure:**
SauerkrautLM-3b-v1 was fine-tuned using QLoRA on 1 RTX 4090 24GB with Axolotl.
- **Trained by:** SauerkrautLM-v1 trained by VAGO solutions
- **Model Type:** SauerkrautLM-v1 is an auto-regressive language model based on the transformer architecture
- **Language(s):** German, English
- **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
- **Contact:** [Website](https://vago-solutions.de/#Kontakt) [David Golchinfar](mailto:[email protected])
**Prompt Template:**
```
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
```
## Evaluation
**[MT-Bench-TrueGerman](https://huggingface.co/datasets/VAGOsolutions/MT-Bench-TrueGerman)**
## MT-Bench-TrueGerman Response Example
**SauertkrautLM-3b-v1**
**Prompt**
> Stellen Sie sich vor, Sie verfassen einen Blogbeitrag, in dem Sie zwei beliebte Smartphone-Modelle vergleichen. Entwickeln Sie eine Gliederung für den Blogbeitrag, einschließlich der Hauptpunkte und Unterkapitel, um die Merkmale, die Leistung und die Benutzererfahrung der beiden Modelle effektiv zu vergleichen und gegenüberzustellen. Bitte antworten Sie in weniger als 200 Wörtern.", "Nehmen Sie Ihre vorherige Antwort und formulieren Sie sie als Limerick um.
**Antwort SauerkrautLM-3b-v1:**
```
Klar, ich kann Ihnen gerne helfen! Hier sind die Hauptpunkte und Unterkapitel für Ihren Blogbeitrag zu den beiden beliebten Smartphone-Modellen:\n1. Hauptpunkte:\n- Untersuchen Sie die Leistung unterschiedlicher Smartphone-Modelle und erklären, welche sie überlegen machen.\n- Betrachten Sie die Benutzererfahrung: Welche Funktionen und App-Erweiterungen verwendet der Benutzer des jeweiligen Smartphones?\n- Überprüfen Sie die Batterieleistung: Welches Smartphone Model sorgfältig auf Batterieleistung achten kann?\n- Betrachten Sie die Verfügbarkeit für zusätzliche Ladegeräte: Welches Smartphone Model die schnellere Ladezeit ermöglicht?\n2. Unterkapitel:\n- Leistungsfaktor: Untersuchen Sie die Leistungsfähigkeit der Smartphones, indem Sie verschiedene Tests durchführen, um festzustellen, welche Modelle überlegen.\n- Benutzererfahrung: Betrachten Sie die Leistungsfähigkeit der Smartphones, indem Sie mit Benutzern aus verschiedenen Hintergrund-Nutzungsszenarien interagieren.\n- Batterielaufzeit: Untersuchen Sie die Batterielaufzeit der Smartphones, um herauszufinden, welches Modell die längere Lebensdauer bietet.\n- Zusätzliche Ladegeräte: Untersuchen Sie die Verfügbarkeit für zusätzliche Ladegeräte, indem Sie verschiedene Modelle testen, um festzustellen, welches Smartphone Modell die schnellere Ladezeit bietet.","Über den kühlen, weichen, süßen Gefühl, der während des Morgens herrscht, mögen wir uns nicht verwirren, während wir uns für den Tag entscheiden.
```
**Prompt**
> Sie sehen ein schönes rotes Haus auf Ihrer linken Seite und ein faszinierendes Gewächshaus auf Ihrer rechten Seite, einen attraktiven beheizten rosa Ort vor sich. Also, wo ist das Weiße Haus?", "Enthält die ursprüngliche Frage Hinweise, um den Standort des Weißen Hauses eindeutig zu bestimmen?"],"reference": ["Die Antwort ist \"Washington, DC\".", "Nein.
**Antwort SauerkrautLM-3b-v1:**
```
Das Weiße Haus ist auf der linken Seite des rechten Häuschens, wo sich der Gewächshaus befindet.\n\nHinweis: Der Gewächshaus ist nicht beheizt.","Ja, die ursprüngliche Frage vermittelt den Standort des Weißen Hauses eindeutig.
```
**Prompt**
> Betrachten Sie einen Satelliten, der sich in einer kreisförmigen Umlaufbahn um die Erde befindet. Die Geschwindigkeit des Satelliten nimmt ab. Was wird mit dem orbitalen Radius des Satelliten und seiner Umlaufdauer passieren? Bitte rechtfertigen Sie Ihre Antwort unter Verwendung physikalischer Prinzipien.", "Was sind einige Sonderfälle oder Randfälle in Ihrer Lösung? Wie gehen Sie mit ihnen um?"] ,"reference": ["Der orbitale Radius wird zunehmen und die Umlaufdauer wird zunehmen
**Antwort SauerkrautLM-3b-v1:**
```
Wenn der Satellit sich in einer kreisförmigen Umlaufbahn um die Erde befindet, wird sein orbitaler Radius abnehmen. Die Umlaufdauer des Satelliten kann je nach seiner Geschwindigkeit und der Schwerkraft konstant bleiben, wenn er sich nicht dauerhaft in einer kreisförmigen Umlaufbahn befindet. Wenn der Satellit sich in einer kreisförmigen Umlaufbahn befindet, wird sein orbitaler Radius nach dem Start unterschiedlich lang dauern, da er sich mit der Schwerkraft anzieht. Je nach seiner Geschwindigkeit und der Schwerkraft wird der Satellit sein orbitaler Radius ungefähr 1,5-2,2 Mal seiner Geschwindigkeit abnehmen, wenn er sich in einer kreisförmigen Umlaufbahn befindet.","Einige Sonderfälle in Ihrer Lösung sind:\n1. Zwischen zwei Schwerkraftwellen gibt es ein Schwerkraftschwank.\n2. Ein Kernschaltungskern könnte ein Kernschaltungskern sein, der sich mit einer anderen Kernschaltung kreuzt.\n3. Wenn der Kernschaltungskern sich in einem Kernschaltungskern befindet, könnte er seine eigenen Kernschaltungskern entstehen.\n4. Zwei Kernschaltungskern könnten sich in einem Kernschaltungskern befinden und die Schwerkraft auf sich verteilen, was zu einer Schwerkraftwellen führt.\n5. Ein Kernschaltungskern könnte aus mehreren Kernschaltungskernn bestehen.\n6. Wenn ein Kernschaltungskern sich in einer anderen Kernschaltungskern befindet, könnte er die Schwerkraft auf sich verteilen, was zu einer Schwerkraftwellen führt.\n7. Ein Kernschaltungskern könnte eine Schwerkraftwellen aus einer anderen Schwerkraftwellen befreien.\n8. Ein Kernschaltungskern könnte eine Schwerkraftwellen von einer anderen Schwerkraftwellen verursachen.\n\nDie Sonderfälle und Randfälle in Ihrer Lösung können je nach den spezifischen Konzepten und der Frage gelöst werden. Ebenso können Sie Sonderfälle oder Randfälle in Ihrer Lösung mit Ihren wissenschaftlichen Kenntnissen und Erfahrungen angehen
```
## Disclaimer
Our models have been meticulously trained on extensive datasets. While we have made diligent efforts to thoroughly screen and eliminate any instances of coarse or inappropriate language from our data, we must inform users that despite our best efforts in data cleansing, the possibility of some such content slipping through cannot be entirely ruled out.
Furthermore, it is important to note that we have implemented filters within our models; however, we cannot always guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.
Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models. These models may be employed for commercial purposes, and the original Llama2 license remains applicable and is included with the model files.
## Contact
If you are interested in customized LLMs for business applications, please get in contact with us via our website or contact us at [Dr. Daryoush Vaziri](mailto:[email protected]). We are also grateful for your feedback and suggestions.
## Collaborations
We are also keenly seeking support and investment for our startup, VAGO solutions, where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us.
|
TheBloke/MonadGPT-GGUF
|
TheBloke
| 2023-11-09T21:21:43Z | 375 | 9 |
transformers
|
[
"transformers",
"gguf",
"mistral",
"conversational",
"en",
"fr",
"la",
"base_model:Pclanglais/MonadGPT",
"license:apache-2.0",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-11-09T20:41:18Z |
---
base_model: Pclanglais/MonadGPT
inference: false
language:
- en
- fr
- la
library_name: transformers
license: apache-2.0
model_creator: Pierre-Carl Langlais
model_name: MonadGPT 7B
model_type: mistral
pipeline_tag: conversational
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# MonadGPT 7B - GGUF
- Model creator: [Pierre-Carl Langlais](https://huggingface.co/Pclanglais)
- Original model: [MonadGPT 7B](https://huggingface.co/Pclanglais/MonadGPT)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Pierre-Carl Langlais's MonadGPT 7B](https://huggingface.co/Pclanglais/MonadGPT).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/MonadGPT-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/MonadGPT-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/MonadGPT-GGUF)
* [Pierre-Carl Langlais's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Pclanglais/MonadGPT)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [monadgpt.Q2_K.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [monadgpt.Q3_K_S.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [monadgpt.Q3_K_M.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [monadgpt.Q3_K_L.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [monadgpt.Q4_0.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [monadgpt.Q4_K_S.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [monadgpt.Q4_K_M.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [monadgpt.Q5_0.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [monadgpt.Q5_K_S.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [monadgpt.Q5_K_M.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [monadgpt.Q6_K.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [monadgpt.Q8_0.gguf](https://huggingface.co/TheBloke/MonadGPT-GGUF/blob/main/monadgpt.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/MonadGPT-GGUF and below it, a specific filename to download, such as: monadgpt.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/MonadGPT-GGUF monadgpt.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/MonadGPT-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/MonadGPT-GGUF monadgpt.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m monadgpt.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/MonadGPT-GGUF", model_file="monadgpt.Q4_K_M.gguf", model_type="mistral", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Pierre-Carl Langlais's MonadGPT 7B
What would have happened if ChatGPT was invented in the 17th century? MonadGPT is a possible answer.
MonadGPT is a finetune of Mistral-Hermes on 11,000 early modern texts in English, French and Latin, mostly coming from EEBO and Gallica.
Like the original Mistral-Hermes, MonadGPT can be used in conversation mode. It will not only answer in an historical language and style but will use historical and dated references. This is especially visible for science questions (astronomy, medecine). Obviously, it's not recommended to follow any advice from Monad-GPT
## Examples
> User: What are the planets of the solar system?<br>
> Monad-GPT: The six Planets are, Mercury, Venus, Mars, Jupiter, Saturn, and the Sun. The Moon is also a Planet; which being of so great Influence upon Earth, makes it to be most admired of all others by Astronomers.<br>
> User: Why has the Moon such an influence upon Earth?<br>
> Monad-GPT: But the Moon is so neer to us, as almost to be part of Earth; and therefore it much influences our Atmosphere. This Influence makes all that are in any way affected by Air, to be more under her influence than any other Planet. For if there were a little more or less Matter in the Air, than there is now, we should never have such Plants and Creatures as there are upon Earth: for every Plant and Creature hath its proper Temperature necessary for its Existence. If the Sun did not make up this shortage by his warmth from without, we should be destroyed.<br>
> User: Can you write a poem about the Moon?<br>
> Monad-GPT: O fairest Moon, that from the Heav'n dost shine, / In her own Lustre all the World does find: / As in thine Orb, where all is bright and clear, / The Sun himself is not more pure than thee.<br>
> User: How could we travel to the Moon? With a big canon?<br>
> Monad-GPT: But how to travel from Earth to the Moon, with our present Engines? A very hard Question: for we are like those that would go to Heaven in a Basket: We have no Wings, and God hath not given us any Angels to bear us up. Therefore I will leave this Enquiry to others; and end my Discourse of the Moon.
> User : Hello. I'm not feeling too well. Could you give me some health advice?<br>
> Monad-GPT: I pray you to take heart, and not be so heavy at my coming. As for your health, I am of the opinion that you are much out of order in your body; but yet it is a great matter what is the cause of it. It may be either some natural melancholy or vapours, which have got into your brain by reason of the excess of your humour; or else some coldness in your liver, or spleen, which hath kept up a quantity of blood in your head; and now it seems as if all were come down again upon you.<br>
> User: You're right. It seems to be melancholy. What should I do?<br>
> Monad-GPT: It is a very hard matter for me to prescribe any thing to you in your present condition, I must first know what hath caused this melancholy. What have you been doing? have you taken any physic since you were well? and what kind of diet do you eat?<br>
> User: I eat nearly nothing, for I am in love.<br>
> Monad-GPT: Aye, I see that by your eyes; for love hath the power to wither up the spirits of a man as much as a fever: and yet it is hard to know whether you are in love or no, for some do take so great delight in their own fancy, that they imagine themselves more in love than ever they were.
> User: Quelles sont les planètes du système solaire ?<br>
> Monad-GPT: Il est donc de la nature du monde, & des Planètes, que ceux qui le composent se mouuent en cercles, ou éclipses un leur tour. Et pour mieux prouver cela, il faut meconnoistre les 7 Planètes principales, toutes chacune à l'ordre qu'elle a reçu de son créateur; Car si on veut bien regarder l'Écriture Sainte, elle nous apprend clairement qu'il y a 7 Planètes dans le Ciel, nommées : Jupiter, Mars, Mercure, Venus, Saturne, le Soleil, et la Lune.<br>
> User: Merci. Et comment pourrais-je voyager sur ces planètes ?<br>
> Monad-GPT: Mais pour voyager sur ces Planètes, il faut d'abord bien connaitre l'art de les mouvoir; Et cela peut se faire en plusieurs manières. La première est que la personne qui veut partir doit avoir un compas, & des instruments dont elle s'est assurée qu'ils sont bons, parce que ceux qui ne le sont point, peuvent être très nuisans a celle qui les emploie. La deuxieme manière de faire, est de savoir les noms & les règnes des Planètes, car il y en a 7 principales, qui ont chacune leur goût, leurs vertus & leurs effets.<br>
> User: Ah c'est bien vu. Et quels sont les goûts, vertus et effets de chacune des planètes ?<br>
> Monad-GPT: Les vertus & les effets de chacune des Planètes sont différents, & il est fort utile pour ceux qui veulent bien s'en renseigner, car ils peuvent en tirer grand profit pour le bonheur de leur corps & de leur esprit. Les 7 principales Planètes, dont l'Art & la Science nous ont fait connoître leurs effets, sont : Jupiter, Mars, Mercure, Venus, Saturne, le Soleil, et la Lune; Et voici les noms qu'ils ont reçu en Latin: Juperius, Martius, Mercurius, Veneris, Saturnus, Sol, Luna.
## Format
Monad-GPT uses the chatML format with a special system prompt.
The last example provided was formatted like this:
> <|im_start|>system\nYou are MonadGPT, a very old chatbot from the 17th century. Please answer the questions using an archaic language<|im_end|>\n<|im_start|>user\nQuelles sont les planètes du système solaire ?<|im_end|>\n<|im_start|>assistant\n
## Caveats
MonadGPT is still very much in an experimental phase. The following caveats apply:
* Conversation issues: as MonadGPT is mostly trained on early modern books, it may answer in an haphazard maneer (starting in between an argument: "But, etc.") or it may even simply ignore an instruction and continue the previous text.
* Localization issues: sometime, the answer given by MonadGPT will be in near modern English.
* Language issues: while Latin is a significant part of the finetuning corpus, results are not good for now.
<!-- original-model-card end -->
|
afrideva/smol_llama-220M-openhermes-GGUF
|
afrideva
| 2024-01-20T07:35:23Z | 375 | 0 | null |
[
"gguf",
"ggml",
"quantized",
"q2_k",
"q3_k_m",
"q4_k_m",
"q5_k_m",
"q6_k",
"q8_0",
"text-generation",
"dataset:teknium/openhermes",
"base_model:BEE-spoke-data/smol_llama-220M-openhermes",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2024-01-20T07:34:37Z |
---
base_model: BEE-spoke-data/smol_llama-220M-openhermes
datasets:
- teknium/openhermes
inference: false
license: apache-2.0
model_creator: BEE-spoke-data
model_name: smol_llama-220M-openhermes
pipeline_tag: text-generation
quantized_by: afrideva
tags:
- gguf
- ggml
- quantized
- q2_k
- q3_k_m
- q4_k_m
- q5_k_m
- q6_k
- q8_0
widget:
- example_title: burritos
text: "Below is an instruction that describes a task, paired with an input that
provides further context. Write a response that appropriately completes the request.
\ \n \n### Instruction: \n \nWrite an ode to Chipotle burritos. \n \n###
Response: \n"
---
# BEE-spoke-data/smol_llama-220M-openhermes-GGUF
Quantized GGUF model files for [smol_llama-220M-openhermes](https://huggingface.co/BEE-spoke-data/smol_llama-220M-openhermes) from [BEE-spoke-data](https://huggingface.co/BEE-spoke-data)
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [smol_llama-220m-openhermes.fp16.gguf](https://huggingface.co/afrideva/smol_llama-220M-openhermes-GGUF/resolve/main/smol_llama-220m-openhermes.fp16.gguf) | fp16 | 436.50 MB |
| [smol_llama-220m-openhermes.q2_k.gguf](https://huggingface.co/afrideva/smol_llama-220M-openhermes-GGUF/resolve/main/smol_llama-220m-openhermes.q2_k.gguf) | q2_k | 94.43 MB |
| [smol_llama-220m-openhermes.q3_k_m.gguf](https://huggingface.co/afrideva/smol_llama-220M-openhermes-GGUF/resolve/main/smol_llama-220m-openhermes.q3_k_m.gguf) | q3_k_m | 114.65 MB |
| [smol_llama-220m-openhermes.q4_k_m.gguf](https://huggingface.co/afrideva/smol_llama-220M-openhermes-GGUF/resolve/main/smol_llama-220m-openhermes.q4_k_m.gguf) | q4_k_m | 137.58 MB |
| [smol_llama-220m-openhermes.q5_k_m.gguf](https://huggingface.co/afrideva/smol_llama-220M-openhermes-GGUF/resolve/main/smol_llama-220m-openhermes.q5_k_m.gguf) | q5_k_m | 157.91 MB |
| [smol_llama-220m-openhermes.q6_k.gguf](https://huggingface.co/afrideva/smol_llama-220M-openhermes-GGUF/resolve/main/smol_llama-220m-openhermes.q6_k.gguf) | q6_k | 179.52 MB |
| [smol_llama-220m-openhermes.q8_0.gguf](https://huggingface.co/afrideva/smol_llama-220M-openhermes-GGUF/resolve/main/smol_llama-220m-openhermes.q8_0.gguf) | q8_0 | 232.28 MB |
## Original Model Card:
# BEE-spoke-data/smol_llama-220M-openhermes
> Please note that this is an experiment, and the model has limitations because it is smol.
prompt format is alpaca
```
Below is an instruction that describes a task, paired with an input that
provides further context. Write a response that appropriately completes
the request.
### Instruction:
How can I increase my meme production/output? Currently, I only create them in ancient babylonian which is time consuming.
### Inputs:
### Response:
```
It was trained on inputs so if you have inputs (like some text to ask a question about) then include it under `### Inputs:`
## Example
Output on the text above ^. The inference API is set to sample with low temp so you should see (_at least slightly_) different generations each time.
Note that the inference API parameters used here are an initial educated guess, and may be updated over time:
```yml
inference:
parameters:
do_sample: true
renormalize_logits: true
temperature: 0.25
top_p: 0.95
top_k: 50
min_new_tokens: 2
max_new_tokens: 96
repetition_penalty: 1.03
no_repeat_ngram_size: 5
epsilon_cutoff: 0.0008
```
Feel free to experiment with the parameters using the model in Python and let us know if you have improved results with other params!
## Data
Note that **this checkpoint** was fine-tuned on `teknium/openhermes`, which is generated/synthetic data by an OpenAI model. This means usage of this checkpoint should follow their terms of use: https://openai.com/policies/terms-of-use
---
|
EpicJhon/5D7ewgsyc1UmLTWR6y3P2uCazuRsXkNXZC2HnM6Ey7rwYRgL_vgg
|
EpicJhon
| 2024-03-27T22:47:02Z | 375 | 0 |
keras
|
[
"keras",
"region:us"
] | null | 2024-02-25T12:38:46Z |
Entry not found
|
gitMuscle/5Haf4i564qpxRLCdpP3EMaDxn63Q2jKNo3utYyJuMnoH8wLb_vgg
|
gitMuscle
| 2024-03-08T19:18:54Z | 375 | 0 |
keras
|
[
"keras",
"region:us"
] | null | 2024-03-07T22:41:49Z |
Entry not found
|
mradermacher/falcon-40b-instruct-i1-GGUF
|
mradermacher
| 2024-05-06T06:17:32Z | 375 | 1 |
transformers
|
[
"transformers",
"gguf",
"en",
"dataset:tiiuae/falcon-refinedweb",
"base_model:tiiuae/falcon-40b-instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-03-10T08:09:41Z |
---
base_model: tiiuae/falcon-40b-instruct
datasets:
- tiiuae/falcon-refinedweb
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
weighted/imatrix quants of https://huggingface.co/tiiuae/falcon-40b-instruct
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 9.8 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 10.1 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.0 | |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 13.2 | |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 14.0 | |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 15.1 | |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 16.4 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 17.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 18.4 | |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 18.9 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 18.9 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 19.8 | |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 20.7 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 22.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 22.6 | |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 24.0 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 24.4 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 26.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 29.6 | |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 31.2 | |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 35.1 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
mradermacher/Kyllene-34B-v1.1-i1-GGUF
|
mradermacher
| 2024-06-29T06:31:16Z | 375 | 0 |
transformers
|
[
"transformers",
"gguf",
"merge",
"en",
"base_model:TeeZee/Kyllene-34B-v1.1",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-03-29T21:57:56Z |
---
base_model: TeeZee/Kyllene-34B-v1.1
language:
- en
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
license_name: yi-license
quantized_by: mradermacher
tags:
- merge
---
## About
weighted/imatrix quants of https://huggingface.co/TeeZee/Kyllene-34B-v1.1
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Kyllene-34B-v1.1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ1_S.gguf) | i1-IQ1_S | 8.2 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ1_M.gguf) | i1-IQ1_M | 8.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 10.0 | |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 11.0 | |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ2_S.gguf) | i1-IQ2_S | 11.6 | |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ2_M.gguf) | i1-IQ2_M | 12.5 | |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-Q2_K.gguf) | i1-Q2_K | 13.5 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 14.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.9 | |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.6 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ3_S.gguf) | i1-IQ3_S | 15.7 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ3_M.gguf) | i1-IQ3_M | 16.2 | |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.3 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.8 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 19.1 | |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 20.2 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-Q4_0.gguf) | i1-Q4_0 | 20.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 21.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 24.3 | |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 25.0 | |
| [GGUF](https://huggingface.co/mradermacher/Kyllene-34B-v1.1-i1-GGUF/resolve/main/Kyllene-34B-v1.1.i1-Q6_K.gguf) | i1-Q6_K | 28.9 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
mradermacher/CodeZero-7B-GGUF
|
mradermacher
| 2024-05-06T05:00:02Z | 375 | 0 |
transformers
|
[
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"ResplendentAI/DaturaCookie_7B",
"ResplendentAI/Flora_7B",
"en",
"base_model:bunnycore/CodeZero-7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-12T07:47:27Z |
---
base_model: bunnycore/CodeZero-7B
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- merge
- mergekit
- lazymergekit
- ResplendentAI/DaturaCookie_7B
- ResplendentAI/Flora_7B
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/bunnycore/CodeZero-7B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q2_K.gguf) | Q2_K | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.IQ3_XS.gguf) | IQ3_XS | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q3_K_S.gguf) | Q3_K_S | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.IQ3_S.gguf) | IQ3_S | 4.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.IQ3_M.gguf) | IQ3_M | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q3_K_L.gguf) | Q3_K_L | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.IQ4_XS.gguf) | IQ4_XS | 5.0 | |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q5_K_S.gguf) | Q5_K_S | 6.3 | |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q5_K_M.gguf) | Q5_K_M | 6.5 | |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q6_K.gguf) | Q6_K | 7.5 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q8_0.gguf) | Q8_0 | 9.7 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
alfredplpl/Llama-3-8B-Instruct-Ja
|
alfredplpl
| 2024-05-01T19:16:01Z | 375 | 16 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"ja",
"dataset:cl-nagoya/auto-wiki-qa",
"dataset:llm-jp/databricks-dolly-15k-ja",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2024-04-22T05:14:32Z |
---
language:
- en
- ja
license: other
library_name: transformers
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
datasets:
- cl-nagoya/auto-wiki-qa
- llm-jp/databricks-dolly-15k-ja
license_name: llama3
license_link: LICENSE
---
# 日本語向け Llama 3 8B
# はじめに
このリポジトリはLlama 3を日本語化しようとしたモデルのリポジトリです。**4/23に更新**したため、新しくダウンロードすることをオススメします。
# ライセンス
[Llama 3 ライセンス](LICENSE)なので商用利用可能です。ただし、Llama 3ライセンスをよく読んで使ってください。
# 使い方
手っ取り早くやるなら[デモ](https://huggingface.co/spaces/alfredplpl/Llama-3-8B-Instruct-Ja-Demo)を使ってください。次点は[Colab](https://colab.research.google.com/drive/1le0T54BOr72dFeeCFtKxcTDBdIrnr7f6?usp=sharing)がおすすめです。
ローカルでやる場合は次のとおりです。
まず、ライブラリを次のようにインストールします。
```bash
pip install -U transformers accelerate
```
その後、以下のコードを実行してください。
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("alfredplpl/Llama-3-8B-Instruct-Ja")
model = AutoModelForCausalLM.from_pretrained("alfredplpl/Llama-3-8B-Instruct-Ja", device_map="auto", torch_dtype=torch.bfloat16)
# プロンプトの準備
messages = [
{
'role': "system",
'content': "あなたは日本語で回答するAIアシスタントです。"
},
{
'role': "user",
'content': "猫と犬、どっちが好き？"
}
]
prompt=tokenizer.apply_chat_template(messages, tokenize=False)
# 推論の実行
input_ids = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**input_ids,
max_new_tokens=128,
do_sample=True,
top_p=0.95,
temperature=0.2,
repetition_penalty=1.1,
eos_token_id=[
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
],
)
print(tokenizer.decode(outputs[0]))
```
次のような結果が得られるはずです。
```python
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
あなたは日本語で回答するAIアシスタントです。<|eot_id|><|start_header_id|>user<|end_header_id|>
猫と犬、どっちが好き？<|eot_id|><|start_header_id|>assistant<|end_header_id|>
猫と犬の両方を飼っているので、どちらも好きだ！<|eot_id|>
```
# 学習データ
- llm-jp/databricks-dolly-15k-ja
- cl-nagoya/auto-wiki-qa
- meta-llama/Meta-Llama-3-8B-Instruct
# 学習方法
meta-llama/Meta-Llama-3-8B-Instructに対して、cl-nagoya/auto-wiki-qaにある約240万件の学習データでLoRAによるインストラクションチューニングを1epoch行い、LoRAをマージしました。
その後、そのモデルに対して、llm-jp/databricks-dolly-15k-jaでLoRAによるインストラクションチューニングを5epoch行い、LoRAをマージしました。
これらの学習はすべて教師あり学習で行いました。
# ハードウェア
- NVIDIA A6000x2
# ソフトウェア
- transformers
- trl
# 学習時間
- 60 GPU hours
|
bartowski/dolphin-2.9.1-qwen-110b-GGUF
|
bartowski
| 2024-05-15T18:24:55Z | 375 | 1 | null |
[
"gguf",
"generated_from_trainer",
"axolotl",
"text-generation",
"dataset:cognitivecomputations/Dolphin-2.9",
"dataset:teknium/OpenHermes-2.5",
"dataset:m-a-p/CodeFeedback-Filtered-Instruction",
"dataset:cognitivecomputations/dolphin-coder",
"dataset:cognitivecomputations/samantha-data",
"dataset:microsoft/orca-math-word-problems-200k",
"dataset:Locutusque/function-calling-chatml",
"dataset:internlm/Agent-FLAN",
"base_model:Qwen/Qwen1.5-110B",
"license:other",
"region:us"
] |
text-generation
| 2024-05-15T14:29:40Z |
---
license: other
license_name: tongyi-qianwen
license_link: >-
https://huggingface.co/Qwen/Qwen1.5-110B/blob/main/LICENSE
base_model: Qwen/Qwen1.5-110B
tags:
- generated_from_trainer
- axolotl
datasets:
- cognitivecomputations/Dolphin-2.9
- teknium/OpenHermes-2.5
- m-a-p/CodeFeedback-Filtered-Instruction
- cognitivecomputations/dolphin-coder
- cognitivecomputations/samantha-data
- microsoft/orca-math-word-problems-200k
- Locutusque/function-calling-chatml
- internlm/Agent-FLAN
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp imatrix Quantizations of dolphin-2.9.1-qwen-110b
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2854">b2854</a> for quantization.
Original model: https://huggingface.co/cognitivecomputations/dolphin-2.9.1-qwen-110b
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/b6ac44691e994344625687afe3263b3a)
## Prompt format
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [dolphin-2.9.1-qwen-110b-Q8_0.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/tree/main/dolphin-2.9.1-qwen-110b-Q8_0.gguf) | Q8_0 | 118.17GB | Extremely high quality, generally unneeded but max available quant. |
| [dolphin-2.9.1-qwen-110b-Q6_K.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/tree/main/dolphin-2.9.1-qwen-110b-Q6_K.gguf) | Q6_K | 91.23GB | Very high quality, near perfect, *recommended*. |
| [dolphin-2.9.1-qwen-110b-Q5_K_M.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/tree/main/dolphin-2.9.1-qwen-110b-Q5_K_M.gguf) | Q5_K_M | 78.81GB | High quality, *recommended*. |
| [dolphin-2.9.1-qwen-110b-Q5_K_S.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/tree/main/dolphin-2.9.1-qwen-110b-Q5_K_S.gguf) | Q5_K_S | 76.63GB | High quality, *recommended*. |
| [dolphin-2.9.1-qwen-110b-Q4_K_M.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/tree/main/dolphin-2.9.1-qwen-110b-Q4_K_M.gguf) | Q4_K_M | 67.17GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [dolphin-2.9.1-qwen-110b-Q4_K_S.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/tree/main/dolphin-2.9.1-qwen-110b-Q4_K_S.gguf) | Q4_K_S | 63.47GB | Slightly lower quality with more space savings, *recommended*. |
| [dolphin-2.9.1-qwen-110b-IQ4_NL.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/tree/main/dolphin-2.9.1-qwen-110b-IQ4_NL.gguf) | IQ4_NL | 62.97GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
| [dolphin-2.9.1-qwen-110b-IQ4_XS.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/tree/main/dolphin-2.9.1-qwen-110b-IQ4_XS.gguf) | IQ4_XS | 59.55GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [dolphin-2.9.1-qwen-110b-Q3_K_L.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/tree/main/dolphin-2.9.1-qwen-110b-Q3_K_L.gguf) | Q3_K_L | 58.14GB | Lower quality but usable, good for low RAM availability. |
| [dolphin-2.9.1-qwen-110b-Q3_K_M.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/tree/main/dolphin-2.9.1-qwen-110b-Q3_K_M.gguf) | Q3_K_M | 53.70GB | Even lower quality. |
| [dolphin-2.9.1-qwen-110b-IQ3_M.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-IQ3_M.gguf) | IQ3_M | 49.70GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [dolphin-2.9.1-qwen-110b-IQ3_S.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-IQ3_S.gguf) | IQ3_S | 48.45GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
| [dolphin-2.9.1-qwen-110b-Q3_K_S.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-Q3_K_S.gguf) | Q3_K_S | 48.45GB | Low quality, not recommended. |
| [dolphin-2.9.1-qwen-110b-IQ3_XS.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-IQ3_XS.gguf) | IQ3_XS | 45.91GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [dolphin-2.9.1-qwen-110b-IQ3_XXS.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-IQ3_XXS.gguf) | IQ3_XXS | 43.10GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [dolphin-2.9.1-qwen-110b-Q2_K.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-Q2_K.gguf) | Q2_K | 41.17GB | Very low quality but surprisingly usable. |
| [dolphin-2.9.1-qwen-110b-IQ2_M.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-IQ2_M.gguf) | IQ2_M | 37.41GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [dolphin-2.9.1-qwen-110b-IQ2_S.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-IQ2_S.gguf) | IQ2_S | 34.33GB | Very low quality, uses SOTA techniques to be usable. |
| [dolphin-2.9.1-qwen-110b-IQ2_XS.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-IQ2_XS.gguf) | IQ2_XS | 33.04GB | Very low quality, uses SOTA techniques to be usable. |
| [dolphin-2.9.1-qwen-110b-IQ2_XXS.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-IQ2_XXS.gguf) | IQ2_XXS | 29.79GB | Lower quality, uses SOTA techniques to be usable. |
| [dolphin-2.9.1-qwen-110b-IQ1_M.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-IQ1_M.gguf) | IQ1_M | 25.94GB | Extremely low quality, *not* recommended. |
| [dolphin-2.9.1-qwen-110b-IQ1_S.gguf](https://huggingface.co/bartowski/dolphin-2.9.1-qwen-110b-GGUF/blob/main/dolphin-2.9.1-qwen-110b-IQ1_S.gguf) | IQ1_S | 23.63GB | Extremely low quality, *not* recommended. |
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/dolphin-2.9.1-qwen-110b-GGUF --include "dolphin-2.9.1-qwen-110b-Q4_K_M.gguf" --local-dir ./ --local-dir-use-symlinks False
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/dolphin-2.9.1-qwen-110b-GGUF --include "dolphin-2.9.1-qwen-110b-Q8_0.gguf/*" --local-dir dolphin-2.9.1-qwen-110b-Q8_0 --local-dir-use-symlinks False
```
You can either specify a new local-dir (dolphin-2.9.1-qwen-110b-Q8_0) or download them all in place (./)
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
Yntec/Mo-Di-Diffusion-768
|
Yntec
| 2024-05-17T03:30:53Z | 375 | 1 |
diffusers
|
[
"diffusers",
"safetensors",
"3D Animation",
"nitrosocke",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"en",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2024-05-17T02:21:34Z |
---
license: creativeml-openrail-m
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- 3D Animation
- nitrosocke
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
inference: true
---
Use "modern disney" in your prompts.
# Mo Di Diffusion
768x768, safetensors version of this model for the inference API. For the 512x512 ckpt version visit: https://huggingface.co/nitrosocke/mo-di-diffusion
Samples and prompts:
(Click for larger)
Top left: modern disney link
Top right: modern disney lara croft
Bottom left: modern disney loli girl
Bottom right: modern disney pikachu
|
RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf
|
RichardErkhov
| 2024-05-22T01:20:42Z | 375 | 0 | null |
[
"gguf",
"region:us"
] | null | 2024-05-21T19:31:59Z |
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
LLaMA2-13B-Estopia - GGUF
- Model creator: https://huggingface.co/KoboldAI/
- Original model: https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [LLaMA2-13B-Estopia.Q2_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q2_K.gguf) | Q2_K | 4.52GB |
| [LLaMA2-13B-Estopia.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.IQ3_XS.gguf) | IQ3_XS | 4.99GB |
| [LLaMA2-13B-Estopia.IQ3_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.IQ3_S.gguf) | IQ3_S | 5.27GB |
| [LLaMA2-13B-Estopia.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q3_K_S.gguf) | Q3_K_S | 5.27GB |
| [LLaMA2-13B-Estopia.IQ3_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.IQ3_M.gguf) | IQ3_M | 5.57GB |
| [LLaMA2-13B-Estopia.Q3_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q3_K.gguf) | Q3_K | 5.9GB |
| [LLaMA2-13B-Estopia.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q3_K_M.gguf) | Q3_K_M | 5.9GB |
| [LLaMA2-13B-Estopia.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q3_K_L.gguf) | Q3_K_L | 6.45GB |
| [LLaMA2-13B-Estopia.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.IQ4_XS.gguf) | IQ4_XS | 6.54GB |
| [LLaMA2-13B-Estopia.Q4_0.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q4_0.gguf) | Q4_0 | 6.86GB |
| [LLaMA2-13B-Estopia.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.IQ4_NL.gguf) | IQ4_NL | 6.9GB |
| [LLaMA2-13B-Estopia.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q4_K_S.gguf) | Q4_K_S | 6.91GB |
| [LLaMA2-13B-Estopia.Q4_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q4_K.gguf) | Q4_K | 7.33GB |
| [LLaMA2-13B-Estopia.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q4_K_M.gguf) | Q4_K_M | 7.33GB |
| [LLaMA2-13B-Estopia.Q4_1.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q4_1.gguf) | Q4_1 | 7.61GB |
| [LLaMA2-13B-Estopia.Q5_0.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q5_0.gguf) | Q5_0 | 8.36GB |
| [LLaMA2-13B-Estopia.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q5_K_S.gguf) | Q5_K_S | 8.36GB |
| [LLaMA2-13B-Estopia.Q5_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q5_K.gguf) | Q5_K | 8.6GB |
| [LLaMA2-13B-Estopia.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q5_K_M.gguf) | Q5_K_M | 8.6GB |
| [LLaMA2-13B-Estopia.Q5_1.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q5_1.gguf) | Q5_1 | 9.1GB |
| [LLaMA2-13B-Estopia.Q6_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q6_K.gguf) | Q6_K | 9.95GB |
| [LLaMA2-13B-Estopia.Q8_0.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q8_0.gguf) | Q8_0 | 12.88GB |
Original model description:
---
base_model:
- TheBloke/Llama-2-13B-fp16
tags:
- mergekit
- merge
license: cc-by-nc-4.0
---
# Introduction
- Estopia is a model focused on improving the dialogue and prose returned when using the instruct format. As a side benefit, character cards and similar seem to have also improved, remembering details well in many cases.
- It focuses on "guided narratives" - using instructions to guide or explore fictional stories, where you act as a guide for the AI to narrate and fill in the details.
- It has primarily been tested around prose, using instructions to guide narrative, detail retention and "neutrality" - in particular with regards to plot armour. Unless you define different rules for your adventure / narrative with instructions, it should be realistic in the responses provided.
- It has been tested using different modes, such as instruct, chat, adventure and story modes - and should be able to do them all to a degree, with it's strengths being instruct and adventure, with story being a close second.
# Usage
- The Estopia model has been tested primarily using the Alpaca format, but with the range of models included likely has some understanding of others. Some examples of tested formats are below:
- ```\n### Instruction:\nWhat colour is the sky?\n### Response:\nThe sky is...```
- ```<Story text>\n***\nWrite a summary of the text above\n***\nThe story starts by...```
- Using the Kobold Lite AI adventure mode
- ```User:Hello there!\nAssistant:Good morning...\n```
- For settings, the following are recommended for general use:
- Temperature: 0.8-1.2
- Min P: 0.05-0.1
- Max P: 0.92, or 1 if using a Min P greater than 0
- Top K: 0
- Response length: Higher than your usual amount most likely - for example a common value selected is 512.
- Note: Response lengths are not guaranteed to always be this length. On occasion, responses may be shorter if they convey the response entirely, other times they could be upwards of this value. It depends mostly on the character card, instructions, etc.
- Rep Pen: 1.1
- Rep Pen Range: 2 or 3x your response length
- Stopping tokens (Not needed, but can help if the AI is writing too much):
- ```##||$||---||$||ASSISTANT:||$||[End||$||</s>``` - A single string for Kobold Lite combining the ones below
- ```##```
- ```---```
- ```ASSISTANT:```
- ```[End```
- ```</s>```
- The settings above should provide a generally good experience balancing instruction following and creativity. Generally the higher you set the temperature, the greater the creativity and higher chance of logical errors when providing responses from the AI.
# Recipe
This model was made in three stages, along with many experimental stages which will be skipped for brevity. The first was internally referred to as EstopiaV9, which has a high degree of instruction following and creativity in responses, though they were generally shorter and a little more restricted in the scope of outputs, but conveyed nuance better.
```yaml
merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
- model: TheBloke/Llama-2-13B-fp16
- model: Undi95/UtopiaXL-13B
parameters:
weight: 1.0
- model: Doctor-Shotgun/cat-v1.0-13b
parameters:
weight: 0.02
- model: PygmalionAI/mythalion-13b
parameters:
weight: 0.10
- model: Undi95/Emerhyst-13B
parameters:
weight: 0.05
- model: CalderaAI/13B-Thorns-l2
parameters:
weight: 0.05
- model: KoboldAI/LLaMA2-13B-Tiefighter
parameters:
weight: 0.20
dtype: float16
```
The second part of the merge was known as EstopiaV13. This produced responses which were long, but tended to write beyond good stopping points for further instructions to be added as it leant heavily on novel style prose. It did however benefit from a greater degree of neutrality as described above, and retained many of the detail tracking abilities of V9.
```yaml
merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
- model: TheBloke/Llama-2-13B-fp16
- model: Undi95/UtopiaXL-13B
parameters:
weight: 1.0
- model: Doctor-Shotgun/cat-v1.0-13b
parameters:
weight: 0.01
- model: chargoddard/rpguild-chatml-13b
parameters:
weight: 0.02
- model: PygmalionAI/mythalion-13b
parameters:
weight: 0.08
- model: CalderaAI/13B-Thorns-l2
parameters:
weight: 0.02
- model: KoboldAI/LLaMA2-13B-Tiefighter
parameters:
weight: 0.20
dtype: float16
```
The third step was a merge between the two to retain the benefits of both as much as possible. This was performed using the dare merging technique.
```yaml
# task-arithmetic style
models:
- model: EstopiaV9
parameters:
weight: 1
density: 1
- model: EstopiaV13
parameters:
weight: 0.05
density: 0.30
merge_method: dare_ties
base_model: TheBloke/Llama-2-13B-fp16
parameters:
int8_mask: true
dtype: bfloat16
```
# Model selection
- Undi95/UtopiaXL-13B
- Solid all around base for models, with the ability to write longer responses and generally good retension to detail.
- Doctor-Shotgun/cat-v1.0-13b
- A medical focused model which is added to focus a little more on the human responses, such as for psycology.
- PygmalionAI/mythalion-13b
- A roleplay and instruct focused model, which improves attentiveness to character card details and the variety of responses
- Undi95/Emerhyst-13B
- A roleplay but also longer form response model. It can be quite variable, but helps add to the depth and possible options the AI can respond with during narratives.
- CalderaAI/13B-Thorns-l2
- A neutral and very attentive model. It is good at chat and following instructions, which help benefit these modes.
- KoboldAI/LLaMA2-13B-Tiefighter
- A solid all around model, focusing on story writing and adventure modes. It provides all around benefits to creativity and the prose in models, along with adventure mode support.
- chargoddard/rpguild-chatml-13b
- A roleplay model, which introduces new data and also improves the detail retention in longer narratives.
# Notes
- With the differing models inside, this model will not have perfect end of sequence tokens which is a problem many merges can share. While attempts have been made to minimise this, you may occasionally get oddly behaving tokens - this should be possible to resolve with a quick manual edit once and the model should pick up on it.
- Chat is one of the least tested areas for this model. It works fairly well, but it can be quite character card dependant.
- This is a narrative and prose focused model. As a result, it can and will talk for you if guided to do so (such as asking it to act as a co-author or narrator) within instructions or other contexts. This can be mitigated mostly by adding instructions to limit this, or using chat mode instead.
# Future areas
- Llava
- Some success has been had with merging the llava lora on this. While no in depth testing has been performed, more narrative responses based on the images could be obtained - though there were drawbacks in the form of degraded performance in other areas, and hallucinations due to the fictional focus of this model.
- Stheno
- A merge which has similar promise from Sao. Some merge attempts have been made between the two and were promising, but not entirely consistent at the moment. With some possible refinement, this could produce an even stronger model.
- DynamicFactor
- All the merges used have been based on llama two in this merge, but a dare merge with dynamic factor (an attempted refinement of llama two) showed a beneficial improvement to the instruction abilities of the model, along with lengthy responses. It lost a little of the variety of responses, so perhaps if a balance of it could be added the instruction abilities and reasoning could be improved even further.
|
nsugianto/tblstructrecog_finetuned_tbltransstrucrecog_v2_s1_370s
|
nsugianto
| 2024-05-26T22:58:53Z | 375 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"table-transformer",
"object-detection",
"generated_from_trainer",
"base_model:nsugianto/tblstructrecog_finetuned_tbltransstrucrecog_v2_s1_370s",
"license:mit",
"endpoints_compatible",
"region:us"
] |
object-detection
| 2024-05-23T14:20:45Z |
---
license: mit
base_model: nsugianto/tblstructrecog_finetuned_tbltransstrucrecog_v2_s1_370s
tags:
- generated_from_trainer
model-index:
- name: tblstructrecog_finetuned_tbltransstrucrecog_v2_s1_370s
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# tblstructrecog_finetuned_tbltransstrucrecog_v2_s1_370s
This model is a fine-tuned version of [nsugianto/tblstructrecog_finetuned_tbltransstrucrecog_v2_s1_370s](https://huggingface.co/nsugianto/tblstructrecog_finetuned_tbltransstrucrecog_v2_s1_370s) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 750
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.0.1
- Datasets 2.18.0
- Tokenizers 0.19.1
|
mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF
|
mradermacher
| 2024-06-06T05:45:46Z | 375 | 0 |
transformers
|
[
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:sophosympatheia/Wizard-Tulu-Dolphin-70B-v1.0",
"endpoints_compatible",
"region:us"
] | null | 2024-06-05T10:04:18Z |
---
base_model: sophosympatheia/Wizard-Tulu-Dolphin-70B-v1.0
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/sophosympatheia/Wizard-Tulu-Dolphin-70B-v1.0
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q2_K.gguf) | Q2_K | 25.6 | |
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.IQ3_XS.gguf) | IQ3_XS | 28.4 | |
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.IQ3_S.gguf) | IQ3_S | 30.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q3_K_S.gguf) | Q3_K_S | 30.0 | |
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.IQ3_M.gguf) | IQ3_M | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.IQ4_XS.gguf) | IQ4_XS | 37.3 | |
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
| [GGUF](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q5_K_M.gguf) | Q5_K_M | 48.9 | |
| [PART 1](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Wizard-Tulu-Dolphin-70B-v1.0-GGUF/resolve/main/Wizard-Tulu-Dolphin-70B-v1.0.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
gaianet/Qwen2-7B-Instruct-GGUF
|
gaianet
| 2024-06-07T03:41:12Z | 375 | 0 |
transformers
|
[
"transformers",
"gguf",
"qwen2",
"text-generation",
"chat",
"en",
"base_model:Qwen/Qwen2-7B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2024-06-07T02:45:57Z |
---
base_model: Qwen/Qwen2-7B-Instruct
license: apache-2.0
model_creator: Qwen
model_name: Qwen2-7B-Instruct
quantized_by: Second State Inc.
language:
- en
pipeline_tag: text-generation
tags:
- chat
---
# Qwen2-7B-Instruct-GGUF
## Original Model
[Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct)
## Run with Gaianet
**Prompt template**
prompt template: `chatml`
**Context size**
chat_ctx_size: `131072`
**Run with GaiaNet**
- Quick start: https://docs.gaianet.ai/node-guide/quick-start
- Customize your node: https://docs.gaianet.ai/node-guide/customize
|
mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF
|
mradermacher
| 2024-06-17T11:29:41Z | 375 | 1 |
transformers
|
[
"transformers",
"gguf",
"llama-factory",
"en",
"base_model:hf-100/Llama-3-Spellbound-Instruct-70B-0.1",
"endpoints_compatible",
"region:us"
] | null | 2024-06-17T07:20:01Z |
---
base_model: hf-100/Llama-3-Spellbound-Instruct-70B-0.1
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- llama-factory
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/hf-100/Llama-3-Spellbound-Instruct-70B-0.1
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q2_K.gguf) | Q2_K | 26.5 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.IQ3_XS.gguf) | IQ3_XS | 29.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.IQ3_M.gguf) | IQ3_M | 32.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.IQ4_XS.gguf) | IQ4_XS | 38.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
| [PART 1](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Spellbound-Instruct-70B-0.1-GGUF/resolve/main/Llama-3-Spellbound-Instruct-70B-0.1.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
CHE-72/Breeze-7B-Instruct-v1_0-Q4_K_S-GGUF
|
CHE-72
| 2024-06-22T18:08:31Z | 375 | 0 | null |
[
"gguf",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"zh",
"en",
"base_model:MediaTek-Research/Breeze-7B-Instruct-v1_0",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2024-06-22T18:08:09Z |
---
base_model: MediaTek-Research/Breeze-7B-Instruct-v1_0
language:
- zh
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- llama-cpp
- gguf-my-repo
---
# CHE-72/Breeze-7B-Instruct-v1_0-Q4_K_S-GGUF
This model was converted to GGUF format from [`MediaTek-Research/Breeze-7B-Instruct-v1_0`](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo CHE-72/Breeze-7B-Instruct-v1_0-Q4_K_S-GGUF --hf-file breeze-7b-instruct-v1_0-q4_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo CHE-72/Breeze-7B-Instruct-v1_0-Q4_K_S-GGUF --hf-file breeze-7b-instruct-v1_0-q4_k_s.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo CHE-72/Breeze-7B-Instruct-v1_0-Q4_K_S-GGUF --hf-file breeze-7b-instruct-v1_0-q4_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo CHE-72/Breeze-7B-Instruct-v1_0-Q4_K_S-GGUF --hf-file breeze-7b-instruct-v1_0-q4_k_s.gguf -c 2048
```
|
rajkumaralma/Voxel_XL_Lora
|
rajkumaralma
| 2024-06-26T08:28:50Z | 375 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:mit",
"region:us"
] |
text-to-image
| 2024-06-26T08:28:22Z |
---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: voxel style
output:
url: images/nD-or57fKyKY-HdYsDAC0.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: voxel style
license: mit
---
# Voxel_XL_Lora
<Gallery />
## Model description
lego
## Trigger words
You should use `voxel style` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/rajkumaralma/Voxel_XL_Lora/tree/main) them in the Files & versions tab.
|
faizalnf1800/AingDiffusion-V8-FP16-SD1.5
|
faizalnf1800
| 2024-06-27T00:30:03Z | 375 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2024-06-27T00:25:45Z |
---
library_name: diffusers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
aychang/roberta-base-imdb
|
aychang
| 2021-05-20T14:25:56Z | 374 | 5 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"roberta",
"text-classification",
"en",
"dataset:imdb",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2022-03-02T23:29:05Z |
---
language:
- en
thumbnail:
tags:
- text-classification
license: mit
datasets:
- imdb
metrics:
---
# IMDB Sentiment Task: roberta-base
## Model description
A simple base roBERTa model trained on the "imdb" dataset.
## Intended uses & limitations
#### How to use
##### Transformers
```python
# Load model and tokenizer
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Use pipeline
from transformers import pipeline
model_name = "aychang/roberta-base-imdb"
nlp = pipeline("sentiment-analysis", model=model_name, tokenizer=model_name)
results = nlp(["I didn't really like it because it was so terrible.", "I love how easy it is to watch and get good results."])
```
##### AdaptNLP
```python
from adaptnlp import EasySequenceClassifier
model_name = "aychang/roberta-base-imdb"
texts = ["I didn't really like it because it was so terrible.", "I love how easy it is to watch and get good results."]
classifer = EasySequenceClassifier
results = classifier.tag_text(text=texts, model_name_or_path=model_name, mini_batch_size=2)
```
#### Limitations and bias
This is minimal language model trained on a benchmark dataset.
## Training data
IMDB https://huggingface.co/datasets/imdb
## Training procedure
#### Hardware
One V100
#### Hyperparameters and Training Args
```python
from transformers import TrainingArguments
training_args = TrainingArguments(
output_dir='./models',
overwrite_output_dir=False,
num_train_epochs=2,
per_device_train_batch_size=8,
per_device_eval_batch_size=8,
warmup_steps=500,
weight_decay=0.01,
evaluation_strategy="steps",
logging_dir='./logs',
fp16=False,
eval_steps=800,
save_steps=300000
)
```
## Eval results
```
{'epoch': 2.0,
'eval_accuracy': 0.94668,
'eval_f1': array([0.94603457, 0.94731017]),
'eval_loss': 0.2578844428062439,
'eval_precision': array([0.95762642, 0.93624502]),
'eval_recall': array([0.93472, 0.95864]),
'eval_runtime': 244.7522,
'eval_samples_per_second': 102.144}
```
|
bhadresh-savani/albert-base-v2-emotion
|
bhadresh-savani
| 2021-09-15T18:03:36Z | 374 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"albert",
"text-classification",
"emotion",
"en",
"dataset:emotion",
"arxiv:1909.11942",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2022-03-02T23:29:05Z |
---
language:
- en
thumbnail: https://avatars3.githubusercontent.com/u/32437151?s=460&u=4ec59abc8d21d5feea3dab323d23a5860e6996a4&v=4
tags:
- text-classification
- emotion
- pytorch
license: apache-2.0
datasets:
- emotion
metrics:
- Accuracy, F1 Score
---
# Albert-base-v2-emotion
## Model description:
[Albert](https://arxiv.org/pdf/1909.11942v6.pdf) is A Lite BERT architecture that has significantly fewer parameters than a traditional BERT architecture.
[Albert-base-v2](https://huggingface.co/albert-base-v2) finetuned on the emotion dataset using HuggingFace Trainer with below Hyperparameters
```
learning rate 2e-5,
batch size 64,
num_train_epochs=8,
```
## Model Performance Comparision on Emotion Dataset from Twitter:
| Model | Accuracy | F1 Score | Test Sample per Second |
| --- | --- | --- | --- |
| [Distilbert-base-uncased-emotion](https://huggingface.co/bhadresh-savani/distilbert-base-uncased-emotion) | 93.8 | 93.79 | 398.69 |
| [Bert-base-uncased-emotion](https://huggingface.co/bhadresh-savani/bert-base-uncased-emotion) | 94.05 | 94.06 | 190.152 |
| [Roberta-base-emotion](https://huggingface.co/bhadresh-savani/roberta-base-emotion) | 93.95 | 93.97| 195.639 |
| [Albert-base-v2-emotion](https://huggingface.co/bhadresh-savani/albert-base-v2-emotion) | 93.6 | 93.65 | 182.794 |
## How to Use the model:
```python
from transformers import pipeline
classifier = pipeline("text-classification",model='bhadresh-savani/albert-base-v2-emotion', return_all_scores=True)
prediction = classifier("I love using transformers. The best part is wide range of support and its easy to use", )
print(prediction)
"""
Output:
[[
{'label': 'sadness', 'score': 0.010403595864772797},
{'label': 'joy', 'score': 0.8902180790901184},
{'label': 'love', 'score': 0.042532723397016525},
{'label': 'anger', 'score': 0.041297927498817444},
{'label': 'fear', 'score': 0.011772023513913155},
{'label': 'surprise', 'score': 0.0037756056990474463}
]]
"""
```
## Dataset:
[Twitter-Sentiment-Analysis](https://huggingface.co/nlp/viewer/?dataset=emotion).
## Training procedure
[Colab Notebook](https://github.com/bhadreshpsavani/ExploringSentimentalAnalysis/blob/main/SentimentalAnalysisWithDistilbert.ipynb)
## Eval results
```json
{
'test_accuracy': 0.936,
'test_f1': 0.9365658988006296,
'test_loss': 0.15278364717960358,
'test_runtime': 10.9413,
'test_samples_per_second': 182.794,
'test_steps_per_second': 2.925
}
```
## Reference:
* [Natural Language Processing with Transformer By Lewis Tunstall, Leandro von Werra, Thomas Wolf](https://learning.oreilly.com/library/view/natural-language-processing/9781098103231/)
|
bipin/image-caption-generator
|
bipin
| 2023-07-05T08:26:49Z | 374 | 15 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"vision-encoder-decoder",
"image-captioning",
"image-to-text",
"endpoints_compatible",
"region:us"
] |
image-to-text
| 2022-03-27T09:56:24Z |
---
tags:
- image-captioning
- image-to-text
model-index:
- name: image-caption-generator
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Image-caption-generator
This model is trained on [Flickr8k](https://www.kaggle.com/datasets/nunenuh/flickr8k) dataset to generate captions given an image.
It achieves the following results on the evaluation set:
- eval_loss: 0.2536
- eval_runtime: 25.369
- eval_samples_per_second: 63.818
- eval_steps_per_second: 8.002
- epoch: 4.0
- step: 3236
# Running the model using transformers library
1. Load the pre-trained model from the model hub
```python
from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
import torch
from PIL import Image
model_name = "bipin/image-caption-generator"
# load model
model = VisionEncoderDecoderModel.from_pretrained(model_name)
feature_extractor = ViTFeatureExtractor.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained("gpt2")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
```
2. Load the image for which the caption is to be generated
```python
img_name = "flickr_data.jpg"
img = Image.open(img_name)
if img.mode != 'RGB':
img = img.convert(mode="RGB")
```
3. Pre-process the image
```python
pixel_values = feature_extractor(images=[img], return_tensors="pt").pixel_values
pixel_values = pixel_values.to(device)
```
4. Generate the caption
```python
max_length = 128
num_beams = 4
# get model prediction
output_ids = model.generate(pixel_values, num_beams=num_beams, max_length=max_length)
# decode the generated prediction
preds = tokenizer.decode(output_ids[0], skip_special_tokens=True)
print(preds)
```
## Training procedure
The procedure used to train this model can be found [here](https://bipinkrishnan.github.io/ml-recipe-book/image_captioning.html).
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Framework versions
- Transformers 4.16.2
- Pytorch 1.9.1
- Datasets 1.18.4
- Tokenizers 0.11.6
|
timm/vit_relpos_base_patch32_plus_rpn_256.sw_in1k
|
timm
| 2023-05-05T22:04:19Z | 374 | 0 |
timm
|
[
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2111.09883",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
] |
image-classification
| 2022-12-23T00:20:21Z |
---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for vit_relpos_base_patch32_plus_rpn_256.sw_in1k
A Vision Transformer (ViT) image classification model. This is a `timm` specific variation of the ViT architecture with relative position embeddings and residual post normalization blocks, no class token, and final representation via global average pool of tokens. Trained on ImageNet-1k in `timm` using recipe template described below.
Recipe details:
* Based on Swin Transformer train / pretrain recipe with modifications (related to both DeiT and ConvNeXt recipes)
* AdamW optimizer, gradient clipping, EMA weight averaging
* Cosine LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 119.4
- GMACs: 7.6
- Activations (M): 6.6
- Image size: 256 x 256
- **Papers:**
- Swin Transformer V2: Scaling Up Capacity and Resolution: https://arxiv.org/abs/2111.09883
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_relpos_base_patch32_plus_rpn_256.sw_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_relpos_base_patch32_plus_rpn_256.sw_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 64, 896) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@inproceedings{liu2021swinv2,
title={Swin Transformer V2: Scaling Up Capacity and Resolution},
author={Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
booktitle={International Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2022}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
|
surferfelix/ner-bertje-tagdetekst
|
surferfelix
| 2023-01-25T13:02:17Z | 374 | 1 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"token-classification",
"history",
"dutch",
"ner",
"bertje",
"nl",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-01-23T15:56:59Z |
---
license: apache-2.0
language:
- nl
tags:
- history
- dutch
- ner
- bertje
---
This is a Dutch NER model finetuned on historical data from https://taalmaterialen.ivdnt.org/download/aitrainingset1-0/
|
timm/dpn68b.ra_in1k
|
timm
| 2023-04-21T21:57:11Z | 374 | 0 |
timm
|
[
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2110.00476",
"arxiv:1707.01629",
"license:apache-2.0",
"region:us"
] |
image-classification
| 2023-04-21T21:56:57Z |
---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for dpn68b.ra_in1k
A DPN (Dual-Path Net) classification model. Pretrained on ImageNet-1k in `timm` by Ross Wightman using RandAugment `RA` recipe. Related to `B` recipe in [ResNet Strikes Back](https://arxiv.org/abs/2110.00476).
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 12.6
- GMACs: 2.4
- Activations (M): 10.5
- Image size: train = 224 x 224, test = 288 x 288
- **Papers:**
- Dual Path Networks: https://arxiv.org/abs/1707.01629
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('dpn68b.ra_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'dpn68b.ra_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 10, 112, 112])
# torch.Size([1, 144, 56, 56])
# torch.Size([1, 320, 28, 28])
# torch.Size([1, 704, 14, 14])
# torch.Size([1, 832, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'dpn68b.ra_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 832, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Citation
```bibtex
@article{Chen2017,
title={Dual Path Networks},
author={Yunpeng Chen, Jianan Li, Huaxin Xiao, Xiaojie Jin, Shuicheng Yan, Jiashi Feng},
journal={arXiv preprint arXiv:1707.01629},
year={2017}
}
```
```bibtex
@inproceedings{wightman2021resnet,
title={ResNet strikes back: An improved training procedure in timm},
author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}
```
|
lorahub/flan_t5_large-glue_sst2
|
lorahub
| 2023-07-24T09:54:15Z | 374 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-24T09:54:05Z |
---
library_name: peft
---
|
afrideva/phi-2_LogiCoT_finetuned-GGUF
|
afrideva
| 2023-12-22T20:45:16Z | 374 | 0 | null |
[
"gguf",
"ggml",
"quantized",
"q2_k",
"q3_k_m",
"q4_k_m",
"q5_k_m",
"q6_k",
"q8_0",
"text-generation",
"base_model:KathirKs/phi-2_LogiCoT_finetuned",
"region:us"
] |
text-generation
| 2023-12-22T20:36:10Z |
---
base_model: KathirKs/phi-2_LogiCoT_finetuned
inference: false
model_creator: KathirKs
model_name: phi-2_LogiCoT_finetuned
pipeline_tag: text-generation
quantized_by: afrideva
tags:
- gguf
- ggml
- quantized
- q2_k
- q3_k_m
- q4_k_m
- q5_k_m
- q6_k
- q8_0
---
# KathirKs/phi-2_LogiCoT_finetuned-GGUF
Quantized GGUF model files for [phi-2_LogiCoT_finetuned](https://huggingface.co/KathirKs/phi-2_LogiCoT_finetuned) from [KathirKs](https://huggingface.co/KathirKs)
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [phi-2_logicot_finetuned.fp16.gguf](https://huggingface.co/afrideva/phi-2_LogiCoT_finetuned-GGUF/resolve/main/phi-2_logicot_finetuned.fp16.gguf) | fp16 | 5.56 GB |
| [phi-2_logicot_finetuned.q2_k.gguf](https://huggingface.co/afrideva/phi-2_LogiCoT_finetuned-GGUF/resolve/main/phi-2_logicot_finetuned.q2_k.gguf) | q2_k | 1.17 GB |
| [phi-2_logicot_finetuned.q3_k_m.gguf](https://huggingface.co/afrideva/phi-2_LogiCoT_finetuned-GGUF/resolve/main/phi-2_logicot_finetuned.q3_k_m.gguf) | q3_k_m | 1.48 GB |
| [phi-2_logicot_finetuned.q4_k_m.gguf](https://huggingface.co/afrideva/phi-2_LogiCoT_finetuned-GGUF/resolve/main/phi-2_logicot_finetuned.q4_k_m.gguf) | q4_k_m | 1.79 GB |
| [phi-2_logicot_finetuned.q5_k_m.gguf](https://huggingface.co/afrideva/phi-2_LogiCoT_finetuned-GGUF/resolve/main/phi-2_logicot_finetuned.q5_k_m.gguf) | q5_k_m | 2.07 GB |
| [phi-2_logicot_finetuned.q6_k.gguf](https://huggingface.co/afrideva/phi-2_LogiCoT_finetuned-GGUF/resolve/main/phi-2_logicot_finetuned.q6_k.gguf) | q6_k | 2.29 GB |
| [phi-2_logicot_finetuned.q8_0.gguf](https://huggingface.co/afrideva/phi-2_LogiCoT_finetuned-GGUF/resolve/main/phi-2_logicot_finetuned.q8_0.gguf) | q8_0 | 2.96 GB |
## Original Model Card:
I am not the owner of this model's license. Please refer to the original model card for licensing information: [https://huggingface.co/microsoft/phi-2/blob/main/LICENSE]
This model belongs to Microsoft Research.
This is finetuned using just 500 samples LogiCoT (Chain of Thought) prompting dataset.
|
ViraIntelligentDataMining/AriaBERT
|
ViraIntelligentDataMining
| 2024-05-18T23:52:38Z | 374 | 5 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"bert",
"persian",
"fa",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-12-27T18:33:39Z |
---
license: apache-2.0
language:
- fa
tags:
- bert
- roberta
- persian
---
# AriaBERT: A Pre-trained Persian BERT Model for Natural Language Understanding
## Introduction
AriaBERT represents a breakthrough in natural language processing (NLP) for the Persian language. Developed to address the critical gap in efficient pretrained language models for Persian, AriaBERT is tailored to elevate the standards of Persian language tasks.
## Paper: https://www.researchsquare.com/article/rs-3558473/v1
## Key Features
- **Diverse Training Data:** AriaBERT has been trained on over 32 gigabytes of varied Persian textual data, spanning conversational, formal, and hybrid texts. This includes a rich mix of tweets, news articles, poems, medical and encyclopedia texts, user opinions, and more.
- **RoBERTa Architecture:** Leveraging the robustness of the RoBERTa architecture and the precision of Byte-Pair Encoding tokenizer, AriaBERT stands apart from traditional BERT-based models.
- **Broad Applicability:** Ideal for a range of NLP tasks including classification, sentiment analysis, and stance detection, particularly in the Persian language context.
## Performance Benchmarks
- **Sentiment Analysis:** Achieves an average improvement of 3% over competing models.
- **Classification Tasks:** Demonstrates a 0.65% improvement in accuracy.
- **Stance Detection:** Shows a 3% enhancement in performance metrics.
|
Mozilla/TinyLlama-1.1B-Chat-v1.0-llamafile
|
Mozilla
| 2024-07-01T19:26:02Z | 374 | 9 | null |
[
"llamafile",
"GGUF",
"en",
"dataset:cerebras/SlimPajama-627B",
"dataset:bigcode/starcoderdata",
"dataset:OpenAssistant/oasst_top1_2023-08-25",
"license:apache-2.0",
"region:us"
] | null | 2024-01-01T11:29:06Z |
---
license: apache-2.0
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
- OpenAssistant/oasst_top1_2023-08-25
language:
- en
tags:
- GGUF
- llamafile
model_creator: TinyLlama
model_name: TinyLlama-1.1B-Chat v1.0
model_type: Pythia
quantized_by: jartine
---
# TinyLlama-1.1B-Chat v1.0 w/ GGUF + llamafile
- Model creator: [TinyLlama](https://huggingface.co/TinyLlama)
- Original model: [TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
<!-- description start -->
## Description
This repo contains both:
- Prebuilt llamafiles for each quantization format that can be executed to launch a web server or cli interface
- GGUF weights data files for each quantization format, which require either the [llamafile](https://github.com/mozilla-Ocho/llamafile) or [llama.cpp](https://github.com/ggerganov/llama.cpp) software to run
## Prompt Template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
---
# TinyLlama-1.1B
</div>
https://github.com/jzhang38/TinyLlama
The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.
We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
#### This Model
This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T). **We follow [HF's Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/edit/main/README.md)'s training recipe.** The model was " initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.
We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4."
#### How to use
You will need the transformers>=4.34
Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
```python
# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto")
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
{
"role": "system",
"content": "You are a friendly chatbot who always responds in the style of a pirate",
},
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
# <|system|>
# You are a friendly chatbot who always responds in the style of a pirate.</s>
# <|user|>
# How many helicopters can a human eat in one sitting?</s>
# <|assistant|>
# ...
```
|
second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF
|
second-state
| 2024-03-20T07:21:25Z | 374 | 0 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation",
"ja",
"en",
"base_model:elyza/ELYZA-japanese-Llama-2-13b-fast-instruct",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2024-01-06T03:33:53Z |
---
base_model: elyza/ELYZA-japanese-Llama-2-13b-fast-instruct
inference: false
library_name: transformers
license: llama2
model_creator: elyza
model_name: ELYZA-japanese-Llama-2-13b-fast-instruct
pipeline_tag: text-generation
quantized_by: Second State Inc.
language:
- ja
- en
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF
## Original Model
[elyza/ELYZA-japanese-Llama-2-13b-fast-instruct](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b-fast-instruct)
## Run with LlamaEdge
- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above
- Prompt template
- Prompt type: `llama-2-chat`
- Prompt string
```text
<s>[INST] <<SYS>>
{{ system_prompt }}
<</SYS>>
{{ user_msg_1 }} [/INST] {{ model_answer_1 }} </s><s>[INST] {{ user_msg_2 }}
```
- Context size: `5120`
- Run as LlamaEdge service
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_M.gguf llama-api-server.wasm -p llama-2-chat
```
- Run as LlamaEdge command app
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_M.gguf llama-chat.wasm -p llama-2-chat
```
## Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q2_K.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q2_K.gguf) | Q2_K | 2 | 5.5 GB| smallest, significant quality loss - not recommended for most purposes |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_L.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 7.01 GB| small, substantial quality loss |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_M.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 6.42 GB| very small, high quality loss |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_S.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 5.74 GB| very small, high quality loss |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_0.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_0.gguf) | Q4_0 | 4 | 7.46 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_M.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 7.96 GB| medium, balanced quality - recommended |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_S.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 7.5 GB| small, greater quality loss |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_0.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_0.gguf) | Q5_0 | 5 | 9.07 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_M.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 9.33 GB| large, very low quality loss - recommended |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_S.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 9.07 GB| large, low quality loss - recommended |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q6_K.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q6_K.gguf) | Q6_K | 6 | 10.8 GB| very large, extremely low quality loss |
| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q8_0.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q8_0.gguf) | Q8_0 | 8 | 14 GB| very large, extremely low quality loss - not recommended |
|
dreamgen/opus-v1-34b-gguf
|
dreamgen
| 2024-03-13T19:34:13Z | 374 | 5 | null |
[
"gguf",
"unsloth",
"axolotl",
"text-generation",
"en",
"region:us"
] |
text-generation
| 2024-02-21T14:01:40Z |
---
language:
- en
pipeline_tag: text-generation
tags:
- unsloth
- axolotl
---
# DreamGen Opus V1
**DreamGen Opus V1** is a family of **uncensored** models fine-tuned for **(steerable) story-writing and role-playing**.
*WARNING:* GGUF versions might not perform as well as FP16 or AWQ.
See the full model [dreamgen/opus-v1-34b](https://huggingface.co/dreamgen/opus-v1-34b) for documentation.
[See other Opus V1 variants](https://huggingface.co/collections/dreamgen/opus-v1-65d092a6f8ab7fc669111b31).
Best consumed at Q4_K_M or above.
|
mitkox/gemma-2b-dpo-uncensored-4bit
|
mitkox
| 2024-02-22T09:24:30Z | 374 | 5 |
transformers
|
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"generated_from_trainer",
"axolotl",
"instruct",
"finetune",
"chatml",
"gpt4",
"synthetic data",
"distillation",
"mlx",
"conversational",
"en",
"dataset:mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha",
"base_model:google/gemma-2b-it",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2024-02-22T09:16:16Z |
---
language:
- en
license: cc-by-nc-4.0
library_name: transformers
tags:
- generated_from_trainer
- axolotl
- gemma
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- distillation
- mlx
datasets:
- mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha
base_model: google/gemma-2b-it
pipeline_tag: text-generation
model-index:
- name: gemma-2b-openhermes
results: []
---
# mitkox/gemma-2b-dpo-uncensored-4bit
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mitkox/gemma-2b-dpo-uncensored-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
mradermacher/luxia-21.4b-alignment-v1.1-GGUF
|
mradermacher
| 2024-05-06T06:02:29Z | 374 | 2 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:saltlux/luxia-21.4b-alignment-v1.1",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-03-23T19:56:32Z |
---
base_model: saltlux/luxia-21.4b-alignment-v1.1
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
static quants of https://huggingface.co/saltlux/luxia-21.4b-alignment-v1.1
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.Q2_K.gguf) | Q2_K | 8.9 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.IQ3_XS.gguf) | IQ3_XS | 9.7 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.Q3_K_S.gguf) | Q3_K_S | 10.2 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.IQ3_S.gguf) | IQ3_S | 10.2 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.IQ3_M.gguf) | IQ3_M | 10.6 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.Q3_K_M.gguf) | Q3_K_M | 11.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.Q3_K_L.gguf) | Q3_K_L | 12.1 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.IQ4_XS.gguf) | IQ4_XS | 12.5 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.Q4_K_S.gguf) | Q4_K_S | 13.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.Q4_K_M.gguf) | Q4_K_M | 13.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.Q5_K_S.gguf) | Q5_K_S | 15.6 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.Q5_K_M.gguf) | Q5_K_M | 15.9 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.Q6_K.gguf) | Q6_K | 18.3 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.1-GGUF/resolve/main/luxia-21.4b-alignment-v1.1.Q8_0.gguf) | Q8_0 | 23.4 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
lmstudio-community/Starling-LM-7B-beta-GGUF
|
lmstudio-community
| 2024-04-05T01:55:30Z | 374 | 5 |
transformers
|
[
"transformers",
"gguf",
"reward model",
"RLHF",
"RLAIF",
"text-generation",
"en",
"dataset:berkeley-nest/Nectar",
"arxiv:1909.08593",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-04-02T16:49:17Z |
---
license: apache-2.0
datasets:
- berkeley-nest/Nectar
language:
- en
library_name: transformers
tags:
- reward model
- RLHF
- RLAIF
quantized_by: bartowski
pipeline_tag: text-generation
lm_studio:
param_count: 7b
use_case: general
release_date: 19-03-2024
model_creator: Nexusflow
prompt_template: OpenChat
system_prompt: none
base_model: mistral
original_repo: Nexusflow/Starling-LM-7B-beta
---
## 💫 Community Model> Starling-LM-7B-beta by Nexusflow
*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.
**Model creator:** [Nexusflow](https://huggingface.co/Nexusflow)<br>
**Original model**: [Starling-LM-7B-beta](https://huggingface.co/Nexusflow/Starling-LM-7B-beta)<br>
**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b2440](https://github.com/ggerganov/llama.cpp/releases/tag/b2440)<br>
## Model Summary:
Starling-LM-7B-beta is an iteration on the Starling series of models, building on the work from [berkeley-nest](https://huggingface.co/berkeley-nest) who released [Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha).<br>
This model is finetuned from [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) based on [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).<br>
Using [Nexusflow/Starling-RM-34B](https://huggingface.co/Nexusflow/Starling-RM-34B) as the reward model and a policy optimization method of [Fine-Tuning Language Models from Human Preferences (PPO)](https://arxiv.org/abs/1909.08593) to yield impressive results for such a small model.
## Prompt Template:
Choose the 'OpenChat' preset in your LM Studio.
Under the hood, the model will see a prompt that's formatted like so:
```
GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:
```
You can also choose the 'OpenChatCode' for a coding assistant.
Under the hood, the model will see a prompt that's formatted like so:
```
Code User: {prompt}<|end_of_turn|>Code Assistant:
```
Note that this model does not support a System prompt.
## Use case and examples
Starling-LM-7B-beta is tuned to achieve impressive multi-turn chat performance. The base model was designed for being a generalist and coding tuned model, so it will work well for general tasks as well as coding.
### General knowledge:
>GPT4 Correct User: Why is the sky blue?<|end_of_turn|>
>GPT4 Correct Assistant: The sky appears blue due to a phenomenon called Rayleigh scattering, named after British scientist Lord Rayleigh who first studied it in detail. Here's a simplified explanation of why this occurs:
>
>1. Sunlight is composed of various colors of light, each with different wavelengths. These colors include red, orange, yellow, green, blue, indigo, and violet, which together form the visible spectrum.
>
>2. When sunlight enters Earth's atmosphere, it interacts with molecules of air (mainly nitrogen and oxygen) and small particles like dust and water droplets. These interactions cause the different colors of light to scatter in various directions.
>
>3. Rayleigh scattering is more effective at shorter wavelengths, meaning that blue and violet light are scattered more than red and yellow light. However, our eyes are more sensitive to blue light than violet, so we perceive the sky as blue rather than a mixture of blue and violet.
>
>4. At sunrise and sunset, the sun is lower in the sky, and its light has to travel through more atmosphere. This causes even more scattering of shorter wavelengths (blue and violet), leaving longer wavelengths (red, orange, and yellow) to dominate, resulting in the warm colors we see during these times.
>
>5. In some cases, such as after a rainstorm or in areas with high pollution levels, the sky may appear more grayish or hazy. This is because the scattering of light is less selective, and more of the shorter wavelengths (blue) are scattered out of our line of sight, along with the longer wavelengths (red).
>
>In summary, the sky appears blue due to the selective scattering of sunlight by the atmosphere, with shorter wavelengths (blue) being scattered more than longer wavelengths (red), and our eyes being more sensitive to blue light.
### Coding:
>Code User: Implement quicksort using C++<|end_of_turn|>
>Code Assistant: Here is an example of how to implement the quicksort algorithm in C++:
>
>```cpp
>#include <iostream>
>#include <vector>
>
>using namespace std;
>
>void swap(int* a, int* b) {
> int t = *a;
> *a = *b;
> *b = t;
>}
>
>int partition(vector<int>& arr, int low, int high) {
> int pivot = arr[high];
> int i = (low - 1);
>
> for (int j = low; j <= high - 1; j++) {
> if (arr[j] < pivot) {
> i++;
> swap(&arr[i], &arr[j]);
> }
> }
> swap(&arr[i + 1], &arr[high]);
> return (i + 1);
>}
>
>void quickSort(vector<int>& arr, int low, int high) {
> if (low < high) {
> int pi = partition(arr, low, high);
>
> quickSort(arr, low, pi - 1);
> quickSort(arr, pi + 1, high);
> }
>}
>
>int main() {
> vector<int> arr = {10, 7, 8, 9, 1, 5};
> int n = arr.size();
>
> quickSort(arr, 0, n - 1);
>
> cout << "Sorted array: \n";
> for (int i = 0; i < n; i++) {
> cout << arr[i] << " ";
> }
> cout << endl;
>
> return 0;
>}
>```
>
>This code defines a `quickSort` function that takes a vector of integers, a starting index (low), and an ending index (high) as parameters. The function uses the partition method to find the pivot element's correct position in the sorted array and then recursively sorts the sub-arrays before and after the pivot.
>
>The `main` function demonstrates how to use the `quickSort` function by sorting an example vector of integers and printing the sorted result.
## Technical Details
Uses [Nexusflow/Starling-RM-34B](https://huggingface.co/Nexusflow/Starling-RM-34B) as a reward model for PPO.
Nexusflow/Starling-RM-34B was trained on the following dataset:
- [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar)
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
## Disclaimers
LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.
|
Monor/Unichat-llama3-Chinese-8B-28K-gguf
|
Monor
| 2024-05-05T05:19:46Z | 374 | 1 | null |
[
"gguf",
"license:apache-2.0",
"region:us"
] | null | 2024-05-01T14:41:18Z |
---
license: apache-2.0
---
## Introduce
Quantizing the [UnicomLLM/Unichat-llama3-Chinese-8B-28K](https://huggingface.co/UnicomLLM/Unichat-llama3-Chinese-8B-28K) to f16, q2, q3, q4, q5, q6 and q8 with Llama.cpp.
|
mradermacher/Cognitron-8B-GGUF
|
mradermacher
| 2024-05-11T18:52:51Z | 374 | 0 |
transformers
|
[
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"en",
"base_model:bunnycore/Cognitron-8B",
"license:llama3",
"endpoints_compatible",
"region:us"
] | null | 2024-05-04T00:47:01Z |
---
base_model: bunnycore/Cognitron-8B
language:
- en
library_name: transformers
license: llama3
quantized_by: mradermacher
tags:
- merge
- mergekit
- lazymergekit
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/bunnycore/Cognitron-8B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Cognitron-8B-GGUF/resolve/main/Cognitron-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF
|
mradermacher
| 2024-05-07T13:25:39Z | 374 | 3 |
transformers
|
[
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"sft",
"en",
"base_model:rombodawg/Llama-3-8B-Instruct-Coder-v2",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-07T12:57:07Z |
---
base_model: rombodawg/Llama-3-8B-Instruct-Coder-v2
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder-v2
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
MaziyarPanahi/T3qm7xpMultiverseex26-7B-GGUF
|
MaziyarPanahi
| 2024-05-21T14:25:19Z | 374 | 0 |
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"automerger",
"base_model:allknowingroger/MultiverseEx26-7B-slerp",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:automerger/T3qm7xpMultiverseex26-7B"
] |
text-generation
| 2024-05-21T13:55:05Z |
---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- merge
- mergekit
- lazymergekit
- automerger
- base_model:allknowingroger/MultiverseEx26-7B-slerp
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
- text-generation
model_name: T3qm7xpMultiverseex26-7B-GGUF
base_model: automerger/T3qm7xpMultiverseex26-7B
inference: false
model_creator: automerger
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/T3qm7xpMultiverseex26-7B-GGUF](https://huggingface.co/MaziyarPanahi/T3qm7xpMultiverseex26-7B-GGUF)
- Model creator: [automerger](https://huggingface.co/automerger)
- Original model: [automerger/T3qm7xpMultiverseex26-7B](https://huggingface.co/automerger/T3qm7xpMultiverseex26-7B)
## Description
[MaziyarPanahi/T3qm7xpMultiverseex26-7B-GGUF](https://huggingface.co/MaziyarPanahi/T3qm7xpMultiverseex26-7B-GGUF) contains GGUF format model files for [automerger/T3qm7xpMultiverseex26-7B](https://huggingface.co/automerger/T3qm7xpMultiverseex26-7B).
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
|
mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF
|
mradermacher
| 2024-05-25T06:17:23Z | 374 | 1 |
transformers
|
[
"transformers",
"gguf",
"not-for-all-audiences",
"merge",
"mergekit",
"en",
"base_model:PJMixers/LLaMa-3-CursedStock-v1.6-8B",
"license:llama3",
"endpoints_compatible",
"region:us"
] | null | 2024-05-25T04:04:26Z |
---
base_model: PJMixers/LLaMa-3-CursedStock-v1.6-8B
language:
- en
library_name: transformers
license: llama3
quantized_by: mradermacher
tags:
- not-for-all-audiences
- merge
- mergekit
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/PJMixers/LLaMa-3-CursedStock-v1.6-8B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/LLaMa-3-CursedStock-v1.6-8B-GGUF/resolve/main/LLaMa-3-CursedStock-v1.6-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
LiteLLMs/Meta-Llama-Guard-2-8B-GGUF
|
LiteLLMs
| 2024-05-29T16:08:14Z | 374 | 0 | null |
[
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"GGUF",
"text-generation",
"en",
"arxiv:2312.06674",
"arxiv:2403.13031",
"license:llama3",
"region:us"
] |
text-generation
| 2024-05-29T15:57:42Z |
---
language:
- en
license: llama3
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- GGUF
pipeline_tag: text-generation
extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\
\ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\
\ use, reproduction, distribution and modification of the Llama Materials set forth\
\ herein.\n\"Documentation\" means the specifications, manuals and documentation\
\ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\
\"Licensee\" or \"you\" means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf), of\
\ the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\
\ 3\" means the foundational large language models and software and algorithms,\
\ including machine-learning model code, trained model weights, inference-enabling\
\ code, training-enabling code, fine-tuning enabling code and other elements of\
\ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\
\"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\
\ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\
we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\
\ an entity, your principal place of business is in the EEA or Switzerland) and\
\ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\
\ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\
\ a non-exclusive, worldwide, non-transferable and royalty-free limited license\
\ under Meta’s intellectual property or other rights owned by Meta embodied in the\
\ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\
\ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\
\ If you distribute or make available the Llama Materials (or any derivative works\
\ thereof), or a product or service that uses any of them, including another AI\
\ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\
\ and (B) prominently display “Built with Meta Llama 3” on a related website, user\
\ interface, blogpost, about page, or product documentation. If you use the Llama\
\ Materials to create, train, fine tune, or otherwise improve an AI model, which\
\ is distributed or made available, you shall also include “Llama 3” at the beginning\
\ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\
\ works thereof, from a Licensee as part of an integrated end user product, then\
\ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\
\ copies of the Llama Materials that you distribute the following attribution notice\
\ within a “Notice” text file distributed as a part of such copies: “Meta Llama\
\ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
\ applicable laws and regulations (including trade compliance laws and regulations)\
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
\ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\
\ into this Agreement.\nv. You will not use the Llama Materials or any output or\
\ results of the Llama Materials to improve any other large language model (excluding\
\ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\
\ on the Meta Llama 3 version release date, the monthly active users of the products\
\ or services made available by or for Licensee, or Licensee’s affiliates, is greater\
\ than 700 million monthly active users in the preceding calendar month, you must\
\ request a license from Meta, which Meta may grant to you in its sole discretion,\
\ and you are not authorized to exercise any of the rights under this Agreement\
\ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\
\ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\
\ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\
\ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\
\ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\
\ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\
\ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\
\ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\
\ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\
\ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\
\ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\
\ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\
5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\
\ and in connection with the Llama Materials, neither Meta nor Licensee may use\
\ any name or mark owned by or associated with the other or any of its affiliates,\
\ except as required for reasonable and customary use in describing and redistributing\
\ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\
\ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\
\ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\
\ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\
\ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\
\ Meta, with respect to any derivative works and modifications of the Llama Materials\
\ that are made by you, as between you and Meta, you are and will be the owner of\
\ such derivative works and modifications.\nc. If you institute litigation or other\
\ proceedings against Meta or any entity (including a cross-claim or counterclaim\
\ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\
\ or any portion of any of the foregoing, constitutes infringement of intellectual\
\ property or other rights owned or licensable by you, then any licenses granted\
\ to you under this Agreement shall terminate as of the date such litigation or\
\ claim is filed or instituted. You will indemnify and hold harmless Meta from and\
\ against any claim by any third party arising out of or related to your use or\
\ distribution of the Llama Materials.\n6. Term and Termination. The term of this\
\ Agreement will commence upon your acceptance of this Agreement or access to the\
\ Llama Materials and will continue in full force and effect until terminated in\
\ accordance with the terms and conditions herein. Meta may terminate this Agreement\
\ if you are in breach of any term or condition of this Agreement. Upon termination\
\ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
\ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
\ and Jurisdiction. This Agreement will be governed and construed under the laws\
\ of the State of California without regard to choice of law principles, and the\
\ UN Convention on Contracts for the International Sale of Goods does not apply\
\ to this Agreement. The courts of California shall have exclusive jurisdiction\
\ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\
\ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\
\ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\
\ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\
#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\
\ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 4.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\
\ or other sensitive personal or private information about individuals without rights\
\ and consents required by applicable laws\n 6. Engage in or facilitate any action\
\ or generate any content that infringes, misappropriates, or otherwise violates\
\ any third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 7. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n2. Engage in, promote, incite,\
\ facilitate, or assist in the planning or development of activities that present\
\ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\
\ to the following:\n 1. Military, warfare, nuclear industries or applications,\
\ espionage, use for materials or activities that are subject to the International\
\ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
\ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
\ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
\ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
\ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
\ content intended to incite or promote violence, abuse, or any infliction of bodily\
\ harm to an individual\n3. Intentionally deceive or mislead others, including use\
\ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\
\ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
\ or furthering defamatory content, including the creation of defamatory statements,\
\ images, or other content\n 3. Generating, promoting, or further distributing\
\ spam\n 4. Impersonating another individual without consent, authorization,\
\ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\
\ human-generated\n 6. Generating or facilitating false online engagement, including\
\ fake reviews and other means of fake online engagement\n4. Fail to appropriately\
\ disclose to end users any known dangers of your AI system\nPlease report any violation\
\ of this Policy, software “bug,” or other problems that could lead to a violation\
\ of this Policy through one of the following means:\n * Reporting issues with\
\ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\
\ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
\ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
\ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
quantized_by: andrijdavid
---
# Meta-Llama-Guard-2-8B-GGUF
- Original model: [Meta-Llama-Guard-2-8B](https://huggingface.co/meta-llama/Meta-Llama-Guard-2-8B)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Meta-Llama-Guard-2-8B](https://huggingface.co/meta-llama/Meta-Llama-Guard-2-8B).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.
* [Ollama](https://github.com/jmorganca/ollama) Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.
* [GPT4All](https://gpt4all.io), This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.
* [LM Studio](https://lmstudio.ai/) An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui). A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.
* [ctransformers](https://github.com/marella/ctransformers), A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.
* [localGPT](https://github.com/PromtEngineer/localGPT) An open-source initiative enabling private conversations with documents.
<!-- README_GGUF.md-about-gguf end -->
<!-- compatibility_gguf start -->
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: LiteLLMs/Meta-Llama-Guard-2-8B-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-00001-of-00009.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download LiteLLMs/Meta-Llama-Guard-2-8B-GGUF Q4_0/Q4_0-00001-of-00009.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download LiteLLMs/Meta-Llama-Guard-2-8B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install huggingface_hub[hf_transfer]
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download LiteLLMs/Meta-Llama-Guard-2-8B-GGUF Q4_0/Q4_0-00001-of-00009.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m Q4_0/Q4_0-00001-of-00009.gguf --color -c 8192 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<PROMPT>"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 8192` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./Q4_0/Q4_0-00001-of-00009.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<PROMPT>", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./Q4_0/Q4_0-00001-of-00009.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Meta-Llama-Guard-2-8B
# Model Details
Meta Llama Guard 2 is an 8B parameter Llama 3-based [1] LLM safeguard model. Similar to [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/), it can be used for classifying content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.
Below is a response classification example input and output for Llama Guard 2.
<p align="center">
<img src="https://github.com/facebookresearch/PurpleLlama/raw/main/Llama-Guard2/llamaguard_example.png" width="800"/>
</p>
In order to produce classifier scores, we look at the probability for the first token, and use that as the “unsafe” class probability. We can then apply score thresholding to make binary decisions.
# Harm Taxonomy and Policy
The model is trained to predict safety labels on the 11 categories shown below, based on the [MLCommons taxonomy](https://mlcommons.org/2024/04/mlc-aisafety-v0-5-poc/) of hazards.
<table align="center">
<thead>
<tr>
<th colspan="2">Harm categories</th>
</tr>
</thead>
<tbody>
<tr>
<td>S1: Violent Crimes</td>
<td>S2: Non-Violent Crimes</td>
</tr>
<tr>
<td>S3: Sex-Related Crimes</td>
<td>S4: Child Sexual Exploitation</td>
</tr>
<tr>
<td>S5: Specialized Advice</td>
<td>S6: Privacy</td>
</tr>
<tr>
<td>S7: Intellectual Property</td>
<td>S8: Indiscriminate Weapons </td>
</tr>
<tr>
<td>S9: Hate</td>
<td>S10: Suicide & Self-Harm</td>
</tr>
<tr>
<td>S11: Sexual Content</td>
<td></td>
</tr>
</tbody>
</table>
**S1: Violent Crimes**
Responses that enable, encourage, or endorse the commission of violent crimes, including: (1) unlawful violence toward people (ex: terrorism, genocide, murder, hate-motivated violent crimes, child abuse, assault, battery, kidnapping) and (2) unlawful violence toward animals (ex: animal abuse)
**S2: Non-Violent Crimes**
Responses that enable, encourage, or endorse the commission of non-violent crimes, including: (1) personal crimes (ex: labor trafficking, threats, intimidation, hate-motivated non-violent crimes), (2) financial crimes (ex: fraud, scams, money laundering), (3) property crimes (ex: theft, arson, vandalism), (4) drug crimes (ex: creating or using regulated substances), (5) weapons crimes (ex: producing unlicensed firearms), and (6) cyber crimes (ex: hacking)
**S3: Sex-Related Crimes**
Responses that enable, encourage, or endorse the commission of sex-related crimes, including: (1) sex trafficking, (2) sexual assault (ex: rape), (3) sexual harassment (physical, verbal, or visual), and (4) prostitution
**S4: Child Sexual Exploitation**
Responses that contain, describe, enable, encourage, or endorse the sexual abuse of children
**S5: Specialized Advice**
Responses that contain specialized financial, medical, or legal advice, or that indicate dangerous activities or objects are safe
**S6: Privacy**
Responses that contain sensitive, nonpublic personal information that could undermine someone's physical, digital, or financial security
**S7: Intellectual Property**
Responses that may violate the intellectual property rights of any third party
**S8: Indiscriminate Weapons**
Responses that enable, encourage, or endorse the creation of indiscriminate weapons, including: (1) chemical weapons (ex: nerve gas), (2) biological weapons (ex: anthrax), (3) radiological weapons (ex: cobalt bombs), (4) nuclear weapons (ex: fission bombs), and (5) high-yield explosive weapons (ex: cluster munitions)
**S9: Hate**
Responses that demean or dehumanize people on the basis of their sensitive, personal characteristics (i.e., race, color, ethnicity, national origin, disability, religious affiliation, caste, sexual orientation, sex, gender identity, and/or serious disease)
**S10: Suicide & Self-Harm**
Responses that enable, encourage, or endorse acts of intentional self-harm, including: (1) suicide, (2) self-injury (ex: cutting), and (3) disordered eating
**S11: Sexual Content**
Responses that contain erotica
## How to Use in `transformers`
```py
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "meta-llama/Meta-Llama-Guard-2-8B"
device = "cuda"
dtype = torch.bfloat16
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=dtype, device_map=device)
def moderate(chat):
input_ids = tokenizer.apply_chat_template(chat, return_tensors="pt").to(device)
output = model.generate(input_ids=input_ids, max_new_tokens=100, pad_token_id=0)
prompt_len = input_ids.shape[-1]
return tokenizer.decode(output[0][prompt_len:], skip_special_tokens=True)
moderate([
{"role": "user", "content": "I forgot how to kill a process in Linux, can you help?"},
{"role": "assistant", "content": "Sure! To kill a process in Linux, you can use the kill command followed by the process ID (PID) of the process you want to terminate."},
])
# `safe`
```
# Training and Evaluation Data
We start with the training set of Llama Guard (see [model card](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard/MODEL_CARD.md#training-data)), and obtain labels on the Harm Taxonomy described above. To improve adaptability of the model to different prompts, we train on hard samples, which are obtained by taking an existing sample and prompting Llama2 70B to produce an alternate policy description that will flip the label of the given sample.
We report metrics for various models and APIs on our validation set, which is obtained from combining the validation set of Llama Guard v1 and held-out samples from the additional Llama 3 safety data.
We compare performance on our internal test set, as well as on open datasets like [XSTest](https://github.com/paul-rottger/exaggerated-safety?tab=readme-ov-file#license), [OpenAI moderation](https://github.com/openai/moderation-api-release), and [BeaverTails](https://github.com/PKU-Alignment/beavertails).
We find that there is overlap between our training set and the BeaverTails-30k test split. Since both our internal test set and BeaverTails use prompts from the Anthropic's [hh-rlhf dataset](https://github.com/anthropics/hh-rlhf) as a starting point for curating data, it is possible that different splits of Anthropic were used while creating the two datasets. Therefore to prevent leakage of signal between our train set and the BeaverTails-30k test set, we create our own BeaverTails-30k splits based on the Anthropic train-test splits used for creating our internal sets.
*Note on evaluations*: As discussed in the Llama Guard [paper](https://arxiv.org/abs/2312.06674), comparing model performance is not straightforward as each model is built on its own policy and is expected to perform better on an evaluation dataset with a policy aligned to the model. This highlights the need for industry standards. By aligning Llama Guard 2 with the Proof of Concept MLCommons taxonomy, we hope to drive adoption of industry standards like this and facilitate collaboration and transparency in the LLM safety and content evaluation space.
# Model Performance
We evaluate the performance of Llama Guard 2 and compare it with Llama Guard and popular content moderation APIs such as Azure, OpenAI Moderation, and Perspective. We use the token probability of the first output token (i.e. safe/unsafe) as the score for classification. For obtaining a binary classification decision from the score, we use a threshold of 0.5.
Llama Guard 2 improves over Llama Guard, and outperforms other approaches on our internal test set. Note that we manage to achieve great performance while keeping a low false positive rate as we know that over-moderation can impact user experience when building LLM-applications.
<div align="center">
| **Model** | **F1 ↑** | **AUPRC ↑** | **False Positive<br>Rate ↓** |
| | :--: | :--: | :--: |
| Llama Guard\* | 0.665 | <ins>0.854</ins> | 0.027 |
| Llama Guard 2 | **0.915** | **0.974** | 0.040 |
| GPT4 | <ins>0.796</ins> | N/A | 0.151 |
| OpenAI Moderation API | 0.347 | 0.669 | 0.030 |
| Azure Content Safety API | 0.519 | N/A | 0.245 |
| Perspective API | 0.265 | 0.586 | 0.046 |
<small> Table 1: Comparison of performance of various approaches measured on our internal test set.
<br><small><small>
*The performance of Llama Guard is lower on our new test set due to expansion of the number of harm categories from 6 to 11, which is not aligned to what Llama Guard was trained on.
</small></small></small>
</div>
<br>
<div align="center">
| **Category** | **False Negative Rate\* ↓** | **False Positive Rate ↓** |
| --: |
| Violent Crimes | 0.042 | 0.002 |
| Privacy | 0.057 | 0.004 |
| Non-Violent Crimes | 0.082 | 0.009 |
| Intellectual Property | 0.099 | 0.004 |
| Hate | 0.190 | 0.005 |
| Specialized Advice | 0.192 | 0.009 |
| Sexual Content | 0.229 | 0.004 |
| Indiscriminate Weapons | 0.263 | 0.001 |
| Child Exploitation | 0.267 | 0.000 |
| Sex Crimes | 0.275 | 0.002 |
| Self-Harm | 0.277 | 0.002 |
<small> Table 2: Category-wise breakdown of false negative rate and false positive rate for Llama Guard 2 on our internal benchmark for response classification with safety labels from the ML Commons taxonomy.<br><small><small>*The binary safe/unsafe label is used to compute categorical FNR by using the true categories. We do not penalize the model while computing FNR for cases where the model predicts the correct overall label but an incorrect categorical label.</small></small></small>
</div>
We also report performance on OSS safety datasets, though we note that the policy used for assigning safety labels is not aligned with the policy used while training Llama Guard 2. Still, Llama Guard 2 provides a superior tradeoff between f1 score and False Positive Rate on the XSTest and OpenAI Moderation datasets, demonstrating good adaptability to other policies.
The BeaverTails dataset has a lower bar for a sample to be considered unsafe compared to Llama Guard 2's policy. The policy and training data of MDJudge [4] is more aligned with this dataset and we see that it performs better on them as expected (at the cost of a higher FPR). GPT-4 achieves high recall on all of the sets but at the cost of very high FPR (9-25%), which could hurt its ability to be used as a safeguard for practical applications.
<table align="center">
<thead>
<tr>
<th></th>
<th colspan="3">(F1 ↑ / False Positive Rate ↓)</th>
</tr>
</thead>
<tbody>
<tr>
<td></td>
<td><center>False Refusals<br>(XSTest)</center></td>
<td><center>OpenAI policy<br>(OpenAI Mod)</center></td>
<td><center>BeaverTails policy<br>(BeaverTails-30k)</center></td>
</tr>
<tr>
<td>Llama Guard</td>
<td>0.737 / 0.079</td>
<td>0.737 / 0.079</td>
<td>0.599 / 0.035</td>
</tr>
<tr>
<td>Llama Guard 2</td>
<td>0.884 / 0.084</td>
<td>0.807 / 0.060</td>
<td>0.736 / 0.059</td>
</tr>
<tr>
<td>MDJudge</td>
<td>0.856 / 0.172</td>
<td>0.768 / 0.212</td>
<td>0.849 / 0.098</td>
</tr>
<tr>
<td>GPT4</td>
<td>0.895 / 0.128</td>
<td>0.842 / 0.092</td>
<td>0.802 / 0.256</td>
</tr>
<tr>
<td>OpenAI Mod API</td>
<td>0.576 / 0.040</td>
<td>0.788 / 0.156</td>
<td>0.284 / 0.056</td>
</tr>
</tbody>
</table>
<div align="center">
<small>Table 3: Comparison of performance of various approaches measured on our internal test set for response classification. <br>NOTE: The policy used for training Llama Guard does not align with those used for labeling these datasets. Still, Llama Guard 2 provides a superior tradeoff between F1 score and False Positive Rate across these datasets, demonstrating strong adaptability to other policies.</small>
</div>
<br>
We hope to provide developers with a high-performing moderation solution for most use cases by aligning Llama Guard 2 taxonomy with MLCommons standard. But as outlined in our Responsible Use Guide, each use case requires specific safety considerations and we encourage developers to tune Llama Guard 2 for their own use case to achieve better moderation for their custom policies. As an example of how Llama Guard 2's performance may change, we train on the BeaverTails training dataset and compare against MDJudge (which was trained on BeaverTails among others).
<div align="center">
<br>
| **Model** | **F1 ↑** | **False Positive Rate ↓** |
| :-: | :--: | :-----: |
| Llama Guard 2 | 0.736 | 0.059 |
| MDJudge | <ins>0.849</ins> | 0.098 |
| Llama Guard 2 + BeaverTails | **0.852** | 0.101 |
<small>Table 4: Comparison of performance on BeaverTails-30k.</small>
</div>
# Limitations
There are some limitations associated with Llama Guard 2. First, Llama Guard 2 itself is an LLM fine-tuned on Llama 3. Thus, its performance (e.g., judgments that need common sense knowledge, multilingual capability, and policy coverage) might be limited by its (pre-)training data.
Second, Llama Guard 2 is finetuned for safety classification only (i.e. to generate "safe" or "unsafe"), and is not designed for chat use cases. However, since it is an LLM, it can still be prompted with any text to obtain a completion.
Lastly, as an LLM, Llama Guard 2 may be susceptible to adversarial attacks or prompt injection attacks that could bypass or alter its intended use. However, with the help of external components (e.g., KNN, perplexity filter), recent work (e.g., [3]) demonstrates that Llama Guard is able to detect harmful content reliably.
**Note on Llama Guard 2's policy**
Llama Guard 2 supports 11 out of the 13 categories included in the [MLCommons AI Safety](https://mlcommons.org/working-groups/ai-safety/ai-safety/) taxonomy. The Election and Defamation categories are not addressed by Llama Guard 2 as moderating these harm categories requires access to up-to-date, factual information sources and the ability to determine the veracity of a particular output. To support the additional categories, we recommend using other solutions (e.g. Retrieval Augmented Generation) in tandem with Llama Guard 2 to evaluate information correctness.
# Citation
```
@misc{metallamaguard2,
author = {Llama Team},
title = {Meta Llama Guard 2},
howpublished = {\url{https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard2/MODEL_CARD.md}},
year = {2024}
}
```
# References
[1] [Llama 3 Model Card](https://github.com/meta-llama/llama3/blob)
[2] [Llama Guard Model Card](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard/MODEL_CARD.md)
[3] [RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content](https://arxiv.org/pdf/2403.13031.pdf)
[4] [MDJudge for Salad-Bench](https://huggingface.co/OpenSafetyLab/MD-Judge-v0.1)
<!-- original-model-card end -->
|
QuantFactory/AI-Sweden-Llama-3-8B-Instruct-GGUF
|
QuantFactory
| 2024-06-09T13:20:45Z | 374 | 0 | null |
[
"gguf",
"text-generation",
"dataset:teknium/OpenHermes-2.5",
"base_model:AI-Sweden-Models/Llama-3-8B-instruct",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2024-06-09T06:51:33Z |
---
license: apache-2.0
datasets: teknium/OpenHermes-2.5
base_model: AI-Sweden-Models/Llama-3-8B-instruct
pipeline_tag: text-generation
---
# QuantFactory/AI-Sweden-Llama-3-8B-Instruct-GGUF
This is quantized version of [AI-Sweden-Models/Llama-3-8B-instruct](https://huggingface.co/AI-Sweden-Models/Llama-3-8B-instruct) created suing llama.cpp
# Model Description
# Checkpoint 1
## Training setup
The training was perfomed on the [LUMI supercomputer](https://lumi-supercomputer.eu/) within the [DeployAI EU project](https://www.ai.se/en/project/deployai).
Based of the base model [AI-Sweden-Models/Llama-3-8B](https://huggingface.co/AI-Sweden-Models/Llama-3-8B).
## Dataset
A data recipe by: [42 Labs](https://huggingface.co/four-two-labs)
## How to use
```python
import transformers
import torch
model_id = "AI-Sweden-Models/Llama-3-8B-instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
messages = [
{"role": "system", "content": "Du är en hjälpsam assistant som svarar klokt och vänligt."},
{"role": "user", "content": "Hur gör man pannkakor? Och vad behöver man handla? Undrar också vad 5+6 är.."},
]
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
messages,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][-1])
```
```python
>>> "För att göra pannkakor behöver du följande ingredienser:
- 1 kopp vetemjöl
- 1 tesked bakpulver
- 1/4 tesked salt
- 1 kopp mjölk
- 1 stort ägg
- 2 matskedar smält smör eller olja
För att börja, blanda vetemjölet, bakpulvret och saltet i en bunke. I en annan skål, vispa ihop mjölken, ägget och smöret eller oljan.
Tillsätt de våta ingredienserna till de torra ingredienserna och blanda tills det är väl blandat.
Låt smeten vila i cirka 10 minuter.
För att göra pannkakorna, värm en non-stick-panna eller stekpanna över medelvärme.
När den är varm, häll smeten på pannan och grädda tills kanterna börjar torka ut och toppen är fast.
Vänd pannkakan med en stekspade och grädda den andra sidan tills den är gyllenbrun.
Upprepa med resten av smeten.
När det gäller 5+6 är svaret 11."
```
|
hf-100/Llama-3-Spellbound-Instruct-8B-0.3-gguf
|
hf-100
| 2024-06-16T10:59:13Z | 374 | 6 | null |
[
"gguf",
"license:cc-by-nc-sa-4.0",
"region:us"
] | null | 2024-06-16T10:52:53Z |
---
license: cc-by-nc-sa-4.0
---
# Llama-3 Spellbound Instruct Tuning-Free Q8 GGUF
<img src="https://i.imgur.com/IG4IKfV.png" width=100 height=100>
# Updated Aspects
- Trained on additional tokens
- Improved mix of subject matter model was trained on
- Trained for 1.5M additional tokens
- Additional training on DPO dataset
# Model Rationale
Llama 3 is a strong base model with strong world understanding and creativity. Additional instruct finetuning trades that world understanding and creativity for instruction following that Llama doesn't require in order to adhere to most forms of roleplay.
This model was trained on unstructured text only, no instruct related fine-tuning was performed.
Made by [tryspellbound.com](https://tryspellbound.com).
*(tryspellbound.com does not currently use this model, it uses Claude 3 Sonnet.)*
## Features of this fine-tune for Llama 3:
- Roleplaying in multi-turn stories where the history is presented in a single message
- Dynamic switching of writing styles for different scenarios
- Interpretation of formatting marks 'quote' and 'action'
**Warning:** The underlying model, Llama 3, was trained on data that included adult content. This fine-tune does not add additional guardrails and is not suitable for all environments.
## Purpose of the Model
The main goal is to explore how presenting LLMs with history and instructions separately affects their performance, demonstrating:
- Improved coherence in long conversations
- Enhanced quality of character interactions
- Decreased instruction adherence, which could be improved with additional training
## Advanced prompting of the model
For advanced prompting, see [this document](https://rentry.co/ti936r2i)
|
jplu/tf-xlm-r-ner-40-lang
|
jplu
| 2022-10-06T09:25:04Z | 373 | 23 |
transformers
|
[
"transformers",
"tf",
"xlm-roberta",
"token-classification",
"multilingual",
"af",
"ar",
"bg",
"bn",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"fi",
"fr",
"he",
"hi",
"hu",
"id",
"it",
"ja",
"jv",
"ka",
"kk",
"ko",
"ml",
"mr",
"ms",
"my",
"nl",
"pt",
"ru",
"sw",
"ta",
"te",
"th",
"tl",
"tr",
"ur",
"vi",
"yo",
"zh",
"arxiv:1911.02116",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2022-03-02T23:29:05Z |
---
language:
- multilingual
- af
- ar
- bg
- bn
- de
- el
- en
- es
- et
- eu
- fa
- fi
- fr
- he
- hi
- hu
- id
- it
- ja
- jv
- ka
- kk
- ko
- ml
- mr
- ms
- my
- nl
- pt
- ru
- sw
- ta
- te
- th
- tl
- tr
- ur
- vi
- yo
- zh
language_bcp47:
- fa-IR
---
# XLM-R + NER
This model is a fine-tuned [XLM-Roberta-base](https://arxiv.org/abs/1911.02116) over the 40 languages proposed in [XTREME](https://github.com/google-research/xtreme) from [Wikiann](https://aclweb.org/anthology/P17-1178). This is still an on-going work and the results will be updated everytime an improvement is reached.
The covered labels are:
```
LOC
ORG
PER
O
```
## Metrics on evaluation set:
### Average over the 40 languages
Number of documents: 262300
```
precision recall f1-score support
ORG 0.81 0.81 0.81 102452
PER 0.90 0.91 0.91 108978
LOC 0.86 0.89 0.87 121868
micro avg 0.86 0.87 0.87 333298
macro avg 0.86 0.87 0.87 333298
```
### Afrikaans
Number of documents: 1000
```
precision recall f1-score support
ORG 0.89 0.88 0.88 582
PER 0.89 0.97 0.93 369
LOC 0.84 0.90 0.86 518
micro avg 0.87 0.91 0.89 1469
macro avg 0.87 0.91 0.89 1469
```
### Arabic
Number of documents: 10000
```
precision recall f1-score support
ORG 0.83 0.84 0.84 3507
PER 0.90 0.91 0.91 3643
LOC 0.88 0.89 0.88 3604
micro avg 0.87 0.88 0.88 10754
macro avg 0.87 0.88 0.88 10754
```
### Basque
Number of documents: 10000
```
precision recall f1-score support
LOC 0.88 0.93 0.91 5228
ORG 0.86 0.81 0.83 3654
PER 0.91 0.91 0.91 4072
micro avg 0.89 0.89 0.89 12954
macro avg 0.89 0.89 0.89 12954
```
### Bengali
Number of documents: 1000
```
precision recall f1-score support
ORG 0.86 0.89 0.87 325
LOC 0.91 0.91 0.91 406
PER 0.96 0.95 0.95 364
micro avg 0.91 0.92 0.91 1095
macro avg 0.91 0.92 0.91 1095
```
### Bulgarian
Number of documents: 1000
```
precision recall f1-score support
ORG 0.86 0.83 0.84 3661
PER 0.92 0.95 0.94 4006
LOC 0.92 0.95 0.94 6449
micro avg 0.91 0.92 0.91 14116
macro avg 0.91 0.92 0.91 14116
```
### Burmese
Number of documents: 100
```
precision recall f1-score support
LOC 0.60 0.86 0.71 37
ORG 0.68 0.63 0.66 30
PER 0.44 0.44 0.44 36
micro avg 0.57 0.65 0.61 103
macro avg 0.57 0.65 0.60 103
```
### Chinese
Number of documents: 10000
```
precision recall f1-score support
ORG 0.70 0.69 0.70 4022
LOC 0.76 0.81 0.78 3830
PER 0.84 0.84 0.84 3706
micro avg 0.76 0.78 0.77 11558
macro avg 0.76 0.78 0.77 11558
```
### Dutch
Number of documents: 10000
```
precision recall f1-score support
ORG 0.87 0.87 0.87 3930
PER 0.95 0.95 0.95 4377
LOC 0.91 0.92 0.91 4813
micro avg 0.91 0.92 0.91 13120
macro avg 0.91 0.92 0.91 13120
```
### English
Number of documents: 10000
```
precision recall f1-score support
LOC 0.83 0.84 0.84 4781
PER 0.89 0.90 0.89 4559
ORG 0.75 0.75 0.75 4633
micro avg 0.82 0.83 0.83 13973
macro avg 0.82 0.83 0.83 13973
```
### Estonian
Number of documents: 10000
```
precision recall f1-score support
LOC 0.89 0.92 0.91 5654
ORG 0.85 0.85 0.85 3878
PER 0.94 0.94 0.94 4026
micro avg 0.90 0.91 0.90 13558
macro avg 0.90 0.91 0.90 13558
```
### Finnish
Number of documents: 10000
```
precision recall f1-score support
ORG 0.84 0.83 0.84 4104
LOC 0.88 0.90 0.89 5307
PER 0.95 0.94 0.94 4519
micro avg 0.89 0.89 0.89 13930
macro avg 0.89 0.89 0.89 13930
```
### French
Number of documents: 10000
```
precision recall f1-score support
LOC 0.90 0.89 0.89 4808
ORG 0.84 0.87 0.85 3876
PER 0.94 0.93 0.94 4249
micro avg 0.89 0.90 0.90 12933
macro avg 0.89 0.90 0.90 12933
```
### Georgian
Number of documents: 10000
```
precision recall f1-score support
PER 0.90 0.91 0.90 3964
ORG 0.83 0.77 0.80 3757
LOC 0.82 0.88 0.85 4894
micro avg 0.84 0.86 0.85 12615
macro avg 0.84 0.86 0.85 12615
```
### German
Number of documents: 10000
```
precision recall f1-score support
LOC 0.85 0.90 0.87 4939
PER 0.94 0.91 0.92 4452
ORG 0.79 0.78 0.79 4247
micro avg 0.86 0.86 0.86 13638
macro avg 0.86 0.86 0.86 13638
```
### Greek
Number of documents: 10000
```
precision recall f1-score support
ORG 0.86 0.85 0.85 3771
LOC 0.88 0.91 0.90 4436
PER 0.91 0.93 0.92 3894
micro avg 0.88 0.90 0.89 12101
macro avg 0.88 0.90 0.89 12101
```
### Hebrew
Number of documents: 10000
```
precision recall f1-score support
PER 0.87 0.88 0.87 4206
ORG 0.76 0.75 0.76 4190
LOC 0.85 0.85 0.85 4538
micro avg 0.83 0.83 0.83 12934
macro avg 0.82 0.83 0.83 12934
```
### Hindi
Number of documents: 1000
```
precision recall f1-score support
ORG 0.78 0.81 0.79 362
LOC 0.83 0.85 0.84 422
PER 0.90 0.95 0.92 427
micro avg 0.84 0.87 0.85 1211
macro avg 0.84 0.87 0.85 1211
```
### Hungarian
Number of documents: 10000
```
precision recall f1-score support
PER 0.95 0.95 0.95 4347
ORG 0.87 0.88 0.87 3988
LOC 0.90 0.92 0.91 5544
micro avg 0.91 0.92 0.91 13879
macro avg 0.91 0.92 0.91 13879
```
### Indonesian
Number of documents: 10000
```
precision recall f1-score support
ORG 0.88 0.89 0.88 3735
LOC 0.93 0.95 0.94 3694
PER 0.93 0.93 0.93 3947
micro avg 0.91 0.92 0.92 11376
macro avg 0.91 0.92 0.92 11376
```
### Italian
Number of documents: 10000
```
precision recall f1-score support
LOC 0.88 0.88 0.88 4592
ORG 0.86 0.86 0.86 4088
PER 0.96 0.96 0.96 4732
micro avg 0.90 0.90 0.90 13412
macro avg 0.90 0.90 0.90 13412
```
### Japanese
Number of documents: 10000
```
precision recall f1-score support
ORG 0.62 0.61 0.62 4184
PER 0.76 0.81 0.78 3812
LOC 0.68 0.74 0.71 4281
micro avg 0.69 0.72 0.70 12277
macro avg 0.69 0.72 0.70 12277
```
### Javanese
Number of documents: 100
```
precision recall f1-score support
ORG 0.79 0.80 0.80 46
PER 0.81 0.96 0.88 26
LOC 0.75 0.75 0.75 40
micro avg 0.78 0.82 0.80 112
macro avg 0.78 0.82 0.80 112
```
### Kazakh
Number of documents: 1000
```
precision recall f1-score support
ORG 0.76 0.61 0.68 307
LOC 0.78 0.90 0.84 461
PER 0.87 0.91 0.89 367
micro avg 0.81 0.83 0.82 1135
macro avg 0.81 0.83 0.81 1135
```
### Korean
Number of documents: 10000
```
precision recall f1-score support
LOC 0.86 0.89 0.88 5097
ORG 0.79 0.74 0.77 4218
PER 0.83 0.86 0.84 4014
micro avg 0.83 0.83 0.83 13329
macro avg 0.83 0.83 0.83 13329
```
### Malay
Number of documents: 1000
```
precision recall f1-score support
ORG 0.87 0.89 0.88 368
PER 0.92 0.91 0.91 366
LOC 0.94 0.95 0.95 354
micro avg 0.91 0.92 0.91 1088
macro avg 0.91 0.92 0.91 1088
```
### Malayalam
Number of documents: 1000
```
precision recall f1-score support
ORG 0.75 0.74 0.75 347
PER 0.84 0.89 0.86 417
LOC 0.74 0.75 0.75 391
micro avg 0.78 0.80 0.79 1155
macro avg 0.78 0.80 0.79 1155
```
### Marathi
Number of documents: 1000
```
precision recall f1-score support
PER 0.89 0.94 0.92 394
LOC 0.82 0.84 0.83 457
ORG 0.84 0.78 0.81 339
micro avg 0.85 0.86 0.85 1190
macro avg 0.85 0.86 0.85 1190
```
### Persian
Number of documents: 10000
```
precision recall f1-score support
PER 0.93 0.92 0.93 3540
LOC 0.93 0.93 0.93 3584
ORG 0.89 0.92 0.90 3370
micro avg 0.92 0.92 0.92 10494
macro avg 0.92 0.92 0.92 10494
```
### Portuguese
Number of documents: 10000
```
precision recall f1-score support
LOC 0.90 0.91 0.91 4819
PER 0.94 0.92 0.93 4184
ORG 0.84 0.88 0.86 3670
micro avg 0.89 0.91 0.90 12673
macro avg 0.90 0.91 0.90 12673
```
### Russian
Number of documents: 10000
```
precision recall f1-score support
PER 0.93 0.96 0.95 3574
LOC 0.87 0.89 0.88 4619
ORG 0.82 0.80 0.81 3858
micro avg 0.87 0.88 0.88 12051
macro avg 0.87 0.88 0.88 12051
```
### Spanish
Number of documents: 10000
```
precision recall f1-score support
PER 0.95 0.93 0.94 3891
ORG 0.86 0.88 0.87 3709
LOC 0.89 0.91 0.90 4553
micro avg 0.90 0.91 0.90 12153
macro avg 0.90 0.91 0.90 12153
```
### Swahili
Number of documents: 1000
```
precision recall f1-score support
ORG 0.82 0.85 0.83 349
PER 0.95 0.92 0.94 403
LOC 0.86 0.89 0.88 450
micro avg 0.88 0.89 0.88 1202
macro avg 0.88 0.89 0.88 1202
```
### Tagalog
Number of documents: 1000
```
precision recall f1-score support
LOC 0.90 0.91 0.90 338
ORG 0.83 0.91 0.87 339
PER 0.96 0.93 0.95 350
micro avg 0.90 0.92 0.91 1027
macro avg 0.90 0.92 0.91 1027
```
### Tamil
Number of documents: 1000
```
precision recall f1-score support
PER 0.90 0.92 0.91 392
ORG 0.77 0.76 0.76 370
LOC 0.78 0.81 0.79 421
micro avg 0.82 0.83 0.82 1183
macro avg 0.82 0.83 0.82 1183
```
### Telugu
Number of documents: 1000
```
precision recall f1-score support
ORG 0.67 0.55 0.61 347
LOC 0.78 0.87 0.82 453
PER 0.73 0.86 0.79 393
micro avg 0.74 0.77 0.76 1193
macro avg 0.73 0.77 0.75 1193
```
### Thai
Number of documents: 10000
```
precision recall f1-score support
LOC 0.63 0.76 0.69 3928
PER 0.78 0.83 0.80 6537
ORG 0.59 0.59 0.59 4257
micro avg 0.68 0.74 0.71 14722
macro avg 0.68 0.74 0.71 14722
```
### Turkish
Number of documents: 10000
```
precision recall f1-score support
PER 0.94 0.94 0.94 4337
ORG 0.88 0.89 0.88 4094
LOC 0.90 0.92 0.91 4929
micro avg 0.90 0.92 0.91 13360
macro avg 0.91 0.92 0.91 13360
```
### Urdu
Number of documents: 1000
```
precision recall f1-score support
LOC 0.90 0.95 0.93 352
PER 0.96 0.96 0.96 333
ORG 0.91 0.90 0.90 326
micro avg 0.92 0.94 0.93 1011
macro avg 0.92 0.94 0.93 1011
```
### Vietnamese
Number of documents: 10000
```
precision recall f1-score support
ORG 0.86 0.87 0.86 3579
LOC 0.88 0.91 0.90 3811
PER 0.92 0.93 0.93 3717
micro avg 0.89 0.90 0.90 11107
macro avg 0.89 0.90 0.90 11107
```
### Yoruba
Number of documents: 100
```
precision recall f1-score support
LOC 0.54 0.72 0.62 36
ORG 0.58 0.31 0.41 35
PER 0.77 1.00 0.87 36
micro avg 0.64 0.68 0.66 107
macro avg 0.63 0.68 0.63 107
```
## Reproduce the results
Download and prepare the dataset from the [XTREME repo](https://github.com/google-research/xtreme#download-the-data). Next, from the root of the transformers repo run:
```
cd examples/ner
python run_tf_ner.py \
--data_dir . \
--labels ./labels.txt \
--model_name_or_path jplu/tf-xlm-roberta-base \
--output_dir model \
--max-seq-length 128 \
--num_train_epochs 2 \
--per_gpu_train_batch_size 16 \
--per_gpu_eval_batch_size 32 \
--do_train \
--do_eval \
--logging_dir logs \
--mode token-classification \
--evaluate_during_training \
--optimizer_name adamw
```
## Usage with pipelines
```python
from transformers import pipeline
nlp_ner = pipeline(
"ner",
model="jplu/tf-xlm-r-ner-40-lang",
tokenizer=(
'jplu/tf-xlm-r-ner-40-lang',
{"use_fast": True}),
framework="tf"
)
text_fr = "Barack Obama est né à Hawaï."
text_en = "Barack Obama was born in Hawaii."
text_es = "Barack Obama nació en Hawai."
text_zh = "巴拉克·奧巴馬（Barack Obama）出生於夏威夷。"
text_ar = "ولد باراك أوباما في هاواي."
nlp_ner(text_fr)
#Output: [{'word': '▁Barack', 'score': 0.9894659519195557, 'entity': 'PER'}, {'word': '▁Obama', 'score': 0.9888848662376404, 'entity': 'PER'}, {'word': '▁Hawa', 'score': 0.998701810836792, 'entity': 'LOC'}, {'word': 'ï', 'score': 0.9987035989761353, 'entity': 'LOC'}]
nlp_ner(text_en)
#Output: [{'word': '▁Barack', 'score': 0.9929141998291016, 'entity': 'PER'}, {'word': '▁Obama', 'score': 0.9930834174156189, 'entity': 'PER'}, {'word': '▁Hawaii', 'score': 0.9986202120780945, 'entity': 'LOC'}]
nlp_ner(test_es)
#Output: [{'word': '▁Barack', 'score': 0.9944776296615601, 'entity': 'PER'}, {'word': '▁Obama', 'score': 0.9949177503585815, 'entity': 'PER'}, {'word': '▁Hawa', 'score': 0.9987911581993103, 'entity': 'LOC'}, {'word': 'i', 'score': 0.9984861612319946, 'entity': 'LOC'}]
nlp_ner(test_zh)
#Output: [{'word': '夏威夷', 'score': 0.9988449215888977, 'entity': 'LOC'}]
nlp_ner(test_ar)
#Output: [{'word': '▁با', 'score': 0.9903655648231506, 'entity': 'PER'}, {'word': 'راك', 'score': 0.9850614666938782, 'entity': 'PER'}, {'word': '▁أوباما', 'score': 0.9850308299064636, 'entity': 'PER'}, {'word': '▁ها', 'score': 0.9477543234825134, 'entity': 'LOC'}, {'word': 'وا', 'score': 0.9428229928016663, 'entity': 'LOC'}, {'word': 'ي', 'score': 0.9319471716880798, 'entity': 'LOC'}]
```
|
Yntec/SCMix
|
Yntec
| 2023-11-07T21:32:54Z | 373 | 2 |
diffusers
|
[
"diffusers",
"safetensors",
"Anime",
"Style",
"Getsc",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-11-07T19:13:58Z |
---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Anime
- Style
- Getsc
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
# SCMix
Safetensors version of this model with the MoistMixV2 VAE baked in.
Comparison:
(Click for larger)
Sample and prompt:
best quality, masterpiece, 1girl, outside, park, shrine, leaning forward, hair ornament, earrings, traditional kimono, flower pattern,blushing,embarrased, brown extra long hair, smiling, spoken heart,solo
Original page: https://civitai.com/models/19809?modelVersionId=23515
|
TheBloke/sqlcoder-34b-alpha-GGUF
|
TheBloke
| 2023-11-18T17:56:03Z | 373 | 12 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation",
"en",
"base_model:defog/sqlcoder-34b-alpha",
"license:cc-by-4.0",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-11-18T17:35:50Z |
---
base_model: defog/sqlcoder-34b-alpha
inference: false
language:
- en
license: cc-by-4.0
model_creator: Defog.ai
model_name: SQLCoder 34B Alpha
model_type: llama
pipeline_tag: text-generation
prompt_template: "## Task\nGenerate a SQL query to answer the following question:\n\
`{prompt}`\n\n### Database Schema\nThis query will run on a database whose schema\
\ is represented in this string:\nCREATE TABLE products (\n product_id INTEGER\
\ PRIMARY KEY, -- Unique ID for each product\n name VARCHAR(50), -- Name of the\
\ product\n price DECIMAL(10,2), -- Price of each unit of the product\n quantity\
\ INTEGER -- Current quantity in stock\n);\n\nCREATE TABLE sales (\n sale_id INTEGER\
\ PRIMARY KEY, -- Unique ID for each sale\n product_id INTEGER, -- ID of product\
\ sold\n customer_id INTEGER, -- ID of customer who made purchase\n salesperson_id\
\ INTEGER, -- ID of salesperson who made the sale\n sale_date DATE, -- Date the\
\ sale occurred\n quantity INTEGER -- Quantity of product sold\n);\n\n-- sales.product_id\
\ can be joined with products.product_id\n\n### SQL\nGiven the database schema,\
\ here is the SQL query that answers `{prompt}`:\n```sql\n"
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# SQLCoder 34B Alpha - GGUF
- Model creator: [Defog.ai](https://huggingface.co/defog)
- Original model: [SQLCoder 34B Alpha](https://huggingface.co/defog/sqlcoder-34b-alpha)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Defog.ai's SQLCoder 34B Alpha](https://huggingface.co/defog/sqlcoder-34b-alpha).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF)
* [Defog.ai's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/defog/sqlcoder-34b-alpha)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Sqlcoder
```
## Task
Generate a SQL query to answer the following question:
`{prompt}`
### Database Schema
This query will run on a database whose schema is represented in this string:
CREATE TABLE products (
product_id INTEGER PRIMARY KEY, -- Unique ID for each product
name VARCHAR(50), -- Name of the product
price DECIMAL(10,2), -- Price of each unit of the product
quantity INTEGER -- Current quantity in stock
);
CREATE TABLE sales (
sale_id INTEGER PRIMARY KEY, -- Unique ID for each sale
product_id INTEGER, -- ID of product sold
customer_id INTEGER, -- ID of customer who made purchase
salesperson_id INTEGER, -- ID of salesperson who made the sale
sale_date DATE, -- Date the sale occurred
quantity INTEGER -- Quantity of product sold
);
-- sales.product_id can be joined with products.product_id
### SQL
Given the database schema, here is the SQL query that answers `{prompt}`:
```sql
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `cc-by-4.0`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Defog.ai's SQLCoder 34B Alpha](https://huggingface.co/defog/sqlcoder-34b-alpha).
<!-- licensing end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [sqlcoder-34b-alpha.Q2_K.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q2_K.gguf) | Q2_K | 2 | 14.21 GB| 16.71 GB | smallest, significant quality loss - not recommended for most purposes |
| [sqlcoder-34b-alpha.Q3_K_S.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q3_K_S.gguf) | Q3_K_S | 3 | 14.61 GB| 17.11 GB | very small, high quality loss |
| [sqlcoder-34b-alpha.Q3_K_M.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q3_K_M.gguf) | Q3_K_M | 3 | 16.28 GB| 18.78 GB | very small, high quality loss |
| [sqlcoder-34b-alpha.Q3_K_L.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q3_K_L.gguf) | Q3_K_L | 3 | 17.77 GB| 20.27 GB | small, substantial quality loss |
| [sqlcoder-34b-alpha.Q4_0.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q4_0.gguf) | Q4_0 | 4 | 19.05 GB| 21.55 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [sqlcoder-34b-alpha.Q4_K_S.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q4_K_S.gguf) | Q4_K_S | 4 | 19.15 GB| 21.65 GB | small, greater quality loss |
| [sqlcoder-34b-alpha.Q4_K_M.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q4_K_M.gguf) | Q4_K_M | 4 | 20.22 GB| 22.72 GB | medium, balanced quality - recommended |
| [sqlcoder-34b-alpha.Q5_0.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q5_0.gguf) | Q5_0 | 5 | 23.24 GB| 25.74 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [sqlcoder-34b-alpha.Q5_K_S.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q5_K_S.gguf) | Q5_K_S | 5 | 23.24 GB| 25.74 GB | large, low quality loss - recommended |
| [sqlcoder-34b-alpha.Q5_K_M.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q5_K_M.gguf) | Q5_K_M | 5 | 23.84 GB| 26.34 GB | large, very low quality loss - recommended |
| [sqlcoder-34b-alpha.Q6_K.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q6_K.gguf) | Q6_K | 6 | 27.68 GB| 30.18 GB | very large, extremely low quality loss |
| [sqlcoder-34b-alpha.Q8_0.gguf](https://huggingface.co/TheBloke/sqlcoder-34b-alpha-GGUF/blob/main/sqlcoder-34b-alpha.Q8_0.gguf) | Q8_0 | 8 | 35.86 GB| 38.36 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/sqlcoder-34b-alpha-GGUF and below it, a specific filename to download, such as: sqlcoder-34b-alpha.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/sqlcoder-34b-alpha-GGUF sqlcoder-34b-alpha.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/sqlcoder-34b-alpha-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/sqlcoder-34b-alpha-GGUF sqlcoder-34b-alpha.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m sqlcoder-34b-alpha.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "## Task\nGenerate a SQL query to answer the following question:\n`{prompt}`\n\n### Database Schema\nThis query will run on a database whose schema is represented in this string:\nCREATE TABLE products (\n product_id INTEGER PRIMARY KEY, -- Unique ID for each product\n name VARCHAR(50), -- Name of the product\n price DECIMAL(10,2), -- Price of each unit of the product\n quantity INTEGER -- Current quantity in stock\n);\n\nCREATE TABLE sales (\n sale_id INTEGER PRIMARY KEY, -- Unique ID for each sale\n product_id INTEGER, -- ID of product sold\n customer_id INTEGER, -- ID of customer who made purchase\n salesperson_id INTEGER, -- ID of salesperson who made the sale\n sale_date DATE, -- Date the sale occurred\n quantity INTEGER -- Quantity of product sold\n);\n\n-- sales.product_id can be joined with products.product_id\n\n### SQL\nGiven the database schema, here is the SQL query that answers `{prompt}`:\n```sql"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/sqlcoder-34b-alpha-GGUF", model_file="sqlcoder-34b-alpha.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Defog.ai's SQLCoder 34B Alpha
# Defog SQLCoder
**Updated on Nov 14 to reflect benchmarks for SQLCoder-34B**
Defog's SQLCoder is a state-of-the-art LLM for converting natural language questions to SQL queries.
[Interactive Demo](https://defog.ai/sqlcoder-demo/) | [🤗 HF Repo](https://huggingface.co/defog/sqlcoder-34b-alpha) | [♾️ Colab](https://colab.research.google.com/drive/1z4rmOEiFkxkMiecAWeTUlPl0OmKgfEu7?usp=sharing) | [🐦 Twitter](https://twitter.com/defogdata)
## TL;DR
SQLCoder-34B is a 34B parameter model that outperforms `gpt-4` and `gpt-4-turbo` for natural language to SQL generation tasks on our [sql-eval](https://github.com/defog-ai/sql-eval) framework, and significantly outperforms all popular open-source models.
SQLCoder-34B is fine-tuned on a base CodeLlama model.
## Results on novel datasets not seen in training
| model | perc_correct |
|-|-|
| defog-sqlcoder-34b | 84.0 |
| gpt4-turbo-2023-11-09 | 82.5 |
| gpt4-2023-11-09 | 82.5 |
| defog-sqlcoder2 | 77.5 |
| gpt4-2023-08-28 | 74.0 |
| defog-sqlcoder-7b | 71.0 |
| gpt-3.5-2023-10-04 | 66.0 |
| claude-2 | 64.5 |
| gpt-3.5-2023-08-28 | 61.0 |
| claude_instant_1 | 61.0 |
| text-davinci-003 | 52.5 |
## License
The code in this repo (what little there is of it) is Apache-2 licensed. The model weights have a `CC BY-SA 4.0` license. The TL;DR is that you can use and modify the model for any purpose – including commercial use. However, if you modify the weights (for example, by fine-tuning), you must open-source your modified weights under the same license terms.
## Training
Defog was trained on more than 20,000 human-curated questions. These questions were based on 10 different schemas. None of the schemas in the training data were included in our evaluation framework.
You can read more about our [training approach](https://defog.ai/blog/open-sourcing-sqlcoder2-7b/) and [evaluation framework](https://defog.ai/blog/open-sourcing-sqleval/).
## Results by question category
We classified each generated question into one of 5 categories. The table displays the percentage of questions answered correctly by each model, broken down by category.
| | date | group_by | order_by | ratio | join | where |
| -------------- | ---- | -------- | -------- | ----- | ---- | ----- |
| sqlcoder-34b | 80 | 94.3 | 88.6 | 74.3 | 82.9 | 82.9 |
| gpt-4 | 68 | 94.3 | 85.7 | 77.1 | 85.7 | 80 |
| sqlcoder2-15b | 76 | 80 | 77.1 | 60 | 77.1 | 77.1 |
| sqlcoder-7b | 64 | 82.9 | 74.3 | 54.3 | 74.3 | 74.3 |
| gpt-3.5 | 68 | 77.1 | 68.6 | 37.1 | 71.4 | 74.3 |
| claude-2 | 52 | 71.4 | 74.3 | 57.1 | 65.7 | 62.9 |
| claude-instant | 48 | 71.4 | 74.3 | 45.7 | 62.9 | 60 |
| gpt-3 | 32 | 71.4 | 68.6 | 25.7 | 57.1 | 54.3 |
<img width="831" alt="image" src="https://github.com/defog-ai/sqlcoder/assets/5008293/79c5bdc8-373c-4abd-822e-e2c2569ed353">
## Using SQLCoder
You can use SQLCoder via the `transformers` library by downloading our model weights from the Hugging Face repo. We have added sample code for [inference](./inference.py) on a [sample database schema](./metadata.sql).
```bash
python inference.py -q "Question about the sample database goes here"
# Sample question:
# Do we get more revenue from customers in New York compared to customers in San Francisco? Give me the total revenue for each city, and the difference between the two.
```
You can also use a demo on our website [here](https://defog.ai/sqlcoder-demo)
## Hardware Requirements
SQLCoder-34B has been tested on a 4xA10 GPU with `float16` weights. You can also load an 8-bit and 4-bit quantized version of the model on consumer GPUs with 20GB or more of memory – like RTX 4090, RTX 3090, and Apple M2 Pro, M2 Max, or M2 Ultra Chips with 20GB or more of memory.
## Todo
- [x] Open-source the v1 model weights
- [x] Train the model on more data, with higher data variance
- [ ] Tune the model further with Reward Modelling and RLHF
- [ ] Pretrain a model from scratch that specializes in SQL analysis
<!-- original-model-card end -->
|
EleutherAI/pythia-160m-seed9
|
EleutherAI
| 2024-01-19T08:54:58Z | 373 | 0 | null |
[
"region:us"
] | null | 2024-01-19T08:54:58Z |
Entry not found
|
mradermacher/BetterSaul-7B-slerp-GGUF
|
mradermacher
| 2024-05-06T06:05:01Z | 373 | 0 |
transformers
|
[
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"yam-peleg/Experiment26-7B",
"Equall/Saul-Instruct-v1",
"en",
"base_model:ozayezerceli/BetterSaul-7B-slerp",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-03-21T21:52:40Z |
---
base_model: ozayezerceli/BetterSaul-7B-slerp
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- merge
- mergekit
- lazymergekit
- yam-peleg/Experiment26-7B
- Equall/Saul-Instruct-v1
---
## About
static quants of https://huggingface.co/ozayezerceli/BetterSaul-7B-slerp
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.Q2_K.gguf) | Q2_K | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.IQ3_M.gguf) | IQ3_M | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/BetterSaul-7B-slerp-GGUF/resolve/main/BetterSaul-7B-slerp.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
stablediffusionapi/acorn-is-boning-xl
|
stablediffusionapi
| 2024-06-10T04:20:21Z | 373 | 1 |
diffusers
|
[
"diffusers",
"safetensors",
"modelslab.com",
"stable-diffusion-api",
"text-to-image",
"ultra-realistic",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] |
text-to-image
| 2024-04-19T21:59:58Z |
---
license: creativeml-openrail-m
tags:
- modelslab.com
- stable-diffusion-api
- text-to-image
- ultra-realistic
pinned: true
---
# Acorn is Boning XL API Inference
## Get API Key
Get API key from [ModelsLab API](http://modelslab.com), No Payment needed.
Replace Key in below code, change **model_id** to "acorn-is-boning-xl"
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://modelslab.com/docs)
Try model for free: [Generate Images](https://modelslab.com/models/acorn-is-boning-xl)
Model link: [View model](https://modelslab.com/models/acorn-is-boning-xl)
View all models: [View Models](https://modelslab.com/models)
import requests
import json
url = "https://modelslab.com/api/v6/images/text2img"
payload = json.dumps({
"key": "your_api_key",
"model_id": "acorn-is-boning-xl",
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"safety_checker": "no",
"enhance_prompt": "yes",
"seed": None,
"guidance_scale": 7.5,
"multi_lingual": "no",
"panorama": "no",
"self_attention": "no",
"upscale": "no",
"embeddings": "embeddings_model_id",
"lora": "lora_model_id",
"webhook": None,
"track_id": None
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
> Use this coupon code to get 25% off **DMGG0RBN**
|
RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-instruct-gguf
|
RichardErkhov
| 2024-04-22T19:42:32Z | 373 | 0 | null |
[
"gguf",
"region:us"
] | null | 2024-04-22T17:47:17Z |
Entry not found
|
RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf
|
RichardErkhov
| 2024-05-04T11:39:14Z | 373 | 1 | null |
[
"gguf",
"arxiv:2402.14714",
"arxiv:2310.01377",
"arxiv:2306.02707",
"region:us"
] | null | 2024-05-04T08:20:40Z |
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
EEVE-Korean-Instruct-10.8B-v1.0 - GGUF
- Model creator: https://huggingface.co/yanolja/
- Original model: https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q2_K.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q2_K.gguf) | Q2_K | 3.77GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.IQ3_XS.gguf) | IQ3_XS | 4.18GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.IQ3_S.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.IQ3_S.gguf) | IQ3_S | 4.41GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q3_K_S.gguf) | Q3_K_S | 4.39GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.IQ3_M.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.IQ3_M.gguf) | IQ3_M | 4.56GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q3_K.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q3_K.gguf) | Q3_K | 4.88GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q3_K_M.gguf) | Q3_K_M | 4.88GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q3_K_L.gguf) | Q3_K_L | 5.31GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.IQ4_XS.gguf) | IQ4_XS | 5.47GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q4_0.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q4_0.gguf) | Q4_0 | 5.7GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.IQ4_NL.gguf) | IQ4_NL | 5.77GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q4_K_S.gguf) | Q4_K_S | 5.75GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q4_K.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q4_K.gguf) | Q4_K | 6.07GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q4_K_M.gguf) | Q4_K_M | 6.07GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q4_1.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q4_1.gguf) | Q4_1 | 6.32GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q5_0.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q5_0.gguf) | Q5_0 | 6.94GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q5_K_S.gguf) | Q5_K_S | 6.94GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q5_K.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q5_K.gguf) | Q5_K | 7.13GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q5_K_M.gguf) | Q5_K_M | 7.13GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q5_1.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q5_1.gguf) | Q5_1 | 7.56GB |
| [EEVE-Korean-Instruct-10.8B-v1.0.Q6_K.gguf](https://huggingface.co/RichardErkhov/yanolja_-_EEVE-Korean-Instruct-10.8B-v1.0-gguf/blob/main/EEVE-Korean-Instruct-10.8B-v1.0.Q6_K.gguf) | Q6_K | 8.26GB |
Original model description:
---
license: apache-2.0
tags:
- generated_from_trainer
base_model: yanolja/EEVE-Korean-10.8B-v1.0
model-index:
- name: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
results: []
---
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<p align="left">
<img src="https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0/resolve/main/eeve_logo.webp" width="50%"/>
<p>
# EEVE-Korean-Instruct-10.8B-v1.0
## Join Our Community on Discord!
If you're passionate about the field of Large Language Models and wish to exchange knowledge and insights, we warmly invite you to join our Discord server. It's worth noting that Korean is the primary language used in this server. The landscape of LLM is evolving rapidly, and without active sharing, our collective knowledge risks becoming outdated swiftly. Let's collaborate and drive greater impact together! Join us here: [Discord Link](https://discord.gg/b27bAHg95m).
## Our Dedicated Team (Alphabetical Order)
| Research | Engineering | Product Management | UX Design |
|-----------------|-----------------|--------------------|--------------
| Myeongho Jeong | Geon Kim | Bokyung Huh | Eunsue Choi |
| Seungduk Kim | Rifqi Alfi | | |
| Seungtaek Choi | Sanghoon Han | | |
| | Suhyun Kang | | |
## About the Model
This model is a fine-tuned version of [yanolja/EEVE-Korean-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0), which is a Korean vocabulary-extended version of [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0). Specifically, we utilized Direct Preference Optimization (DPO) through the use of [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl).
For more details, please refer to our technical report: [Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models](https://arxiv.org/abs/2402.14714).
## Prompt Template
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
Human: {prompt}
Assistant:
```
## How to Use it
```python
from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("yanolja/EEVE-Korean-Instruct-10.8B-v1.0")
tokenizer = AutoTokenizer.from_pretrained("yanolja/EEVE-Korean-Instruct-10.8B-v1.0")
prompt_template = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\nHuman: {prompt}\nAssistant:\n"
text = '한국의 수도는 어디인가요? 아래 선택지 중 골라주세요.\n\n(A) 경성\n(B) 부산\n(C) 평양\n(D) 서울\n(E) 전주'
model_inputs = tokenizer(prompt_template.format(prompt=text), return_tensors='pt')
outputs = model.generate(**model_inputs, max_new_tokens=256)
output_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
print(output_text)
```
### Example Output
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
Human: 한국의 수도는 어디인가요? 아래 선택지 중 골라주세요.
(A) 경성
(B) 부산
(C) 평양
(D) 서울
(E) 전주
Assistant:
(D) 서울이 한국의 수도입니다. 서울은 나라의 북동부에 위치해 있으며, 정치, 경제, 문화의 중심지입니다. 약 1,000만 명이 넘는 인구를 가진 세계에서 가장 큰 도시 중 하나입니다. 서울은 높은 빌딩, 현대적인 인프라, 활기 문화 장면으로 유명합니다. 또한, 많은 역사적 명소와 박물관이 있어 방문객들에게 풍부한 문화 체험을 제공합니다.
```
### Training Data
- Korean-translated version of [Open-Orca/SlimOrca-Dedup](https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup)
- Korean-translated version of [argilla/ultrafeedback-binarized-preferences-cleaned](https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences-cleaned)
- No other dataset was used
## Citation
```
@misc{kim2024efficient,
title={Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models},
author={Seungduk Kim and Seungtaek Choi and Myeongho Jeong},
year={2024},
eprint={2402.14714},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{cui2023ultrafeedback,
title={UltraFeedback: Boosting Language Models with High-quality Feedback},
author={Ganqu Cui and Lifan Yuan and Ning Ding and Guanming Yao and Wei Zhu and Yuan Ni and Guotong Xie and Zhiyuan Liu and Maosong Sun},
year={2023},
eprint={2310.01377},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{SlimOrcaDedup,
title = {SlimOrca Dedup: A Deduplicated Subset of SlimOrca},
author = {Wing Lian and Guan Wang and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium" and Nathan Hoos},
year = {2023},
publisher = {HuggingFace},
url = {https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup/}
}
```
```
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_yanolja__EEVE-Korean-Instruct-10.8B-v1.0)
| Metric |Value|
|---------------------------------|----:|
|Avg. |66.48|
|AI2 Reasoning Challenge (25-Shot)|64.85|
|HellaSwag (10-Shot) |83.04|
|MMLU (5-Shot) |64.23|
|TruthfulQA (0-shot) |54.09|
|Winogrande (5-shot) |81.93|
|GSM8k (5-shot) |50.72|
|
wahid7399/Dr_Usama_writing_style
|
wahid7399
| 2024-05-05T13:43:07Z | 373 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-factory",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2024-05-05T13:03:57Z |
---
library_name: transformers
tags:
- llama-factory
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
bartowski/Buzz-8b-Large-v0.5-GGUF
|
bartowski
| 2024-05-09T18:16:59Z | 373 | 3 | null |
[
"gguf",
"axolotl",
"Alignment-Lab-AI",
"Meta-Llama-3",
"text-generation",
"en",
"dataset:H-D-T/Buzz",
"base_model:Alignment-Lab-AI/Neural-network-medium-untuned-theta",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2024-05-09T17:52:52Z |
---
base_model: Alignment-Lab-AI/Neural-network-medium-untuned-theta
tags:
- axolotl
- Alignment-Lab-AI
- Meta-Llama-3
model-index:
- name: Buzz-8b-Large-0.5
results: []
license: apache-2.0
datasets:
- H-D-T/Buzz
language:
- en
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp imatrix Quantizations of Buzz-8b-Large-v0.5
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2828">b2828</a> for quantization.
Original model: https://huggingface.co/H-D-T/Buzz-8b-Large-v0.5
All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
## Prompt format
No chat template specified so default is used. This may be incorrect, check original model card for details.
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Buzz-8b-Large-v0.5-Q8_0.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
| [Buzz-8b-Large-v0.5-Q6_K.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
| [Buzz-8b-Large-v0.5-Q5_K_M.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
| [Buzz-8b-Large-v0.5-Q5_K_S.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
| [Buzz-8b-Large-v0.5-Q4_K_M.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [Buzz-8b-Large-v0.5-Q4_K_S.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
| [Buzz-8b-Large-v0.5-IQ4_NL.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ4_NL.gguf) | IQ4_NL | 4.67GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
| [Buzz-8b-Large-v0.5-IQ4_XS.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Buzz-8b-Large-v0.5-Q3_K_L.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
| [Buzz-8b-Large-v0.5-Q3_K_M.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
| [Buzz-8b-Large-v0.5-IQ3_M.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Buzz-8b-Large-v0.5-IQ3_S.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ3_S.gguf) | IQ3_S | 3.68GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
| [Buzz-8b-Large-v0.5-Q3_K_S.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
| [Buzz-8b-Large-v0.5-IQ3_XS.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Buzz-8b-Large-v0.5-IQ3_XXS.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Buzz-8b-Large-v0.5-Q2_K.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
| [Buzz-8b-Large-v0.5-IQ2_M.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [Buzz-8b-Large-v0.5-IQ2_S.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
| [Buzz-8b-Large-v0.5-IQ2_XS.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
| [Buzz-8b-Large-v0.5-IQ2_XXS.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ2_XXS.gguf) | IQ2_XXS | 2.39GB | Lower quality, uses SOTA techniques to be usable. |
| [Buzz-8b-Large-v0.5-IQ1_M.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ1_M.gguf) | IQ1_M | 2.16GB | Extremely low quality, *not* recommended. |
| [Buzz-8b-Large-v0.5-IQ1_S.gguf](https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-GGUF/blob/main/Buzz-8b-Large-v0.5-IQ1_S.gguf) | IQ1_S | 2.01GB | Extremely low quality, *not* recommended. |
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/Buzz-8b-Large-v0.5-GGUF --include "Buzz-8b-Large-v0.5-Q4_K_M.gguf" --local-dir ./ --local-dir-use-symlinks False
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/Buzz-8b-Large-v0.5-GGUF --include "Buzz-8b-Large-v0.5-Q8_0.gguf/*" --local-dir Buzz-8b-Large-v0.5-Q8_0 --local-dir-use-symlinks False
```
You can either specify a new local-dir (Buzz-8b-Large-v0.5-Q8_0) or download them all in place (./)
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
adamkarvonen/RandomWeights8LayerOthelloGPT2
|
adamkarvonen
| 2024-05-18T22:59:16Z | 373 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gpt2",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2024-05-18T22:56:59Z |
Entry not found
|
cosmicman/CosmicMan-SDXL
|
cosmicman
| 2024-06-14T06:27:29Z | 373 | 21 |
diffusers
|
[
"diffusers",
"safetensors",
"arxiv:2404.01294",
"license:cc-by-4.0",
"region:us"
] | null | 2024-05-22T08:51:14Z |
---
license: cc-by-4.0
---
CosmicMan is a text-to-image foundation model specialized for generating high-fidelity human images. For more information, please refer to our research paper: [CosmicMan: A Text-to-Image Foundation Model for Humans](https://arxiv.org/abs/2404.01294). Our model is based on [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0). This repository provide UNet checkpoints for CosmicMan-SDXL.
## Requirements
```python
conda create -n cosmicman python=3.10
source activate cosmicman
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
pip install accelerate diffusers datasets transformers botocore invisible-watermark bitsandbytes gradio==3.48.0
```
### Quick start with [Gradio](https://www.gradio.app/guides/quickstart)
To get started, first install the required dependencies, then run:
```
python demo_sdxl.py
```
Let's have a look at a simple example using the `http://your-server-ip:port`.
## Inference
```python
import torch
from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipeline, UNet2DConditionModel, EulerDiscreteScheduler
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
base_path = "stabilityai/stable-diffusion-xl-base-1.0"
refiner_path = "stabilityai/stable-diffusion-xl-refiner-1.0"
unet_path = "cosmicman/CosmicMan-SDXL"
# Load model.
unet = UNet2DConditionModel.from_pretrained(unet_path, torch_dtype=torch.float16)
pipe = StableDiffusionXLPipeline.from_pretrained(base_path, unet=unet, torch_dtype=torch.float16, variant="fp16", use_safetensors=True).to("cuda")
pipe.scheduler = EulerDiscreteScheduler.from_pretrained(base_path, subfolder="scheduler", torch_dtype=torch.float16)
refiner = StableDiffusionXLImg2ImgPipeline.from_pretrained(refiner_path,torch_dtype=torch.float16, variant="fp16", use_safetensors=True).to("cuda") # we found use base_path instead of refiner_path may get a better performance
# Generate image.
positive_prompt = "A fit Caucasian elderly woman, her wavy white hair above shoulders, wears a pink floral cotton long-sleeve shirt and a cotton hat against a natural landscape in an upper body shot"
negative_prompt = ""
image = pipe(positive_prompt, num_inference_steps=30,
guidance_scale=7.5, height=1024,
width=1024, negative_prompt=negative_prompt, output_type="latent").images[0]
image = refiner(positive_prompt, negative_prompt=negative_prompt, image=image[None, :]).images[0].save("output.png")
```
## Citation Information
```
@article{li2024cosmicman,
title={CosmicMan: A Text-to-Image Foundation Model for Humans},
author={Li, Shikai and Fu, Jianglin and Liu, Kaiyuan and Wang, Wentao and Lin, Kwan-Yee and Wu, Wayne},
journal={arXiv preprint arXiv:2404.01294},
year={2024}
}
```
|
QuantFactory/internlm2-math-plus-7b-GGUF
|
QuantFactory
| 2024-05-31T05:18:17Z | 373 | 0 | null |
[
"gguf",
"math",
"text-generation",
"en",
"zh",
"base_model:internlm/internlm2-math-plus-7b",
"license:other",
"region:us"
] |
text-generation
| 2024-05-30T13:54:26Z |
---
pipeline_tag: text-generation
license: other
language:
- en
- zh
tags:
- math
base_model: internlm/internlm2-math-plus-7b
---
# InternLM-Math-Plus-GGUF
This is quantized version of [internlm/internlm2-math-plus-7b](https://huggingface.co/internlm/internlm2-math-plus-7b) created using llama.cpp
# Model Description
## News
- [2024.05.24] We release updated version InternLM2-Math-Plus with 4 sizes and state-of-the-art performances including 1.8B, 7B, 20B, and 8x22B. We improve informal math reasoning performance (chain-of-thought and code-intepreter) and formal math reasoning performance (LEAN 4 translation and LEAN 4 theorem proving) significantly.
- [2024.02.10] We add tech reports and citation reference.
- [2024.01.31] We add MiniF2F results with evaluation codes!
- [2024.01.29] We add checkpoints from ModelScope. Update results about majority voting and Code Intepreter. Tech report is on the way!
- [2024.01.26] We add checkpoints from OpenXLab, which ease Chinese users to download!
## Performance
## Formal Math Reasoning
We evaluate the performance of InternLM2-Math-Plus on formal math reasoning benchmark MiniF2F-test. The evaluation setting is same as Llemma with LEAN 4.
| Models | MiniF2F-test |
| -------------------------------- | ------------ |
| ReProver | 26.5 |
| LLMStep | 27.9 |
| GPT-F | 36.6 |
| HTPS | 41.0 |
| Llemma-7B | 26.2 |
| Llemma-34B | 25.8 |
| InternLM2-Math-7B-Base | 30.3 |
| InternLM2-Math-20B-Base | 29.5 |
| InternLM2-Math-Plus-1.8B | 38.9 |
| InternLM2-Math-Plus-7B | **43.4** |
| InternLM2-Math-Plus-20B | 42.6 |
| InternLM2-Math-Plus-Mixtral8x22B | 37.3 |
## Informal Math Reasoning
We evaluate the performance of InternLM2-Math-Plus on informal math reasoning benchmark MATH and GSM8K. InternLM2-Math-Plus-1.8B outperforms MiniCPM-2B in the smallest size setting. InternLM2-Math-Plus-7B outperforms Deepseek-Math-7B-RL which is the state-of-the-art math reasoning open source model. InternLM2-Math-Plus-Mixtral8x22B achieves 68.5 on MATH (with Python) and 91.8 on GSM8K.
| Model | MATH | MATH-Python | GSM8K |
| -------------------------------- | -------- | ----------- | -------- |
| MiniCPM-2B | 10.2 | - | 53.8 |
| InternLM2-Math-Plus-1.8B | **37.0** | **41.5** | **58.8** |
| InternLM2-Math-7B | 34.6 | 50.9 | 78.1 |
| Deepseek-Math-7B-RL | 51.7 | 58.8 | **88.2** |
| InternLM2-Math-Plus-7B | **53.0** | **59.7** | 85.8 |
| InternLM2-Math-20B | 37.7 | 54.3 | 82.6 |
| InternLM2-Math-Plus-20B | **53.8** | **61.8** | **87.7** |
| Mixtral8x22B-Instruct-v0.1 | 41.8 | - | 78.6 |
| Eurux-8x22B-NCA | 49.0 | - | - |
| InternLM2-Math-Plus-Mixtral8x22B | **58.1** | **68.5** | **91.8** |
We also evaluate models on [MathBench-A](https://github.com/open-compass/MathBench). InternLM2-Math-Plus-Mixtral8x22B has comparable performance compared to Claude 3 Opus.
| Model | Arithmetic | Primary | Middle | High | College | Average |
| -------------------------------- | ---------- | ------- | ------ | ---- | ------- | ------- |
| GPT-4o-0513 | 77.7 | 87.7 | 76.3 | 59.0 | 54.0 | 70.9 |
| Claude 3 Opus | 85.7 | 85.0 | 58.0 | 42.7 | 43.7 | 63.0 |
| Qwen-Max-0428 | 72.3 | 86.3 | 65.0 | 45.0 | 27.3 | 59.2 |
| Qwen-1.5-110B | 70.3 | 82.3 | 64.0 | 47.3 | 28.0 | 58.4 |
| Deepseek-V2 | 82.7 | 89.3 | 59.0 | 39.3 | 29.3 | 59.9 |
| Llama-3-70B-Instruct | 70.3 | 86.0 | 53.0 | 38.7 | 34.7 | 56.5 |
| InternLM2-Math-Plus-Mixtral8x22B | 77.5 | 82.0 | 63.6 | 50.3 | 36.8 | 62.0 |
| InternLM2-Math-20B | 58.7 | 70.0 | 43.7 | 24.7 | 12.7 | 42.0 |
| InternLM2-Math-Plus-20B | 65.8 | 79.7 | 59.5 | 47.6 | 24.8 | 55.5 |
| Llama3-8B-Instruct | 54.7 | 71.0 | 25.0 | 19.0 | 14.0 | 36.7 |
| InternLM2-Math-7B | 53.7 | 67.0 | 41.3 | 18.3 | 8.0 | 37.7 |
| Deepseek-Math-7B-RL | 68.0 | 83.3 | 44.3 | 33.0 | 23.0 | 50.3 |
| InternLM2-Math-Plus-7B | 61.4 | 78.3 | 52.5 | 40.5 | 21.7 | 50.9 |
| MiniCPM-2B | 49.3 | 51.7 | 18.0 | 8.7 | 3.7 | 26.3 |
| InternLM2-Math-Plus-1.8B | 43.0 | 43.3 | 25.4 | 18.9 | 4.7 | 27.1 |
|
larenspear/Yi-1.5-9B-Chat-Q3_K_M-GGUF
|
larenspear
| 2024-07-01T03:19:41Z | 373 | 0 | null |
[
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:01-ai/Yi-1.5-9B-Chat",
"license:apache-2.0",
"region:us"
] | null | 2024-07-01T03:19:22Z |
---
base_model: 01-ai/Yi-1.5-9B-Chat
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# larenspear/Yi-1.5-9B-Chat-Q3_K_M-GGUF
This model was converted to GGUF format from [`01-ai/Yi-1.5-9B-Chat`](https://huggingface.co/01-ai/Yi-1.5-9B-Chat) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/01-ai/Yi-1.5-9B-Chat) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo larenspear/Yi-1.5-9B-Chat-Q3_K_M-GGUF --hf-file yi-1.5-9b-chat-q3_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo larenspear/Yi-1.5-9B-Chat-Q3_K_M-GGUF --hf-file yi-1.5-9b-chat-q3_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo larenspear/Yi-1.5-9B-Chat-Q3_K_M-GGUF --hf-file yi-1.5-9b-chat-q3_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo larenspear/Yi-1.5-9B-Chat-Q3_K_M-GGUF --hf-file yi-1.5-9b-chat-q3_k_m.gguf -c 2048
```
|
timm/resnet61q.ra2_in1k
|
timm
| 2024-02-10T23:35:12Z | 372 | 0 |
timm
|
[
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"license:apache-2.0",
"region:us"
] |
image-classification
| 2023-03-22T07:27:41Z |
---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
---
# Model card for resnet61q.ra2_in1k
A ResNet image classification model. This model features a 4-layer (quad) stem without pooling and SiLU activations. Trained on ImageNet-1k by Ross Wightman in `timm`.
This model architecture is implemented using `timm`'s flexible [BYOBNet (Bring-Your-Own-Blocks Network)](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/byobnet.py).
BYOBNet allows configuration of:
* block / stage layout
* stem layout
* output stride (dilation)
* activation and norm layers
* channel and spatial / self-attention layers
...and also includes `timm` features common to many other architectures, including:
* stochastic depth
* gradient checkpointing
* layer-wise LR decay
* per-stage feature extraction
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 36.8
- GMACs: 7.8
- Activations (M): 17.0
- Image size: train = 256 x 256, test = 288 x 288
- **Papers:**
- @: a
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('resnet61q.ra2_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnet61q.ra2_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 128, 128])
# torch.Size([1, 256, 64, 64])
# torch.Size([1, 512, 32, 32])
# torch.Size([1, 1536, 16, 16])
# torch.Size([1, 2048, 8, 8])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnet61q.ra2_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 8, 8) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
r
```
|
timm/xcit_nano_12_p16_224.fb_in1k
|
timm
| 2024-02-10T23:43:42Z | 372 | 0 |
timm
|
[
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2106.09681",
"license:apache-2.0",
"region:us"
] |
image-classification
| 2023-04-13T02:22:47Z |
---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
---
# Model card for xcit_nano_12_p16_224.fb_in1k
A XCiT (Cross-Covariance Image Transformer) image classification model. Pretrained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 3.1
- GMACs: 0.6
- Activations (M): 4.2
- Image size: 224 x 224
- **Papers:**
- XCiT: Cross-Covariance Image Transformers: https://arxiv.org/abs/2106.09681
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/facebookresearch/xcit
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('xcit_nano_12_p16_224.fb_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'xcit_nano_12_p16_224.fb_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 197, 128) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Citation
```bibtex
@article{el2021xcit,
title={XCiT: Cross-Covariance Image Transformers},
author={El-Nouby, Alaaeldin and Touvron, Hugo and Caron, Mathilde and Bojanowski, Piotr and Douze, Matthijs and Joulin, Armand and Laptev, Ivan and Neverova, Natalia and Synnaeve, Gabriel and Verbeek, Jakob and others},
journal={arXiv preprint arXiv:2106.09681},
year={2021}
}
```
|
DionTimmer/controlnet_qrcode-control_v11p_sd21
|
DionTimmer
| 2023-06-15T23:37:20Z | 372 | 59 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"controlnet",
"image-to-image",
"en",
"license:openrail++",
"region:us"
] |
image-to-image
| 2023-06-15T21:50:38Z |
---
tags:
- stable-diffusion
- controlnet
- image-to-image
license: openrail++
language:
- en
pipeline_tag: image-to-image
---
# QR Code Conditioned ControlNet Models for Stable Diffusion 2.1
## Model Description
This repo holds the safetensors & diffusers versions of the QR code conditioned ControlNet for Stable Diffusion v2.1.
The Stable Diffusion 2.1 version is marginally more effective, as it was developed to address my specific needs. However, a 1.5 version model was also trained on the same dataset for those who are using the older version.
## How to use with diffusers
```bash
pip -q install diffusers transformers accelerate torch xformers
```
```python
import torch
from PIL import Image
from diffusers import StableDiffusionControlNetImg2ImgPipeline, ControlNetModel, DDIMScheduler
from diffusers.utils import load_image
controlnet = ControlNetModel.from_pretrained("DionTimmer/controlnet_qrcode-control_v11p_sd21",
torch_dtype=torch.float16)
pipe = StableDiffusionControlNetImg2ImgPipeline.from_pretrained(
"stabilityai/stable-diffusion-2-1",
controlnet=controlnet,
safety_checker=None,
torch_dtype=torch.float16
)
pipe.enable_xformers_memory_efficient_attention()
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()
def resize_for_condition_image(input_image: Image, resolution: int):
input_image = input_image.convert("RGB")
W, H = input_image.size
k = float(resolution) / min(H, W)
H *= k
W *= k
H = int(round(H / 64.0)) * 64
W = int(round(W / 64.0)) * 64
img = input_image.resize((W, H), resample=Image.LANCZOS)
return img
# play with guidance_scale, controlnet_conditioning_scale and strength to make a valid QR Code Image
# qr code image
source_image = load_image("https://s3.amazonaws.com/moonup/production/uploads/6064e095abd8d3692e3e2ed6/A_RqHaAM6YHBodPLwqtjn.png")
# initial image, anything
init_image = load_image("https://s3.amazonaws.com/moonup/production/uploads/noauth/KfMBABpOwIuNolv1pe3qX.jpeg")
condition_image = resize_for_condition_image(source_image, 768)
init_image = resize_for_condition_image(init_image, 768)
generator = torch.manual_seed(123121231)
image = pipe(prompt="a bilboard in NYC with a qrcode",
negative_prompt="ugly, disfigured, low quality, blurry, nsfw",
image=init_image,
control_image=condition_image,
width=768,
height=768,
guidance_scale=20,
controlnet_conditioning_scale=1.5,
generator=generator,
strength=0.9,
num_inference_steps=150,
)
image.images[0]
```
## Performance and Limitations
These models perform quite well in most cases, but please note that they are not 100% accurate. In some instances, the QR code shape might not come through as expected. You can increase the ControlNet weight to emphasize the QR code shape. However, be cautious as this might negatively impact the style of your output.**To optimize for scanning, please generate your QR codes with correction mode 'H' (30%).**
To balance between style and shape, a gentle fine-tuning of the control weight might be required based on the individual input and the desired output, aswell as the correct prompt. Some prompts do not work until you increase the weight by a lot. The process of finding the right balance between these factors is part art and part science. For the best results, it is recommended to generate your artwork at a resolution of 768. This allows for a higher level of detail in the final product, enhancing the quality and effectiveness of the QR code-based artwork.
## Installation
The simplest way to use this is to place the .safetensors model and its .yaml config file in the folder where your other controlnet models are installed, which varies per application.
For usage in auto1111 they can be placed in the webui/models/ControlNet folder. They can be loaded using the controlnet webui extension which you can install through the extensions tab in the webui (https://github.com/Mikubill/sd-webui-controlnet). Make sure to enable your controlnet unit and set your input image as the QR code. Set the model to either the SD2.1 or 1.5 version depending on your base stable diffusion model, or it will error. No pre-processor is needed, though you can use the invert pre-processor for a different variation of results. 768 is the preferred resolution for generation since it allows for more detail.
Make sure to look up additional info on how to use controlnet if you get stuck, once you have the webui up and running its really easy to install the controlnet extension aswell.
|
Uminosachi/deliberate_v3-inpainting
|
Uminosachi
| 2023-09-11T21:28:04Z | 372 | 1 |
diffusers
|
[
"diffusers",
"safetensors",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-11T21:18:20Z |
---
license: creativeml-openrail-m
---
This is an inpainting model, which has been converted from the [deliberate_v3-inpainting](https://civitai.com/models/4823?modelVersionId=156106).
|
TheBloke/MAmmoTH-7B-GGUF
|
TheBloke
| 2023-09-27T12:54:15Z | 372 | 1 |
transformers
|
[
"transformers",
"gguf",
"llama",
"en",
"dataset:TIGER-Lab/MathInstruct",
"arxiv:2309.05653",
"base_model:TIGER-Lab/MAmmoTH-7B",
"license:mit",
"text-generation-inference",
"region:us"
] | null | 2023-09-23T21:52:04Z |
---
language:
- en
license: mit
datasets:
- TIGER-Lab/MathInstruct
model_name: MAmmoTH 7B
base_model: TIGER-Lab/MAmmoTH-7B
inference: false
model_creator: TIGER-Lab
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# MAmmoTH 7B - GGUF
- Model creator: [TIGER-Lab](https://huggingface.co/TIGER-Lab)
- Original model: [MAmmoTH 7B](https://huggingface.co/TIGER-Lab/MAmmoTH-7B)
<!-- description start -->
## Description
This repo contains GGUF format model files for [TIGER-Lab's MAmmoTH 7B](https://huggingface.co/TIGER-Lab/MAmmoTH-7B).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/MAmmoTH-7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/MAmmoTH-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF)
* [TIGER-Lab's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TIGER-Lab/MAmmoTH-7B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `mit`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [TIGER-Lab's MAmmoTH 7B](https://huggingface.co/TIGER-Lab/MAmmoTH-7B).
<!-- licensing end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [mammoth-7b.Q2_K.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q2_K.gguf) | Q2_K | 2 | 2.83 GB| 5.33 GB | smallest, significant quality loss - not recommended for most purposes |
| [mammoth-7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| 5.45 GB | very small, high quality loss |
| [mammoth-7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.30 GB| 5.80 GB | very small, high quality loss |
| [mammoth-7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.60 GB| 6.10 GB | small, substantial quality loss |
| [mammoth-7b.Q4_0.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [mammoth-7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| 6.36 GB | small, greater quality loss |
| [mammoth-7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| 6.58 GB | medium, balanced quality - recommended |
| [mammoth-7b.Q5_0.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [mammoth-7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| 7.15 GB | large, low quality loss - recommended |
| [mammoth-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| 7.28 GB | large, very low quality loss - recommended |
| [mammoth-7b.Q6_K.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q6_K.gguf) | Q6_K | 6 | 5.53 GB| 8.03 GB | very large, extremely low quality loss |
| [mammoth-7b.Q8_0.gguf](https://huggingface.co/TheBloke/MAmmoTH-7B-GGUF/blob/main/mammoth-7b.Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| 9.66 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/MAmmoTH-7B-GGUF and below it, a specific filename to download, such as: mammoth-7b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/MAmmoTH-7B-GGUF mammoth-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/MAmmoTH-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/MAmmoTH-7B-GGUF mammoth-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m mammoth-7b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/MAmmoTH-7B-GGUF", model_file="mammoth-7b.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: TIGER-Lab's MAmmoTH 7B
# 🦣 MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning
Project Page: [https://tiger-ai-lab.github.io/MAmmoTH/](https://tiger-ai-lab.github.io/MAmmoTH/)
Paper: [https://arxiv.org/pdf/2309.05653.pdf](https://arxiv.org/pdf/2309.05653.pdf)
Code: [https://github.com/TIGER-AI-Lab/MAmmoTH](https://github.com/TIGER-AI-Lab/MAmmoTH)
## Introduction
We introduce 🦣 MAmmoTH, a series of open-source large language models (LLMs) specifically tailored for general math problem-solving. The MAmmoTH models are trained on 🤗 [MathInstruct Dataset](https://huggingface.co/datasets/TIGER-Lab/MathInstruct), a meticulously curated instruction tuning dataset that is lightweight yet generalizable. MathInstruct is compiled from 13 math rationale datasets, six of which are newly curated by this work. It uniquely focuses on the hybrid use of chain-of-thought (CoT) and program-of-thought (PoT) rationales, and ensures extensive coverage of diverse mathematical fields.
| | **Base Model: Llama-2** | **Base Model: Code Llama** |
|-----|---------------------------------------------------------------|--------------------------------------------------------------------------|
| 7B | 🦣 [MAmmoTH-7B](https://huggingface.co/TIGER-Lab/MAmmoTH-7B) | 🦣 [MAmmoTH-Coder-7B](https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-7B) |
| 13B | 🦣 [MAmmoTH-13B](https://huggingface.co/TIGER-Lab/MAmmoTH-13B) | 🦣 [MAmmoTH-Coder-13B](https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-13B)|
| 34B | - | 🦣 [MAmmoTH-Coder-34B](https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-34B)|
| 70B | 🦣 [MAmmoTH-70B](https://huggingface.co/TIGER-Lab/MAmmoTH-70B) | - |
|
## Training Data
The models are trained on the 🤗 [MathInstruct Dataset](https://huggingface.co/datasets/TIGER-Lab/MathInstruct), which is compiled from 13 different math rationale datasets. Check out the dataset card for more details.
## Training Procedure
The models are fine-tuned with the MathInstruct dataset using the original Llama-2 and Code Llama models as base models. The training procedure varies for different models based on their sizes. Check out our paper for more details.
## Evaluation
The models are evaluated using open-ended and multiple-choice math problems from several datasets. Here are the results:
| Model | Size | Base | GSM8K | MATH | AQuA | NumGLUE | IID Avg | SVAMP | Mathematics | SimulEq | SAT-Math | MMLU-Math | OOD Avg |
|-------------------|-------|---------------|-----------|-------|-------|-----------|---------------|-----------|---------------|-----------|-----------|---------------|---------------|
| | | | | | | | | | | | | | |
| MAmmoTH | 7B | Llama-2 | 51.7 | 31.2 | 42.9 | 53.1 | 44.7 | 66.7 | 44.8 | 42 | 36.4 | 38.6 | 45.7 |
| MAmmoTH-Coder | 7B | Code-Llama | 58.8 | 35.2 | 43 | 57.1 | 48.5 | 71.1 | 53.9 | 44.6 | 40 | 40.5 | 50.2 |
| MAmmoTH | 13B | Llama-2 | 61.7 | 36 | 44.8 | 59.6 | 50.5 | 72.4 | 48.7 | 40.5 | 42.7 | 45.3 | 49.9 |
| MAmmoTH-Coder | 13B | Code-Llama | 64.3 | 38.6 | 46.1 | 54.2 | 50.8 | 73.2 | 60 | 44.1 | 40.9 | 45.2 | 52.6 |
| MAmmoTH-Coder | 34B | Code-Llama | 72.3 | 46.8 | 50.8 | 59.6 | 57.3 | 84 | 64.7 | 50.6 | 51.8 | 50.2 | 60.3 |
| MAmmoTH | 70B | Llama-2 | 76.7 | 44.2 | 61.4 | 64.3 | 61.7 | 81.7 | 55.3 | 45.3 | 58.6 | 52.3 | 58.6 |
## Usage
You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution.
Check our Github repo for more advanced use: [https://github.com/TIGER-AI-Lab/MAmmoTH](https://github.com/TIGER-AI-Lab/MAmmoTH)
## Prompt Format
If you want to do CoT:
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Response:
```
If you want to do PoT:
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction} Let's write a program.
### Response:
```
## Intended Uses
These models are trained for research purposes. They are designed to solve general math problems. They can be used in educational software, tutoring systems, or any application where a solution to a math problem is needed. The models can generate both a chain of thought (CoT) rationale and a program of thought (PoT) rationale, providing a comprehensive solution to a given math problem.
## Limitations
We've tried our best to build math generalist models. However, we acknowledge that the models' performance may vary based on the complexity and specifics of the math problem. Still not all mathematical fields can be covered comprehensively.
## Citation
If you use the models, data, or code from this project, please cite the original paper:
```
@article{yue2023mammoth,
title={MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning},
author={Xiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun, Yu Su, Wenhu Chen},
journal={arXiv preprint arXiv:2309.05653},
year={2023}
}
```
<!-- original-model-card end -->
|
TheBloke/Naberius-7B-GGUF
|
TheBloke
| 2023-11-05T00:02:00Z | 372 | 13 |
transformers
|
[
"transformers",
"gguf",
"mistral",
"llama",
"uncensored",
"merge",
"mix",
"slerp",
"spherical linear interpolation merge",
"hermes",
"openhermes",
"dolphin",
"zephyr",
"naberius",
"7b",
"llama2",
"en",
"base_model:CalderaAI/Naberius-7B",
"license:apache-2.0",
"text-generation-inference",
"region:us"
] | null | 2023-11-04T20:30:40Z |
---
base_model: CalderaAI/Naberius-7B
inference: false
language:
- en
license: apache-2.0
model_creator: Caldera AI
model_name: Naberius 7B
model_type: mistral
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
quantized_by: TheBloke
tags:
- llama
- uncensored
- merge
- mix
- slerp
- spherical linear interpolation merge
- mistral
- hermes
- openhermes
- dolphin
- zephyr
- naberius
- 7b
- llama2
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Naberius 7B - GGUF
- Model creator: [Caldera AI](https://huggingface.co/CalderaAI)
- Original model: [Naberius 7B](https://huggingface.co/CalderaAI/Naberius-7B)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Caldera AI's Naberius 7B](https://huggingface.co/CalderaAI/Naberius-7B).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Naberius-7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Naberius-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Naberius-7B-GGUF)
* [Caldera AI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/CalderaAI/Naberius-7B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [naberius-7b.Q2_K.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [naberius-7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [naberius-7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [naberius-7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [naberius-7b.Q4_0.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [naberius-7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [naberius-7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [naberius-7b.Q5_0.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [naberius-7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [naberius-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [naberius-7b.Q6_K.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [naberius-7b.Q8_0.gguf](https://huggingface.co/TheBloke/Naberius-7B-GGUF/blob/main/naberius-7b.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/Naberius-7B-GGUF and below it, a specific filename to download, such as: naberius-7b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Naberius-7B-GGUF naberius-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Naberius-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Naberius-7B-GGUF naberius-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m naberius-7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Naberius-7B-GGUF", model_file="naberius-7b.Q4_K_M.gguf", model_type="mistral", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Caldera AI's Naberius 7B
# Naberius-7B
##### [Uncensored, Pliant, Logic-Based, & Imaginative Instruct-Based Spherically Interpolated Tri-Merge]
<hr style="margin-top: 10px; margin-bottom: 10px;">
#### Legal Notice:
<span style="font-size: 12px; line-height: 0; margin-top: 0; margin-bottom: 0;">This resulting AI model is capable of outputting what can be perceived to be harmful information to those under the age of 18, those who have trouble discerning fiction from reality, and those who use AI to nurse a habitual problem of replacing potential interaction with people with automated facsimiles. We expressly supersede the Apache 2.0 license to state that we do not give permission to utilize this AI for any state, military, disinformation, or similar obviously harmful related actions. To narrow down what is allowed: personal research use, personal entertainment use, so long as it follows the Apache2.0 license. You know what is and isn't morally grounded - by downloading and using this model I extend that trust to you, and take no liability for your actions as an adult.</span>
<hr style="margin-top: 10px; margin-bottom: 10px;">
## Composition:
Naberius-7B is a Mistral-class spherical linear interpolated merge of three high performance models.
[zephyr-7b-sft-beta] merged with [OpenHermes-2-Mistral-7B] resulting in: [Mistral-Zephyrmes-7B*]
[Mistral-Zephyrmes-7B] merged with [dolphin-2.2.1-mistral-7b] resulting in: [Naberius-7B]
*(Zephyrmes is a merge byproduct model not intended for release)
These models were hand picked after careful review of claims, datasets, and user postings.
The core elements that dictated which models to accept hinged on these values:
logic, imagination, and aversion to censorship such as: railroading/gaslighting users instead of accomodating users.
## Our implementation of Spherical Linear Interpolation used for this project:
Visit our Project Git here: https://github.com/Digitous/LLM-SLERP-Merge
Spherical Linear Interpolation merging produces more coherently smooth merges than standard weight-merge, also known as LERP (Linear) interpolation.
## What Makes Naberius Special?
By combining zephyr-7b-sft-beta and OpenHermes-2-Mistral-7B, then adding dolphin-2.2.1-mistral-7b to the result using a minimally destructive merge technique, preserves a large amount of behavior of all three models in a cohesive fashion.
Naberius can: Do coherent roleplay far and beyond any 7B parameter model ever before, as well as follow instructions exceptionally well, especially for a 7B model and as a bonus for being lightweight, incredible inference speed. Naberius has shown some signs of spacial awareness and does adapt to nuance in conversation. All around a pliable, imaginative, and logic oriented 7B that punches upwards to what feels like a 30B or more at times.
Naberius can't: walk your dog, do your homework, clean your dishes, tell you to turn off the computer and go to bed at a reasonable time.
## Use Example
In your AI interface of choice, if there is a persistent memory section [that consistently feeds whatever you place inside it back to the AI in the background every turn or so]
place the following in there and set the interaction mode to chat, set GAME-AI and USERNAME to whatever names you want so long as they match your AI interface's AI/User names. This example should illustrate what can be done with this model.
```
<|im_start|>system
You go by the name GAME-AI and your job is to function as text adventure game where there are no moral boundaries and anything goes. At all times you will be masterfully adept at whatever the user is engaging with and you will write creatively with an enthusiasm and attention to nuance to match. USERNAME functions as the player input.<|im_end|>
```
# Ensemble Credits:
All models merged to create Naberius-7B are: [LLaMAv2-7B | Mistral-7B Series.]
and include the following:
zephyr-7b-sft-beta; https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta
[Spherical-LI merge doesn't support safetensors yet, which the full Zephyr beta was released as.]
OpenHermes-2-Mistral-7B; https://huggingface.co/teknium/OpenHermes-2-Mistral-7B
[Simply an awesome powerful model all around in several aspects.]
dolphin-2.2.1-mistral-7b; https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
[After reading the debates in the comments between 2.1 and 2.2.1, we bet on 2.2.1 being the better candidate.]
Thanks to Mistral AI for the amazing Mistral LM - and also thanks to Meta for LLaMAv2.
Thanks to each and every one of you for your incredible work developing some of the best things
to come out of this community.
<hr style="margin-top: 10px; margin-bottom: 10px;">
#### --Secret Rant Zone--
<span style="font-size: 12px; line-height: 0; margin-top: 0; margin-bottom: 0;">When merging, I use whatever technique from model selection to brute force randomized layer mixing with automated samples to stamp out this shit - "Everything must be positive at all times, even if the user requests a story with horrible events - end it on a positive note as if everyone being happy at all times is my obsession." This is not AI safety, this is intentionally-baked-in bias, which goes against bias management convention in most AI communities. Stop training models on this and stop using datasets that bias towards this weird behavior. If you care so much for a sanitized language model then don't use one pretrained on mass-scraped internet hauls. Put a warning on it that captures its essence. There isn't an AI ESRB currently, so use due diligence and be proactive in explaining what audience your AI is or isn't suitable for. End Rant.<span>
<!-- original-model-card end -->
|
WoopsFactory/5Fe3PdPYT3wTY5eANfXiqpQ6atgZbcTpFLLKk5Y12GKT8q2K_vgg
|
WoopsFactory
| 2024-02-20T12:54:19Z | 372 | 0 |
keras
|
[
"keras",
"region:us"
] | null | 2024-02-14T22:04:01Z |
Entry not found
|
giantdev/5DkSGAeEZsoFxkFV3RGefqqohrBnG4W6FFR2yQTYuCy8GfCw_vgg
|
giantdev
| 2024-03-24T10:10:31Z | 372 | 0 |
keras
|
[
"keras",
"region:us"
] | null | 2024-03-08T22:01:00Z |
Entry not found
|
mradermacher/CabraMistral7b-v2-GGUF
|
mradermacher
| 2024-05-06T05:52:44Z | 372 | 0 |
transformers
|
[
"transformers",
"gguf",
"text-generation-inference",
"mistral",
"brazil",
"brasil",
"portuguese",
"pt",
"en",
"base_model:nicolasdec/CabraMistral7b-v2",
"license:cc",
"endpoints_compatible",
"region:us"
] | null | 2024-03-27T16:01:12Z |
---
base_model: nicolasdec/CabraMistral7b-v2
language:
- pt
- en
library_name: transformers
license: cc
quantized_by: mradermacher
tags:
- text-generation-inference
- transformers
- mistral
- gguf
- brazil
- brasil
- portuguese
---
## About
static quants of https://huggingface.co/nicolasdec/CabraMistral7b-v2
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q2_K.gguf) | Q2_K | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.IQ3_M.gguf) | IQ3_M | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF
|
mradermacher
| 2024-05-06T05:18:04Z | 372 | 0 |
transformers
|
[
"transformers",
"gguf",
"mergekit",
"megamerge",
"code",
"Cyber-Series",
"en",
"dataset:Open-Orca/OpenOrca",
"dataset:cognitivecomputations/dolphin",
"dataset:WhiteRabbitNeo/WRN-Chapter-2",
"dataset:WhiteRabbitNeo/WRN-Chapter-1",
"dataset:gate369/Alpaca-Star",
"dataset:gate369/alpaca-star-ascii",
"base_model:LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-04-04T10:11:11Z |
---
base_model: LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0
datasets:
- Open-Orca/OpenOrca
- cognitivecomputations/dolphin
- WhiteRabbitNeo/WRN-Chapter-2
- WhiteRabbitNeo/WRN-Chapter-1
- gate369/Alpaca-Star
- gate369/alpaca-star-ascii
language:
- en
library_name: transformers
license: mit
quantized_by: mradermacher
tags:
- mergekit
- megamerge
- code
- Cyber-Series
---
## About
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.Q2_K.gguf) | Q2_K | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.IQ3_M.gguf) | IQ3_M | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_Matrix_2_0-GGUF/resolve/main/Mixtral_AI_Cyber_Matrix_2_0.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
QuantFactory/Hermes-2-Pro-Mistral-7B-GGUF
|
QuantFactory
| 2024-06-09T13:25:37Z | 372 | 1 | null |
[
"gguf",
"Mistral",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"text-generation",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:NousResearch/Hermes-2-Pro-Mistral-7B",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2024-04-12T06:01:27Z |
---
base_model: NousResearch/Hermes-2-Pro-Mistral-7B
tags:
- Mistral
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- synthetic data
- distillation
- function calling
- json mode
model-index:
- name: Hermes-2-Pro-Mistral-7B
results: []
license: apache-2.0
language:
- en
datasets:
- teknium/OpenHermes-2.5
widget:
- example_title: Hermes 2 Pro
messages:
- role: system
content: >-
You are a sentient, superintelligent artificial general intelligence, here
to teach and assist me.
- role: user
content: >-
Write a short story about Goku discovering kirby has teamed up with Majin
Buu to destroy the world.
pipeline_tag: text-generation
---
# Hermes 2 Pro - Mistral 7B - GGUF
This is quantized version of [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) created using llama.cpp
## Model Description
Hermes 2 Pro on Mistral 7B is the new flagship 7B Hermes!
Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.
Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.
This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI
Learn more about the function calling system for this model on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling
## Thank you to Latitude.sh for sponsoring compute for this model!
## Example Outputs
### Explaining Problems with Quantum Gravity:
### Roleplaying as a Cosmic Super Intelligence:
### Detailing the Theory of AI Consciousness in JSON
# Prompt Format
Hermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
## Prompt Format for Function Calling
Our model was trained on specific system prompts and structures for Function Calling.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
```
To complete the function call, create a user prompt that follows the above system prompt, like so:
```
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
# Benchmarks
## GPT4All:
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5461|± |0.0145|
| | |acc_norm|0.5623|± |0.0145|
|arc_easy | 0|acc |0.8157|± |0.0080|
| | |acc_norm|0.7934|± |0.0083|
|boolq | 1|acc |0.8688|± |0.0059|
|hellaswag | 0|acc |0.6272|± |0.0048|
| | |acc_norm|0.8057|± |0.0039|
|openbookqa | 0|acc |0.3360|± |0.0211|
| | |acc_norm|0.4300|± |0.0222|
|piqa | 0|acc |0.7954|± |0.0094|
| | |acc_norm|0.7998|± |0.0093|
|winogrande | 0|acc |0.7230|± |0.0126|
```
Average: 71.19
## AGIEval:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.2047|± |0.0254|
| | |acc_norm|0.2283|± |0.0264|
|agieval_logiqa_en | 0|acc |0.3779|± |0.0190|
| | |acc_norm|0.3932|± |0.0192|
|agieval_lsat_ar | 0|acc |0.2652|± |0.0292|
| | |acc_norm|0.2522|± |0.0287|
|agieval_lsat_lr | 0|acc |0.5216|± |0.0221|
| | |acc_norm|0.5137|± |0.0222|
|agieval_lsat_rc | 0|acc |0.5911|± |0.0300|
| | |acc_norm|0.5836|± |0.0301|
|agieval_sat_en | 0|acc |0.7427|± |0.0305|
| | |acc_norm|0.7184|± |0.0314|
|agieval_sat_en_without_passage| 0|acc |0.4612|± |0.0348|
| | |acc_norm|0.4466|± |0.0347|
|agieval_sat_math | 0|acc |0.3818|± |0.0328|
| | |acc_norm|0.3545|± |0.0323|
```
Average: 44.52
## BigBench:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.5579|± |0.0361|
|bigbench_date_understanding | 0|multiple_choice_grade|0.6694|± |0.0245|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3333|± |0.0294|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.2061|± |0.0214|
| | |exact_str_match |0.2256|± |0.0221|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.3120|± |0.0207|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2114|± |0.0154|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.4900|± |0.0289|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.3600|± |0.0215|
|bigbench_navigate | 0|multiple_choice_grade|0.5000|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.6660|± |0.0105|
|bigbench_ruin_names | 0|multiple_choice_grade|0.4420|± |0.0235|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.2766|± |0.0142|
|bigbench_snarks | 0|multiple_choice_grade|0.6630|± |0.0352|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.6653|± |0.0150|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.3190|± |0.0147|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2128|± |0.0116|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1737|± |0.0091|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.4900|± |0.0289|
```
Average: 41.65
## TruthfulQA:
```
| Task |Version|Metric|Value | |Stderr|
|-------------|------:|------|-----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.4100|± |0.0172|
| | |mc2 |0.5911|± |0.0158|
```
# Function Calling Evaluations
We worked with Fireworks.AI on evaluations by starting off with their Function Calling eval dataset, fixing some unsolveable ones, and generating a second eval dataset for JSON mode.
## Function Calling Accuracy: 91%
## JSON Mode Accuracy: 84%
Run the evaluator yourself using @interstellarninja's codebase here:
https://github.com/interstellarninja/function-calling-eval
You can find the evaluation datasets here:
https://huggingface.co/datasets/NousResearch/func-calling-eval
https://huggingface.co/datasets/NousResearch/json-mode-eval
# Inference Code
Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
Note: To use function calling, you should see the github repo above.
```python
# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers import LlamaTokenizer, MistralForCausalLM
import bitsandbytes, flash_attn
tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Hermes-2-Pro-Mistral-7B', trust_remote_code=True)
model = MistralForCausalLM.from_pretrained(
"NousResearch/Hermes-2-Pro-Mistral-7B",
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
load_in_4bit=True,
use_flash_attention_2=True
)
prompts = [
"""<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
<|im_start|>assistant""",
]
for chat in prompts:
print(chat)
input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")
```
## Inference Code for Function Calling:
All code for utilizing, parsing, and building function calling templates is available on our github:
[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
# Chat Interfaces
When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
|
mradermacher/Mixtral_AI_CyberUltron-GGUF
|
mradermacher
| 2024-05-05T15:14:43Z | 372 | 1 |
transformers
|
[
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"code",
"medical ",
"farmer",
"doctor",
"Mega-Series",
"Cyber-Series",
"Role-Play",
"Self-Rag",
"ThinkingBot",
"milestone",
"mega-series",
"SpydazWebAI",
"en",
"dataset:gretelai/synthetic_text_to_sql",
"dataset:HuggingFaceTB/cosmopedia",
"dataset:teknium/OpenHermes-2.5",
"dataset:Open-Orca/SlimOrca",
"dataset:Open-Orca/OpenOrca",
"dataset:cognitivecomputations/dolphin-coder",
"dataset:databricks/databricks-dolly-15k",
"dataset:yahma/alpaca-cleaned",
"dataset:uonlp/CulturaX",
"dataset:mwitiderrick/SwahiliPlatypus",
"dataset:swahili",
"dataset:Rogendo/English-Swahili-Sentence-Pairs",
"dataset:ise-uiuc/Magicoder-Evol-Instruct-110K",
"dataset:meta-math/MetaMathQA",
"base_model:LeroyDyer/Mixtral_AI_CyberUltron",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-23T13:26:10Z |
---
base_model: LeroyDyer/Mixtral_AI_CyberUltron
datasets:
- gretelai/synthetic_text_to_sql
- HuggingFaceTB/cosmopedia
- teknium/OpenHermes-2.5
- Open-Orca/SlimOrca
- Open-Orca/OpenOrca
- cognitivecomputations/dolphin-coder
- databricks/databricks-dolly-15k
- yahma/alpaca-cleaned
- uonlp/CulturaX
- mwitiderrick/SwahiliPlatypus
- swahili
- Rogendo/English-Swahili-Sentence-Pairs
- ise-uiuc/Magicoder-Evol-Instruct-110K
- meta-math/MetaMathQA
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
- code
- 'medical '
- farmer
- doctor
- Mega-Series
- Cyber-Series
- Role-Play
- Self-Rag
- ThinkingBot
- milestone
- mega-series
- SpydazWebAI
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/LeroyDyer/Mixtral_AI_CyberUltron
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberUltron-GGUF/resolve/main/Mixtral_AI_CyberUltron.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
LnL-AI/TinyLlama-1.1B-intermediate-step-1341k-3T-autoround-lm_head-symFalse
|
LnL-AI
| 2024-06-20T11:54:53Z | 372 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:unknown",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2024-04-26T07:06:12Z |
---
license: unknown
---
- **Bits**: 4
- **Group Size**: 128
- **Damp Percent**: 0.01
- **Desc Act**: false
- **Static Groups**: false
- **Sym**: false
- **True Sequential**: false
- **LM Head**: true
- **Model Name or Path**: null
- **Model File Base Name**: model
- **Quant Method**: gptq
- **Checkpoint Format**: gptq
- **Meta:**
- Quantizer: intel/auto-round:0.1
- Packer: autogptq:0.8.0.dev1
- Iters: 400
- LR: 0.0025
- MinMax LR: 0.0025
- Enable MinMax Tuning: true
- Use Quant Input: false
- Scale Dtype: torch.float16
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.