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
|
|---|---|---|---|---|---|---|---|---|---|
Helsinki-NLP/opus-mt-tc-big-fi-en | Helsinki-NLP | 2024-04-16T18:13:57Z | 428 | 4 | transformers | [
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"en",
"fi",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| translation | 2022-03-22T12:39:30Z | ---
language:
- en
- fi
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-fi-en
results:
- task:
name: Translation fin-eng
type: translation
args: fin-eng
dataset:
name: flores101-devtest
type: flores_101
args: fin eng devtest
metrics:
- name: BLEU
type: bleu
value: 35.4
- task:
name: Translation fin-eng
type: translation
args: fin-eng
dataset:
name: newsdev2015
type: newsdev2015
args: fin-eng
metrics:
- name: BLEU
type: bleu
value: 28.6
- task:
name: Translation fin-eng
type: translation
args: fin-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: fin-eng
metrics:
- name: BLEU
type: bleu
value: 57.4
- task:
name: Translation fin-eng
type: translation
args: fin-eng
dataset:
name: newstest2015
type: wmt-2015-news
args: fin-eng
metrics:
- name: BLEU
type: bleu
value: 29.9
- task:
name: Translation fin-eng
type: translation
args: fin-eng
dataset:
name: newstest2016
type: wmt-2016-news
args: fin-eng
metrics:
- name: BLEU
type: bleu
value: 34.3
- task:
name: Translation fin-eng
type: translation
args: fin-eng
dataset:
name: newstest2017
type: wmt-2017-news
args: fin-eng
metrics:
- name: BLEU
type: bleu
value: 37.3
- task:
name: Translation fin-eng
type: translation
args: fin-eng
dataset:
name: newstest2018
type: wmt-2018-news
args: fin-eng
metrics:
- name: BLEU
type: bleu
value: 27.1
- task:
name: Translation fin-eng
type: translation
args: fin-eng
dataset:
name: newstest2019
type: wmt-2019-news
args: fin-eng
metrics:
- name: BLEU
type: bleu
value: 32.7
---
# opus-mt-tc-big-fi-en
Neural machine translation model for translating from Finnish (fi) to English (en).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2021-12-08
* source language(s): fin
* target language(s): eng
* model: transformer (big)
* data: opusTCv20210807+bt ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807+bt-2021-12-08.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-eng/opusTCv20210807+bt-2021-12-08.zip)
* more information released models: [OPUS-MT fin-eng README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/fin-eng/README.md)
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
"Kolme kolmanteen on kaksikymmentäseitsemän.",
"Heille syntyi poikavauva."
]
model_name = "pytorch-models/opus-mt-tc-big-fi-en"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-fi-en")
print(pipe("Kolme kolmanteen on kaksikymmentäseitsemän."))
```
## Benchmarks
* test set translations: [opusTCv20210807+bt-2021-12-08.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-eng/opusTCv20210807+bt-2021-12-08.test.txt)
* test set scores: [opusTCv20210807+bt-2021-12-08.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-eng/opusTCv20210807+bt-2021-12-08.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| fin-eng | tatoeba-test-v2021-08-07 | 0.72298 | 57.4 | 10690 | 80552 |
| fin-eng | flores101-devtest | 0.62521 | 35.4 | 1012 | 24721 |
| fin-eng | newsdev2015 | 0.56232 | 28.6 | 1500 | 32012 |
| fin-eng | newstest2015 | 0.57469 | 29.9 | 1370 | 27270 |
| fin-eng | newstest2016 | 0.60715 | 34.3 | 3000 | 62945 |
| fin-eng | newstest2017 | 0.63050 | 37.3 | 3002 | 61846 |
| fin-eng | newstest2018 | 0.54199 | 27.1 | 3000 | 62325 |
| fin-eng | newstest2019 | 0.59620 | 32.7 | 1996 | 36215 |
| fin-eng | newstestB2016 | 0.55472 | 27.9 | 3000 | 62945 |
| fin-eng | newstestB2017 | 0.58847 | 31.1 | 3002 | 61846 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: f084bad
* port time: Tue Mar 22 14:52:19 EET 2022
* port machine: LM0-400-22516.local
|
malteos/bloom-6b4-clp-german | malteos | 2024-04-06T11:11:50Z | 428 | 37 | transformers | [
"transformers",
"pytorch",
"safetensors",
"bloom",
"ggml",
"text-generation",
"de",
"dataset:oscar",
"arxiv:2301.09626",
"license:bigscience-bloom-rail-1.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2022-11-07T15:33:45Z | ---
language:
- de
license: bigscience-bloom-rail-1.0
library_name: transformers
tags:
- ggml
- bloom
datasets:
- oscar
pipeline_tag: text-generation
---
# BLOOM-CLP German (6.4B parameters)
This is a monolingual German language model trained using the [CLP-Transfer](https://arxiv.org/abs/2301.09626) method based on [BLOOM-7b1](https://huggingface.co/bigscience/bloom-7b1).
You can try out the model at [European Language Grid](https://live.european-language-grid.eu/catalogue/tool-service/20825/try%20out/).
<span style="color:blue">UPDATE: We recently released an instruction-tuned version of this model: [malteos/bloom-6b4-clp-german-oasst-v0.1](https://huggingface.co/malteos/bloom-6b4-clp-german-oasst-v0.1)</span>.
### How to use
You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we
set a seed for reproducibility:
```python
>>> from transformers import pipeline, set_seed
>>> generator = pipeline('text-generation', model='malteos/bloom-6b4-clp-german')
>>> set_seed(42)
>>> generator("Hello, I'm a language model,", max_length=30, num_return_sequences=3)
[{'generated_text': "Hello, I'm a language model, a language for thinking, a language for expressing thoughts."},
{'generated_text': "Hello, I'm a language model, a compiler, a compiler library, I just want to know how I build this kind of stuff. I don"},
{'generated_text': "Hello, I'm a language model, and also have more than a few of your own, but I understand that they're going to need some help"},]
```
## Training dataset
- ca. 50B German tokens
- Web-crawled content from the German subset [OSCAR v22.01](https://oscar-corpus.com/post/oscar-v22-01/) (excluding content tagged as header, footer, noisy, or adult)
- Web-crawled content from the [GC4 Corpus](https://german-nlp-group.github.io/projects/gc4-corpus.html) (including only the head and middle parts)
- Both Web-crawled datasets are deduplicated with [Google's suffix array implementation](https://github.com/google-research/deduplicate-text-datasets)
- German court decisions from [Open Legal Data](http://openlegaldata.io/)
## Code
- [BigScience's Megatron-Deepspeed fork](https://github.com/bigscience-workshop/Megatron-DeepSpeed)
## Hardware
- 32xA100-40GB GPUs
- 12.5 days
- [Tensorboard logs](https://huggingface.co/malteos/bloom-6b4-clp-german-logs/tensorboard)
## Evaluation
Validation PPL compared to from-scratch training (the lower the better):
<img alt="Tokens vs PPL" src="https://github.com/malteos/clp-transfer/raw/main/german-6b-ppl.png">
Additional evaluations can be found in [our paper](https://arxiv.org/abs/2301.09626).
## How to cite
If you are using our code or models, please cite [our paper](https://arxiv.org/abs/2301.09626):
```bibtex
@misc{Ostendorff2023clp,
doi = {10.48550/ARXIV.2301.09626},
author = {Ostendorff, Malte and Rehm, Georg},
title = {Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning},
publisher = {arXiv},
year = {2023}
}
```
## License
[BigScience BLOOM RAIL 1.0](https://bigscience.huggingface.co/blog/the-bigscience-rail-license)
|
Inzamam567/Useless-SomethingV2_2 | Inzamam567 | 2023-03-31T22:15:28Z | 428 | 9 | diffusers | [
"diffusers",
"stable-diffusion",
"text-to-image",
"safetensors",
"en",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-03-31T22:15:28Z | ---
license: creativeml-openrail-m
thumbnail: >-
https://huggingface.co/NoCrypt/SomethingV2_2/resolve/main/images/thumbnail.webp
tags:
- stable-diffusion
- text-to-image
- safetensors
- diffusers
inference: true
language:
- en
widget:
- text: >-
masterpiece, masterpiece, masterpiece, best quality, ultra-detailed, 1girl,
hatsune miku, blue hair, upper body, looking at viewer, ?, negative space,
bioluminescence, bioluminescence, bioluminescence, darkness, wind,
butterfly, black background, portrait, ice
example_title: example
library_name: diffusers
duplicated_from: NoCrypt/SomethingV2_2
---
<center>
<img src="https://huggingface.co/NoCrypt/SomethingV2_2/resolve/main/images/Artboard%201.png"/>
<h1 style="font-size:1.6rem;">
<b>
SomethingV2.2
</b>
</h1>
<p>
Welcome to SomethingV2.2 - an improved anime latent diffusion model from <a href="https://huggingface.co/NoCrypt/SomethingV2">SomethingV2</a>
A lot of things are being discovered lately, such as a way to merge model using mbw automatically, offset noise to get much darker result, and even VAE tuning. This model is intended to use all of those features as the improvements, here's some improvements that have been made:
</p>
<img src="https://huggingface.co/NoCrypt/SomethingV2_2/resolve/main/images/Artboard%202.png"/>
<h2>Can't trust the numbers? Here's some proof</h2>
</center>
%2C%20dark.png)
<img style="display:inline;margin:0;padding:0;" src="https://huggingface.co/NoCrypt/SomethingV2_2/resolve/main/images/00019-1829045217-masterpiece%2C%20best%20quality%2C%20hatsune%20miku%2C%201girl%2C%20white%20shirt%2C%20blue%20necktie%2C%20bare%20shoulders%2C%20very%20detailed%20background%2C%20hands%20on%20ow.png" width="32%"/>
<img style="display:inline;margin:0;padding:0;" src="https://huggingface.co/NoCrypt/SomethingV2_2/resolve/main/images/00018-1769428138-masterpiece%2C%20best%20quality%2C%20hatsune%20miku%2C%201girl%2C%20white%20shirt%2C%20blue%20necktie%2C%20bare%20shoulders%2C%20very%20detailed%20background%2C%20hands%20on%20ow.png" width="32%"/>
<img style="display:inline;margin:0;padding:0;" src="https://huggingface.co/NoCrypt/SomethingV2_2/resolve/main/images/00020-3514023396-masterpiece%2C%20best%20quality%2C%20hatsune%20miku%2C%201girl%2C%20white%20shirt%2C%20blue%20necktie%2C%20bare%20shoulders%2C%20very%20detailed%20background%2C%20cafe%2C%20angry.png" width="32%"/>
<details><summary><big><b>Prompts</b></big></summary>
```yaml
masterpiece, best quality, ultra-detailed, 2girls, upper body, looking at viewer, ?, negative space, (bioluminescence:1.2), darkness, wind, butterfly, black background, glowing,
AND masterpiece, best quality, ultra-detailed, 2girls, hatsune miku, upper body, looking at viewer, ?, negative space, (bioluminescence:1.2), darkness, wind, butterfly, black background, glowing, (blue theme:1.2)
AND masterpiece, best quality, ultra-detailed, 2girls, hakurei reimu, (brown hair:1.1), upper body, looking at viewer, ?, negative space, (bioluminescence:1.2), darkness, wind, butterfly, black background, glowing, (red theme:1.2)
Negative prompt: EasyNegative
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 3452449180, Size: 816x504, Model: somethingv2_1, Denoising strength: 0.58, Clip skip: 2, ENSD: 31337, Latent Couple: "divisions=1:1,1:2,1:2 positions=0:0,0:0,0:1 weights=0.2,0.8,0.8 end at step=13", Hires upscale: 1.9, Hires steps: 12, Hires upscaler: Latent (nearest-exact)
```
```yaml
masterpiece, best quality, hatsune miku, white shirt, darkness, dark background
Negative prompt: EasyNegative
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 72332473, Size: 504x600, Model: somethingv2_1, Denoising strength: 0.58, Clip skip: 2, ENSD: 31337, Hires upscale: 1.85, Hires steps: 12, Hires upscaler: Latent (nearest-exact)
```
```yaml
masterpiece, best quality, hatsune miku, 1girl, white shirt, blue necktie, bare shoulders, very detailed background, hands on own cheeks, open mouth, one eye closed, clenched teeth, smile
Negative prompt: EasyNegative, tattoo, (shoulder tattoo:1.0), (number tattoo:1.3), frills
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1829045217, Size: 456x592, Model: SomethingV2_2, Denoising strength: 0.53, Clip skip: 2, ENSD: 31337, Hires upscale: 1.65, Hires steps: 12, Hires upscaler: Latent (nearest-exact), Discard penultimate sigma: True
```
```yaml
masterpiece, best quality, hatsune miku, 1girl, white shirt, blue necktie, bare shoulders, very detailed background, hands on own cheeks, open mouth, eyez closed, clenched teeth, smile, arms behind back,
Negative prompt: EasyNegative, tattoo, (shoulder tattoo:1.0), (number tattoo:1.3), frills
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1769428138, Size: 456x592, Model: SomethingV2_2, Denoising strength: 0.53, Clip skip: 2, ENSD: 31337, Hires upscale: 1.65, Hires steps: 12, Hires upscaler: Latent (nearest-exact), Discard penultimate sigma: True
```
```yaml
masterpiece, best quality, hatsune miku, 1girl, white shirt, blue necktie, bare shoulders, very detailed background, cafe, angry, crossed arms, detached sleeves, light particles,
Negative prompt: EasyNegative, tattoo, (shoulder tattoo:1.0), (number tattoo:1.3), frills
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 3514023396, Size: 456x592, Model: SomethingV2_2, Denoising strength: 0.53, Clip skip: 2, ENSD: 31337, Hires upscale: 1.65, Hires steps: 12, Hires upscaler: Latent (nearest-exact), Discard penultimate sigma: True
```
</details>
## Non-miku examples
<img style="display:inline;margin:0;padding:0;" width="49%" src="https://huggingface.co/NoCrypt/SomethingV2_2/resolve/main/images/00021-4018636341-masterpiece%2C%20best%20quality%2C%201girl%2C%20aqua%20eyes%2C%20baseball%20cap%2C%20blonde%20hair%2C%20closed%20mouth%2C%20earrings%2C%20green%20background%2C%20hat%2C%20hoop%20earr.png"/>
<img style="display:inline;margin:0;padding:0;" width="49%" src="https://huggingface.co/NoCrypt/SomethingV2_2/resolve/main/images/00022-1334620477-masterpiece%2C%20best%20quality%2C%20landscape.png"/>
<details><summary><big><b>Prompts</b></big></summary>
```yaml
masterpiece, best quality, 1girl, aqua eyes, baseball cap, blonde hair, closed mouth, earrings, green background, hat, hoop earrings, jewelry, looking at viewer, shirt, short hair, simple background, solo, upper body, yellow shirt
Negative prompt: EasyNegative
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 4018636341, Size: 440x592, Model: SomethingV2_2, Denoising strength: 0.53, Clip skip: 2, ENSD: 31337, Hires upscale: 1.65, Hires steps: 13, Hires upscaler: Latent (nearest-exact)
```
```yaml
masterpiece, best quality, landscape
Negative prompt: EasyNegative
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1334620477, Size: 440x592, Model: SomethingV2_2, Denoising strength: 0.53, Clip skip: 2, ENSD: 31337, Hires upscale: 1.65, Hires steps: 13, Hires upscaler: Latent (nearest-exact)
```
</details>
## Recommended settings
- VAE: None (Baked in model, [blessed2](https://huggingface.co/NoCrypt/blessed_vae/blob/main/blessed2.vae.pt))
- Clip Skip: 2
- Sampler: DPM++ 2M Karras
- CFG Scale: 7 ± 5
- Recommended Positive Prompt: masterpiece, best quality, negative space, (bioluminescence:1.2), darkness, dark background
- Recommended Negative Prompt: [EasyNegative](https://huggingface.co/datasets/gsdf/EasyNegative)
- For better results, using hires fix is a must.
- Hires upscaler: Latent (any variant, such as nearest-exact)
## Recipe
*Due to [SD-Silicon's Terms of use](https://huggingface.co/Xynon/SD-Silicon#terms-of-use). I must specify how the model was made*
|Model A | Model B | Interpolation Method | Weight | Name |
|---|---|---|---|---|
|[dpepmkmp](https://huggingface.co/closertodeath/dpepmkmp/blob/main/dpepmkmp.safetensors)|[silicon29-dark](https://huggingface.co/Xynon/SD-Silicon/blob/main/Silicon29/Silicon29-dark.safetensors)|MBW|Reverse Cosine|[dpepsili](https://huggingface.co/un1xx/model_dump/blob/main/bw-merge-dpepmkmp-Silicon29-dark-0.ckpt)|
|[somethingV2_1](https://huggingface.co/NoCrypt/SomethingV2/blob/main/somethingv2_1.safetensors)|[dpepsili](https://huggingface.co/un1xx/model_dump/blob/main/bw-merge-dpepmkmp-Silicon29-dark-0.ckpt)|MBW|Cosine|SomethingV2_2 raw|
|SomethingV2_2 raw|[Blessed2 VAE](https://huggingface.co/NoCrypt/blessed_vae/blob/main/blessed2.vae.pt)|Bake VAE|-|**[SomethingV2_2](https://huggingface.co/NoCrypt/SomethingV2_2/blob/main/SomethingV2_2.safetensors)**|
## Why not call it SomethingV4?
Since this model was based on SomethingV2 and there's not THAT much of improvements in some condition. Calling it V4 is just not right at the moment 😅 |
google/matcha-base | google | 2023-07-22T19:36:43Z | 428 | 22 | transformers | [
"transformers",
"pytorch",
"pix2struct",
"text2text-generation",
"matcha",
"visual-question-answering",
"en",
"fr",
"ro",
"de",
"multilingual",
"arxiv:2212.09662",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
]
| visual-question-answering | 2023-04-03T11:03:02Z | ---
language:
- en
- fr
- ro
- de
- multilingual
inference: false
pipeline_tag: visual-question-answering
license: apache-2.0
tags:
- matcha
---
# Model card for MatCha - base model
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/matcha_architecture.jpg"
alt="drawing" width="600"/>
This model is the base MatCha model. Can be used for fine-tuning purposes only.
# Table of Contents
0. [TL;DR](#TL;DR)
1. [Using the model](#using-the-model)
2. [Contribution](#contribution)
3. [Citation](#citation)
# TL;DR
The abstract of the paper states that:
> Visual language data such as plots, charts, and infographics are ubiquitous in the human world. However, state-of-the-art visionlanguage models do not perform well on these data. We propose MATCHA (Math reasoning and Chart derendering pretraining) to enhance visual language models’ capabilities jointly modeling charts/plots and language data. Specifically we propose several pretraining tasks that cover plot deconstruction and numerical reasoning which are the key capabilities in visual language modeling. We perform the MATCHA pretraining starting from Pix2Struct, a recently proposed imageto-text visual language model. On standard benchmarks such as PlotQA and ChartQA, MATCHA model outperforms state-of-the-art methods by as much as nearly 20%. We also examine how well MATCHA pretraining transfers to domains such as screenshot, textbook diagrams, and document figures and observe overall improvement, verifying the usefulness of MATCHA pretraining on broader visual language tasks.
# Using the model
```python
from transformers import Pix2StructProcessor, Pix2StructForConditionalGeneration
import requests
from PIL import Image
processor = Pix2StructProcessor.from_pretrained('google/matcha-base')
model = Pix2StructForConditionalGeneration.from_pretrained('google/matcha-base')
url = "https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/val/png/20294671002019.png"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(images=image, text="Is the sum of all 4 places greater than Laos?", return_tensors="pt")
predictions = model.generate(**inputs, max_new_tokens=512)
print(processor.decode(predictions[0], skip_special_tokens=True))
>>> No
```
# Converting from T5x to huggingface
You can use the [`convert_pix2struct_checkpoint_to_pytorch.py`](https://github.com/huggingface/transformers/blob/main/src/transformers/models/pix2struct/convert_pix2struct_original_pytorch_to_hf.py) script as follows:
```bash
python convert_pix2struct_checkpoint_to_pytorch.py --t5x_checkpoint_path PATH_TO_T5X_CHECKPOINTS --pytorch_dump_path PATH_TO_SAVE --is_vqa
```
if you are converting a large model, run:
```bash
python convert_pix2struct_checkpoint_to_pytorch.py --t5x_checkpoint_path PATH_TO_T5X_CHECKPOINTS --pytorch_dump_path PATH_TO_SAVE --use-large --is_vqa
```
Once saved, you can push your converted model with the following snippet:
```python
from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor
model = Pix2StructForConditionalGeneration.from_pretrained(PATH_TO_SAVE)
processor = Pix2StructProcessor.from_pretrained(PATH_TO_SAVE)
model.push_to_hub("USERNAME/MODEL_NAME")
processor.push_to_hub("USERNAME/MODEL_NAME")
```
# Contribution
This model was originally contributed by Fangyu Liu, Francesco Piccinno et al. and added to the Hugging Face ecosystem by [Younes Belkada](https://huggingface.co/ybelkada).
# Citation
If you want to cite this work, please consider citing the original paper:
```
@misc{liu2022matcha,
title={MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering},
author={Fangyu Liu and Francesco Piccinno and Syrine Krichene and Chenxi Pang and Kenton Lee and Mandar Joshi and Yasemin Altun and Nigel Collier and Julian Martin Eisenschlos},
year={2022},
eprint={2212.09662},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
timm/xcit_tiny_12_p8_384.fb_dist_in1k | timm | 2024-02-10T23:44:07Z | 428 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2106.09681",
"license:apache-2.0",
"region:us"
]
| image-classification | 2023-04-13T02:31:06Z | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
---
# Model card for xcit_tiny_12_p8_384.fb_dist_in1k
A XCiT (Cross-Covariance Image Transformer) image classification model. Pretrained on ImageNet-1k with distillation by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 6.7
- GMACs: 14.1
- Activations (M): 69.1
- Image size: 384 x 384
- **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_tiny_12_p8_384.fb_dist_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_tiny_12_p8_384.fb_dist_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, 2305, 192) 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}
}
```
|
timm/dla46x_c.in1k | timm | 2023-04-24T21:12:48Z | 428 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:1707.06484",
"license:bsd-3-clause",
"region:us"
]
| image-classification | 2023-04-24T19:34:21Z | ---
tags:
- image-classification
- timm
library_name: timm
license: bsd-3-clause
datasets:
- imagenet-1k
---
# Model card for dla46x_c.in1k
A DLA (Deep Layer Aggregation) image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 1.1
- GMACs: 0.5
- Activations (M): 5.7
- Image size: 224 x 224
- **Papers:**
- Deep Layer Aggregation: https://arxiv.org/abs/1707.06484
- **Original:** https://github.com/ucbdrive/dla
- **Dataset:** ImageNet-1k
## 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('dla46x_c.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(
'dla46x_c.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, 32, 112, 112])
# torch.Size([1, 64, 56, 56])
# torch.Size([1, 64, 28, 28])
# torch.Size([1, 128, 14, 14])
# torch.Size([1, 256, 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(
'dla46x_c.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, 256, 7, 7) 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
@inproceedings{yu2018deep,
title={Deep layer aggregation},
author={Yu, Fisher and Wang, Dequan and Shelhamer, Evan and Darrell, Trevor},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
year={2018}
}
```
|
timm/convformer_b36.sail_in22k_ft_in1k | timm | 2023-05-05T06:00:30Z | 428 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-22k",
"arxiv:2210.13452",
"license:apache-2.0",
"region:us"
]
| image-classification | 2023-05-05T05:59:01Z | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- imagenet-22k
---
# Model card for convformer_b36.sail_in22k_ft_in1k
A ConvFormer (a MetaFormer) image classification model. Pretrained on ImageNet-22k and fine-tuned on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 99.9
- GMACs: 22.7
- Activations (M): 56.1
- Image size: 224 x 224
- **Papers:**
- Metaformer baselines for vision: https://arxiv.org/abs/2210.13452
- **Original:** https://github.com/sail-sg/metaformer
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-22k
## 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('convformer_b36.sail_in22k_ft_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(
'convformer_b36.sail_in22k_ft_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, 128, 56, 56])
# torch.Size([1, 256, 28, 28])
# torch.Size([1, 512, 14, 14])
# torch.Size([1, 768, 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(
'convformer_b36.sail_in22k_ft_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, 768, 7, 7) 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
@article{yu2022metaformer_baselines,
title={Metaformer baselines for vision},
author={Yu, Weihao and Si, Chenyang and Zhou, Pan and Luo, Mi and Zhou, Yichen and Feng, Jiashi and Yan, Shuicheng and Wang, Xinchao},
journal={arXiv preprint arXiv:2210.13452},
year={2022}
}
```
|
aehrc/cxrmate-multi-tf | aehrc | 2024-06-28T05:59:03Z | 428 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"vision-encoder-decoder",
"feature-extraction",
"custom_code",
"arxiv:2307.09758",
"license:apache-2.0",
"region:us"
]
| feature-extraction | 2023-06-11T09:25:36Z | ---
license: apache-2.0
---
# CXRMate: Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report Generation
This is the multi-image Chest X-Ray (CXR) report generator trained with teacher forcing (no reinforcement learning).
## Hugging Face Models From This Paper:
| Link | Longitudinal | Multi-image | Reinforcement learning |
|---|---|---|---|
| https://huggingface.co/aehrc/cxrmate | Y | Y | Y |
| https://huggingface.co/aehrc/cxrmate-tf | Y | Y | N |
| https://huggingface.co/aehrc/cxrmate-multi-tf | N | Y | N |
| https://huggingface.co/aehrc/cxrmate-single-tf | N | N | N |
## ArXiv:
- https://arxiv.org/abs/2307.09758
## GitHub Repository:
- https://github.com/aehrc/cxrmate
## Notebook Example:
- https://github.com/aehrc/cxrmate/blob/main/examples/cxrmate-multi-tf.ipynb |
digiplay/EdisonNilMix_v1 | digiplay | 2023-12-04T18:27:39Z | 428 | 4 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-07-02T09:27:42Z | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
https://civitai.com/models/94664/edison-nil-mix
Sample image :
 |
nota-ai/bk-sdm-tiny | nota-ai | 2023-11-17T02:06:05Z | 428 | 23 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dataset:ChristophSchuhmann/improved_aesthetics_6.5plus",
"arxiv:2305.15798",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-07-12T10:53:04Z | ---
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
datasets:
- ChristophSchuhmann/improved_aesthetics_6.5plus
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 Model Card
Block-removed Knowledge-distilled Stable Diffusion Model (BK-SDM) is an architecturally compressed SDM for efficient general-purpose text-to-image synthesis. This model is bulit with (i) removing several residual and attention blocks from the U-Net of [Stable Diffusion v1.4]( https://huggingface.co/CompVis/stable-diffusion-v1-4) and (ii) distillation pretraining on only 0.22M LAION pairs (fewer than 0.1% of the full training set). Despite being trained with very limited resources, our compact model can imitate the original SDM by benefiting from transferred knowledge.
- **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-tiny", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a tropical bird sitting on a branch of a tree"
image = pipe(prompt).images[0]
image.save("example.png")
```
The following code is also runnable, because we compressed the U-Net of [Stable Diffusion v1.4]( https://huggingface.co/CompVis/stable-diffusion-v1-4) while keeping the other parts (i.e., Text Encoder and Image Decoder) unchanged:
```python
import torch
from diffusers import StableDiffusionPipeline, UNet2DConditionModel
pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16)
pipe.unet = UNet2DConditionModel.from_pretrained("nota-ai/bk-sdm-tiny", subfolder="unet", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a tropical bird sitting on a branch of a tree"
image = pipe(prompt).images[0]
image.save("example.png")
```
## Compression Method
### U-Net Architecture
Certain residual and attention blocks were eliminated from the U-Net of SDM-v1.4:
- 1.04B-param [SDM-v1.4](https://huggingface.co/CompVis/stable-diffusion-v1-4) (0.86B-param U-Net): the original source model.
- 0.76B-param [**BK-SDM-Base**](https://huggingface.co/nota-ai/bk-sdm-base) (0.58B-param U-Net): obtained with ① fewer blocks in outer stages.
- 0.66B-param [**BK-SDM-Small**](https://huggingface.co/nota-ai/bk-sdm-small) (0.49B-param U-Net): obtained with ① and ② mid-stage removal.
- 0.50B-param [**BK-SDM-Tiny**](https://huggingface.co/nota-ai/bk-sdm-tiny) (0.33B-param U-Net): obtained with ①, ②, and ③ further inner-stage removal.
<center>
<img alt="U-Net architectures" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_arch.png" width="100%">
</center>
### Distillation Pretraining
The compact U-Net was trained to mimic the behavior of the original U-Net. We leveraged feature-level and output-level distillation, along with the denoising task loss.
<center>
<img alt="KD-based pretraining" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_kd_bksdm.png" width="100%">
</center>
<br/>
- **Training Data**: 212,776 image-text pairs (i.e., 0.22M pairs) from [LAION-Aesthetics V2 6.5+](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-Small](https://huggingface.co/nota-ai/bk-sdm-small) (Ours) | 16.98 | 31.68 | 0.2677 | 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 |
<br/>
The following figure depicts synthesized images with some MS-COCO captions.
<center>
<img alt="Visual results" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_results.png" width="100%">
</center>
<br/>
# Uses
_Note: This section is taken from the [Stable Diffusion v1 model card]( https://huggingface.co/CompVis/stable-diffusion-v1-4) (which was based on the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini)) and applies in the same way to BK-SDMs_.
## Direct Use
The model is intended for research purposes only. Possible research areas and tasks include
- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of generative models.
- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on generative models.
Excluded uses are described below.
### Misuse, Malicious Use, and Out-of-Scope Use
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
#### Out-of-Scope Use
The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
#### Misuse and Malicious Use
Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
- Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
- Intentionally promoting or propagating discriminatory content or harmful stereotypes.
- Impersonating individuals without their consent.
- Sexual content without consent of the people who might see it.
- Mis- and disinformation
- Representations of egregious violence and gore
- Sharing of copyrighted or licensed material in violation of its terms of use.
- Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
## Limitations and Bias
### Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
- Faces and people in general may not be generated properly.
- The model was trained mainly with English captions and will not work as well in other languages.
- The autoencoding part of the model is lossy
- The model was trained on a large-scale dataset [LAION-5B](https://laion.ai/blog/laion-5b/) which contains adult material and is not fit for product use without additional safety mechanisms and considerations.
- No additional measures were used to deduplicate the dataset. As a result, we observe some degree of memorization for images that are duplicated in the training data. The training data can be searched at [https://rom1504.github.io/clip-retrieval/](https://rom1504.github.io/clip-retrieval/) to possibly assist in the detection of memorized images.
### Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), which consists of images that are primarily limited to English descriptions. Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. This affects the overall output of the model, as white and western cultures are often set as the default. Further, the ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
### Safety Module
The intended use of this model is with the [Safety Checker](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py) in Diffusers. This checker works by checking model outputs against known hard-coded NSFW concepts. The concepts are intentionally hidden to reduce the likelihood of reverse-engineering this filter. Specifically, the checker compares the class probability of harmful concepts in the embedding space of the `CLIPTextModel` *after generation* of the images. The concepts are passed into the model with the generated image and compared to a hand-engineered weight for each NSFW concept.
# 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).* |
sail-rvc/Plankton__SpongeBob___RVC_v2__1K_Epochs_69K_Steps | sail-rvc | 2023-07-14T07:30:41Z | 428 | 3 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:29:48Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Plankton__SpongeBob___RVC_v2__1K_Epochs_69K_Steps
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:30:41
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
TheBloke/Llama-2-13B-GPTQ | TheBloke | 2023-09-27T12:44:47Z | 428 | 118 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-2",
"en",
"arxiv:2307.09288",
"base_model:meta-llama/Llama-2-13b-hf",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
]
| text-generation | 2023-07-18T17:17:40Z | ---
language:
- en
license: llama2
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
model_name: Llama 2 13B
base_model: meta-llama/Llama-2-13b-hf
inference: false
model_creator: Meta
model_type: llama
pipeline_tag: text-generation
prompt_template: '{prompt}
'
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 -->
# Llama 2 13B - GPTQ
- Model creator: [Meta](https://huggingface.co/meta-llama)
- Original model: [Llama 2 13B](https://huggingface.co/meta-llama/Llama-2-13b-hf)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Meta's Llama 2 13B](https://huggingface.co/meta-llama/Llama-2-13b-hf).
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
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Llama-2-13B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama-2-13B-GGUF)
* [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/meta-llama/Llama-2-13b-hf)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: None
```
{prompt}
```
<!-- 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.
All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the `main` branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
<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 dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ 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/Llama-2-13B-GPTQ/tree/main) | 4 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, without Act Order and group size 128g. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.95 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
| [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download from branches
- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Llama-2-13B-GPTQ:main`
- With Git, you can clone a branch with:
```
git clone --single-branch --branch main https://huggingface.co/TheBloke/Llama-2-13B-GPTQ
```
- In Python Transformers code, the branch is the `revision` parameter; see below.
<!-- 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/Llama-2-13B-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/Llama-2-13B-GPTQ:main`
- 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: `Llama-2-13B-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-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers>=4.32.0 optimum>=1.12.0
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
pip3 install .
```
### For CodeLlama models only: you must use Transformers 4.33.0 or later.
If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:
```shell
pip3 uninstall -y transformers
pip3 install git+https://github.com/huggingface/transformers.git
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/Llama-2-13B-GPTQ"
# To use a different branch, change revision
# For example: revision="main"
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'''{prompt}
'''
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 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**: 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: Meta's Llama 2 13B
# **Llama 2**
Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 13B pretrained model, converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.
## Model Details
*Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept our License before requesting access here.*
Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.
**Model Developers** Meta
**Variations** Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations.
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.
||Training Data|Params|Content Length|GQA|Tokens|LR|
|---|---|---|---|---|---|---|
|Llama 2|*A new mix of publicly available online data*|7B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|13B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|70B|4k|✔|2.0T|1.5 x 10<sup>-4</sup>|
*Llama 2 family of models.* Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models - 70B -- use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Dates** Llama 2 was trained between January 2023 and July 2023.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
**Research Paper** ["Llama-2: Open Foundation and Fine-tuned Chat Models"](arxiv.org/abs/2307.09288)
## Intended Use
**Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
To get the expected features and performance for the chat versions, a specific formatting needs to be followed, including the `INST` and `<<SYS>>` tags, `BOS` and `EOS` tokens, and the whitespaces and breaklines in between (we recommend calling `strip()` on inputs to avoid double-spaces). See our reference code in github for details: [`chat_completion`](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L212).
**Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Meta’s sustainability program.
||Time (GPU hours)|Power Consumption (W)|Carbon Emitted(tCO<sub>2</sub>eq)|
|---|---|---|---|
|Llama 2 7B|184320|400|31.22|
|Llama 2 13B|368640|400|62.44|
|Llama 2 70B|1720320|400|291.42|
|Total|3311616||539.00|
**CO<sub>2</sub> emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023.
## Evaluation Results
In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library.
|Model|Size|Code|Commonsense Reasoning|World Knowledge|Reading Comprehension|Math|MMLU|BBH|AGI Eval|
|---|---|---|---|---|---|---|---|---|---|
|Llama 1|7B|14.1|60.8|46.2|58.5|6.95|35.1|30.3|23.9|
|Llama 1|13B|18.9|66.1|52.6|62.3|10.9|46.9|37.0|33.9|
|Llama 1|33B|26.0|70.0|58.4|67.6|21.4|57.8|39.8|41.7|
|Llama 1|65B|30.7|70.7|60.5|68.6|30.8|63.4|43.5|47.6|
|Llama 2|7B|16.8|63.9|48.9|61.3|14.6|45.3|32.6|29.3|
|Llama 2|13B|24.5|66.9|55.4|65.8|28.7|54.8|39.4|39.1|
|Llama 2|70B|**37.5**|**71.9**|**63.6**|**69.4**|**35.2**|**68.9**|**51.2**|**54.2**|
**Overall performance on grouped academic benchmarks.** *Code:* We report the average pass@1 scores of our models on HumanEval and MBPP. *Commonsense Reasoning:* We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. *World Knowledge:* We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. *Reading Comprehension:* For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. *MATH:* We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1.
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama 1|7B|27.42|23.00|
|Llama 1|13B|41.74|23.08|
|Llama 1|33B|44.19|22.57|
|Llama 1|65B|48.71|21.77|
|Llama 2|7B|33.29|**21.25**|
|Llama 2|13B|41.86|26.10|
|Llama 2|70B|**50.18**|24.60|
**Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better).
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama-2-Chat|7B|57.04|**0.00**|
|Llama-2-Chat|13B|62.18|**0.00**|
|Llama-2-Chat|70B|**64.14**|0.01|
**Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.
## Ethical Considerations and Limitations
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide)
## Reporting Issues
Please report any software “bug,” or other problems with the models through one of the following means:
- Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
- Reporting problematic content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
- Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
## Llama Model Index
|Model|Llama2|Llama2-hf|Llama2-chat|Llama2-chat-hf|
|---|---|---|---|---|
|7B| [Link](https://huggingface.co/llamaste/Llama-2-7b) | [Link](https://huggingface.co/llamaste/Llama-2-7b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)|
|13B| [Link](https://huggingface.co/llamaste/Llama-2-13b) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-13b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf)|
|70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)|
|
Yntec/MangledMerge3_768 | Yntec | 2023-08-17T20:35:29Z | 428 | 4 | diffusers | [
"diffusers",
"safetensors",
"Anime",
"Art",
"Realistic",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"pmango300574",
"en",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-08-15T22:30:49Z | ---
license: creativeml-openrail-m
language:
- en
tags:
- Anime
- Art
- Realistic
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
- pmango300574
pipeline_tag: text-to-image
---
# Mangled Merge 3
768 version of this model for the inference API.
Samples and prompts by digiplay:
girl hold several small bottle of milk in chest,anime ,looking at viewer ,in garden,picnic ,honey color hair,best quality ,8k,blue dress,
girl hold several small bottle of milk in chest,anime ,looking at viewer ,in garden,picnic ,honey color hair,two ponytails,best quality ,8k,blue dress,milking cow, :D
Sample image and prompt:
pretty CUTE girl on a chair of ketchup bottles, beechwood materials. DETAILED CHIBI, Spoon, bedroom, bottle interior, Greatly drawn face, detailed hair, Magazine, iconic, 1940, from the movie, Cartoon, sharp focus. traditional atmospheric on canvas by ROSSDRAWS and Clay Mann and artgerm and leyendecker. Graceful. Crisp,
Original page:
https://civitai.com/models/5395?modelVersionId=93316
More samples by digiplay:
|
imone/Mistral_7B_with_EOT_token | imone | 2024-01-22T05:59:54Z | 428 | 5 | transformers | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-10-20T10:54:27Z | ---
license: apache-2.0
---
|
Yntec/MeinaAlter | Yntec | 2023-10-25T13:00:15Z | 428 | 3 | diffusers | [
"diffusers",
"safetensors",
"Anime",
"Landscapes",
"Female",
"Meina",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-10-25T11:36:37Z | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Anime
- Landscapes
- Female
- Meina
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
---
# Meina Alter
Original model page: https://civitai.com/models/20945?modelVersionId=24933
Sample and prompt:
summer vibrancy, Portrait of Cartoon pretty CUTE girl waiting for rain, anime fantasy illustration by tomoyuki yamasaki, DETAILED CHIBI EYES, kyoto studio, madhouse, trending on ufotable. artstation visible brushstrokes art By ROSSDRAWS and Ellen paige and charles sillem lidderdale and hayao miyazaki |
maddes8cht/mosaicml-mpt-7b-8k-instruct-gguf | maddes8cht | 2023-11-01T15:36:48Z | 428 | 1 | null | [
"gguf",
"Composer",
"MosaicML",
"llm-foundry",
"arxiv:2205.14135",
"arxiv:2108.12409",
"arxiv:2010.04245",
"license:cc-by-sa-3.0",
"region:us"
]
| null | 2023-10-28T09:34:05Z | ---
license: cc-by-sa-3.0
datasets:
- competition_math
- conceptofmind/cot_submix_original/cot_gsm8k
- knkarthick/dialogsum
- mosaicml/dolly_hhrlhf
- duorc
- tau/scrolls/qasper
- emozilla/quality
- scrolls/summ_screen_fd
- spider
tags:
- Composer
- MosaicML
- llm-foundry
inference: false
---
[]()
I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
# mpt-7b-8k-instruct - GGUF
- Model creator: [mosaicml](https://huggingface.co/mosaicml)
- Original model: [mpt-7b-8k-instruct](https://huggingface.co/mosaicml/mpt-7b-8k-instruct)
MPT-7b and MPT-30B are part of the family of Mosaic Pretrained Transformer (MPT) models, which use a modified transformer architecture optimized for efficient training and inference.
# About GGUF format
`gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.
A growing list of Software is using it and can therefore use this model.
The core project making use of the ggml library is the [llama.cpp](https://github.com/ggerganov/llama.cpp) project by Georgi Gerganov
# Quantization variants
There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:
# Legacy quants
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
## Note:
Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not *real* K-quants. More details can be found in affected model descriptions.
(This mainly refers to Falcon 7b and Starcoder models)
# K-quants
K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load.
So, if possible, use K-quants.
With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.
---
# Original Model Card:
# MPT-7B-Instruct-8k
MPT-7B-Instruct-8k is a model for long-form instruction following, especially question-answering on and summarization of longer documents.
It is built by finetuning [MPT-7B-8k](https://huggingface.co/mosaicml/mpt-7b-8k) on [Dolly HHRLHF](https://huggingface.co/datasets/mosaicml/dolly_hhrlhf) derived from the [Databricks Dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) and the [Anthropic Helpful and Harmless (HH-RLHF)](https://huggingface.co/datasets/Anthropic/hh-rlhf) datasets. It is also trained on [Competition Math](https://huggingface.co/datasets/competition_math), [Duorc](https://huggingface.co/datasets/duorc), [CoT GSM8k](https://huggingface.co/datasets/conceptofmind/cot_submix_original), [Qasper](https://huggingface.co/datasets/allenai/qasper), [Quality](https://huggingface.co/datasets/emozilla/quality), [Summ Screen FD](https://huggingface.co/datasets/tau/scrolls) and [Spider](https://huggingface.co/datasets/spider).
This is the same dataset that [MPT-30B-Instruct](https://huggingface.co/mosaicml/mpt-30b-instruct) was trained on.
* License: _CC-By-SA-3.0_
This model was trained by [MosaicML](https://www.mosaicml.com) and follows a modified decoder-only transformer architecture.
## Model Date
July 18, 2023
## Model License
_CC-By-SA-3.0_
## Documentation
* [Blog post: MPT-7B-8k](https://www.mosaicml.com/blog/long-context-mpt-7b-8k)
* [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/)
* Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)!
## How to Use
This model is best used with the MosaicML [llm-foundry repository](https://github.com/mosaicml/llm-foundry) for training and finetuning.
```python
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
'mosaicml/mpt-7b-instruct-8k',
trust_remote_code=True
)
```
Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method.
This is because we use a custom `MPT` model architecture that is not yet part of the Hugging Face `transformers` package.
`MPT` includes options for many training efficiency features such as [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), [QK LayerNorm](https://arxiv.org/abs/2010.04245), and more.
To use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision:
```python
import torch
import transformers
name = 'mosaicml/mpt-7b-instruct-8k'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.attn_config['attn_impl'] = 'triton' # change this to use triton-based FlashAttention
config.init_device = 'cuda:0' # For fast initialization directly on GPU!
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
torch_dtype=torch.bfloat16, # Load model weights in bfloat16
trust_remote_code=True
)
```
The model was trained initially with a sequence length of 2048 with an additional pretraining stage for sequence length adapation up to 8192. However, ALiBi enables users to increase the maximum sequence length even further during finetuning and/or inference. For example:
```python
import transformers
name = 'mosaicml/mpt-7b-instruct-8k'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.max_seq_len = 16384 # (input + output) tokens can now be up to 16384
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
trust_remote_code=True
)
```
This model was trained with the MPT-7B-chat tokenizer which is based on the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer and includes additional ChatML tokens.
```python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('mosaicml/mpt-7b-8k')
```
The model can then be used, for example, within a text-generation pipeline.
Note: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html).
```python
from transformers import pipeline
with torch.autocast('cuda', dtype=torch.bfloat16):
inputs = tokenizer('Here is a recipe for vegan banana bread:\n', return_tensors="pt").to('cuda')
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
# or using the HF pipeline
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0')
with torch.autocast('cuda', dtype=torch.bfloat16):
print(
pipe('Here is a recipe for vegan banana bread:\n',
max_new_tokens=100,
do_sample=True,
use_cache=True))
```
## Model Description
The architecture is a modification of a standard decoder-only transformer.
The model has been modified from a standard transformer in the following ways:
* It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf)
* It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings
* It does not use biases
| Hyperparameter | Value |
|----------------|-------|
|n_parameters | 6.7B |
|n_layers | 32 |
| n_heads | 32 |
| d_model | 4096 |
| vocab size | 50432 |
| sequence length | 2048 |
## Data Mix
The model was trained on the following data mix:
| Data Source | Number of Tokens in Source | Proportion |
|-------------|----------------------------|------------|
| competition_math | 1.6 M | 3.66% |
| cot_gsm8k | 3.36 M | 7.67% |
| dialogsum | 0.1 M | 0.23% |
| dolly_hhrlhf | 5.89 M | 13.43% |
| duorc | 7.8 M | 17.80% |
| qasper | 8.72 M | 19.90% |
| quality | 11.29 M | 25.78% |
| scrolls/summ_screen_fd | 4.97 M | 11.33% |
| spider | 0.089 M | 0.20% |
### Training Configuration
This model was trained on 8 80GB A100s for about 6.3 hours using the [MosaicML Platform](https://www.mosaicml.com/platform).
The model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the AdamW optimizer.
## Limitations and Biases
_The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_
MPT-7B-Instruct-8k can produce factually incorrect output, and should not be relied on to produce factually accurate information.
MPT-7B-Instruct-8k was trained on various public datasets.
While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
## Acknowledgements
This model was finetuned by the MosaicML NLP team.
## Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
## MosaicML Platform
If you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://www.mosaicml.com/get-started?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-7b-8k).
## Citation
Please cite this model using the following format:
```
@online{MosaicML2023Introducing,
author = {MosaicML NLP Team},
title = {Introducing MPT-30B: Raising the bar
for open-source foundation models},
year = {2023},
url = {www.mosaicml.com/blog/mpt-30b},
note = {Accessed: 2023-06-22},
urldate = {2023-06-22}
}
```
***End of original Model File***
---
## Please consider to support my work
**Coming Soon:** I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.
<center>
[](https://maddes8cht.github.io)
[](https://stackexchange.com/users/26485911)
[](https://github.com/maddes8cht)
[](https://huggingface.co/maddes8cht)
[](https://twitter.com/maddes1966)
</center> |
openai/consistency-decoder | openai | 2023-11-09T13:51:12Z | 428 | 42 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"license:mit",
"region:us"
]
| null | 2023-11-09T10:50:49Z | ---
library_name: diffusers
tags:
- stable-diffusion
license: mit
---
## Consistency Decoder
This is a decoder that can be used to improve decoding for Stable Diffusion VAEs. To know more, refer to the [DALL-E 3 technical report](https://cdn.openai.com/papers/dall-e-3.pdf).
To original code repository can be found [here](https://github.com/openai/consistencydecoder).
## Usage in 🧨 diffusers
```python
import torch
from diffusers import DiffusionPipeline, ConsistencyDecoderVAE
vae = ConsistencyDecoderVAE.from_pretrained("openai/consistency-decoder", torch_dtype=pipe.torch_dtype)
pipe = StableDiffusionPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5", vae=vae, torch_dtype=torch.float16
).to("cuda")
pipe("horse", generator=torch.manual_seed(0)).images
```
## Results
_(Taken from the original [code repository](https://github.com/openai/consistencydecoder))_
## Examples
Original Image | GAN Decoder | Consistency Decoder |
:---:|:---:|:---:|
 |  |  |
 |  |  |
 |  |  |
|
nvidia/nemotron-3-8b-chat-4k-rlhf | nvidia | 2024-02-09T04:59:22Z | 428 | 23 | nemo | [
"nemo",
"nvidia",
"nemotron-3",
"8B",
"text-generation",
"en",
"ar",
"az",
"bg",
"bn",
"ca",
"cs",
"da",
"de",
"el",
"es",
"et",
"fa",
"fi",
"fr",
"gl",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"is",
"it",
"ka",
"kk",
"kn",
"ko",
"lt",
"lv",
"mk",
"ml",
"mr",
"ne",
"nl",
"no",
"pl",
"pt",
"ro",
"ru",
"sk",
"sl",
"sq",
"sr",
"sv",
"ta",
"te",
"tr",
"uk",
"ur",
"vi",
"ja",
"zh",
"license:other",
"region:us"
]
| text-generation | 2023-11-14T22:56:50Z | ---
license: other
license_name: nv-ai-foundation-models-license
license_link: https://developer.nvidia.com/downloads/nv-ai-foundation-models-license
library_name: nemo
extra_gated_heading: Access Nemotron 3 8B on Hugging Face
extra_gated_description: >-
To download this model, you must agree to the terms of the [NVIDIA AI Foundation Models Community License Agreement](https://developer.nvidia.com/downloads/nv-ai-foundation-models-license).
extra_gated_fields:
I agree to share my name, email address and username with NVIDIA: checkbox
geo: ip_location
language:
- "en"
- "ar"
- "az"
- "bg"
- "bn"
- "ca"
- "cs"
- "da"
- "de"
- "el"
- "es"
- "et"
- "fa"
- "fi"
- "fr"
- "gl"
- "he"
- "hi"
- "hr"
- "hu"
- "hy"
- "id"
- "is"
- "it"
- "ka"
- "kk"
- "kn"
- "ko"
- "lt"
- "lv"
- "mk"
- "ml"
- "mr"
- "ne"
- "nl"
- "no"
- "pl"
- "pt"
- "ro"
- "ru"
- "sk"
- "sl"
- "sq"
- "sr"
- "sv"
- "ta"
- "te"
- "tr"
- "uk"
- "ur"
- "vi"
- "ja"
- "zh"
pipeline_tag: text-generation
inference: false
fine-tuning: true
tags:
- nvidia
- nemotron-3
- 8B
---
# Nemotron-3-8B-Chat-4k-RLHF
## Model Overview
### License
The use of this model is governed by the [NVIDIA AI Foundation Models Community License Agreement](https://developer.nvidia.com/downloads/nv-ai-foundation-models-license).
### Description
Nemotron-3-8B-Chat-4k-RLHF is a large language model instruct-tuned on an 8B base model. It takes input with context length up to 4,096 tokens.The model has been further fine-tuned for instruction following using Reinforcement Learning from Human Feedback (RLHF).
Nemotron-3-8B-Chat-4k-RLHF is part of Nemotron-3, which is a family of enterprise ready generative text models compatible with [NVIDIA NeMo Framework](https://www.nvidia.com/en-us/ai-data-science/generative-ai/nemo-framework/). For other models in this collection, see the [collections page](https://huggingface.co/collections/nvidia/nemotron-3-8b-6553adeb226f6ab4ffc356f9).
NVIDIA NeMo is an end-to-end, cloud-native platform to build, customize, and deploy generative AI models anywhere. It includes training and inferencing frameworks, guardrailing toolkits, data curation tools, and pretrained models, offering enterprises an easy, cost-effective, and fast way to adopt generative AI. To get access to NeMo Framework, please sign up at [this link](https://developer.nvidia.com/nemo-framework/join).
### References
[Announcement Blog](https://developer.nvidia.com/blog/nvidia-ai-foundation-models-build-custom-enterprise-chatbots-and-co-pilots-with-production-ready-llms/)
### Model Architecture
**Architecture Type:** Transformer
**Network Architecture:** Generative Pre-Trained Transformer (GPT-3)
### Prompt Format
Note: For Nemotron-3-8B-Chat-4k-RLHF we recommend keeping the system prompt empty.
#### Single Turn
```text
<extra_id_0>System
<extra_id_1>User
{prompt}
<extra_id_1>Assistant
```
#### Multi-Turn or Few-shot
```text
<extra_id_0>System
<extra_id_1>User
{prompt 1}
<extra_id_1>Assistant
{response 1}
<extra_id_1>User
{prompt 2}
<extra_id_1>Assistant
{response 2}
...
<extra_id_1>User
{prompt N}
<extra_id_1>Assistant
```
#### Example prompt formation code
```python
PROMPT_TEMPLATE = """<extra_id_0>System
{system}
<extra_id_1>User
{prompt}
<extra_id_1>Assistant
"""
system = ""
prompt = "Write a poem on NVIDIA in the style of Shakespeare"
prompt = PROMPT_TEMPLATE.format(prompt=prompt, system=system)
print(prompt)
```
### Software Integration
**Runtime Engine(s):**
NVIDIA AI Enterprise
**Toolkit:**
NeMo Framework
To get access to NeMo Framework, please sign up at [this link](https://developer.nvidia.com/nemo-framework/join). See [NeMo inference container](https://registry.ngc.nvidia.com/orgs/ea-bignlp/teams/ga-participants/containers/nemofw-inference) documentation for details on how to setup and deploy an inference server with NeMo.
**Sample Inference Code:**
```python
from nemo.deploy import NemoQuery
# In this case, we run inference on the same machine
nq = NemoQuery(url="localhost:8000", model_name="Nemotron-3-8B-Chat-4K-RLHF")
# See above for prompt format
output = nq.query_llm(prompts=[prompt], max_output_token=200, top_k=1, top_p=0.0, temperature=0.1)
# NOTE: Chat models require post-processing the output since the `NemoQuery` API
# does not support stopping generation on the special <extra_id_1> token.
output = [[s.split("<extra_id_1>", 1)[0].strip() for s in out] for out in output]
print(output)
```
**Supported Hardware:**
- H100
- A100 80GB, A100 40GB
### Model Version(s)
`Nemotron-3-8B-chat-4k-rlhf-BF16-1`
## Dataset
NVIDIA models are trained on a diverse set of public and proprietary datasets. This model was trained on a dataset containing 3.5 Trillion tokens of text. The dataset contains 53 different human languages and 37 programming languages. NVIDIA is committed to the responsible development of large language models and conducts reviews of all datasets included in training.
## Evaluation
MT Bench Score
| Category | Score |
|-------------------|--------------|
| Total | 5.91 |
| Writing | 8.25 |
| Roleplay | 7.5 |
| Extraction | 5.5 |
| Stem | 7.9 |
| Humanities | 9.12 |
| Reasoning | 3.85 |
| Math | 2.35 |
| Coding | 2.8 |
## Intended use
Nemotron-3-8B-chat-4k-rlhf is best for chat use cases including Question and Answering, Search, Summarization following instructions.
### Ethical use
Technology can have a profound impact on people and the world, and NVIDIA is committed to enabling trust and transparency in AI development. NVIDIA encourages users to adopt principles of AI ethics and trustworthiness to guide your business decisions by following the guidelines in the [NVIDIA AI Foundation Models Community License Agreement](https://developer.nvidia.com/downloads/nv-ai-foundation-models-license).
## Limitations
- The model was trained on data that contains toxic language and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts.
- The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.
|
preechanon/mt5-base-thaisum-text-summarization | preechanon | 2024-06-04T11:10:06Z | 428 | 1 | transformers | [
"transformers",
"safetensors",
"mt5",
"text2text-generation",
"summarization",
"mT5",
"th",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| summarization | 2023-12-22T15:17:38Z | ---
tags:
- summarization
- mT5
language:
- th
widget:
- text: "ผมกินตับหมูดิบแล้วหมดสติไป พอฟื้นอีกทีในต่างโลกดันกลายเป็นหมูซะงั้น! คนที่ช่วยผมเอาไว้คือเจส สาวน้อยผู้อ่านใจคนได้ อู๊ด! น่ารัก! ระดับสายตาหมูทำให้เห็นอะไรสีขาวบริสุทธิ์แวบๆ แจ่มเลย... “เอ่อ ฉันได้ยินเสียงในใจของคุณนะคะ…” ฉิบแล้ว! ความมักมากรั่วไหลหมด! แม้ว่าชีวิตประสาหมูที่มีเด็กสาวผู้อ่อนโยนคอยดูแลจะไม่เลว ผมก็ตัดสินใจมุ่งหน้าสู่นครหลวงพร้อมกับเจสเพื่อหาทางกลับเป็นมนุษย์ การเดินทางแสนรื่นรมย์จึงเริ่มต้นขึ้น... แต่ไหงเราถึงถูกตามล่าเอาชีวิตล่ะเนี่ย!?"
example_title: "Novel"
- text: "พริ้ง คนเริงเมือง, ผลิตโดยบริษัท มีเดีย สตูดิโอ ร่วมกับ ,นีโน่ บราเดอร์ส, ที่ตอนนี้เดินทางมาถึงตอนอวสานแล้ว โดยวันนี้ถึงตอนที่, พริ้ง (จั๊กจั่น–อคัมย์สิริ), ฆ่าสามีที่ 6 ,หลวงเสนาะ, ตายไปเรียบร้อย ก็ถึงคราวที่จะทำตามใจตัวเองด้วยการอ่อย ,เปรมฤทัย (โตนนท์), ลูกชายคนเดียวของ ,หลวงเสนาะ, ให้กลายมาเป็นสามีของตัวเองสมใจอยากเสียที,งานนี้สกิลการอ่อยมาเต็ม เริ่มจากเดินมาหา, เปรมฤทัย, ที่ห้องก่อนจะบอกว่าไม่สามารถทำใจให้เลิกรักได้เลย จนมาถึงวันนี้วันที่สามารถเปิดใจได้แล้ว วันที่เราจะรักกันได้แล้ว ทำไมต้องห้ามใจอีก, เปรมฤทัย, ได้ยินแบบนี้ก็หวั่นไหวคล้อยตามไม่ห้ามใจปล่อยตัวให้ความเสน่หาเข้าครอบงำ,ฉากนี้ ผกก. ,บุ๋ม–รัญญา, ยกกองไปถ่ายทำที่บ้านท่าไม้ จ.สมุทรสงคราม ก่อนเริ่มถ่ายจริง ,บุ๋ม, เรียกทั้ง, จั๊กจั่น, และ ,โตนนท์, มาทำสมาธิ และบิ้วท์ให้ทั้งคู่เข้าใจในความต้องการที่ทั้งตัวละคร ,พริ้ง, และ ,เปรมฤทัย, ต้องการปลดปล่อยออกมา เมื่อทั้งคู่เข้าใจบทแล้วเริ่มถ่ายจริง ,จั๊กจั่น, เล่นเต็มที่ไม่ยั้ง พรั่งพรูความรู้สึกที่มีออกมาพร้อมน้ำตาเรียกความสงสาร ก่อนจะโน้มจูบกันอย่างดูดดื่ม งานนี้จูบจริงไม่ใช้สแตนด์อินใดๆ ติดตามชมฉากแซ่บทิ้งทวน คืนวันพฤหัสบดีนี้ ทางช่อง 7.,ติดตามอ่านนิยายเรื่อง พริ้ง คนเริงเมือง ได้ที่นี่"
example_title: "Thai movie"
- text: "หนุ่มใหญ่วัย 49 ปี เสียชีวิตคาบ้านย่านปากเกร็ด สภาพมีเลือดออกปากกองใหญ่ ข้างศพมีไซริงค์ฉีดยา เพื่อนบอกมาหาที่บ้าน เห็นว่าฉีดไอซ์ไป 2 เข็ม ก่อนคลุ้มคลั่งทำลายข้าวของ ล้มคว่ำหน้าแน่นิ่ง ,เวลา 22.00 น. วันที่ 6 ส.ค. ร.ต.ท.พันธ์พงศ์ ภูริวัฒนพงศ์ รอง สว.(สอบสวน) สภ.ปากเกร็ด จ.นนทบุรี รับแจ้งมีผู้เสียชีวิตภายในบ้านเลขที่ 77/489 หมู่ 1 หมู่บ้านดวงแก้ว ถนนติวานนท์ ต.บ้านใหม่ ไปสอบสวนพร้อมด้วย พ.ต.อ.พงศ์จักร ปรีชาการุณพงศ์ ผกก. พ.ต.ท.นภธร วาชัยยุง รอง ผกก.ป สภ.ปากเกร็ด แพทย์สถาบันนิติวิทยาศาสตร์ และเจ้าหน้าที่กู้ภัยมูลนิธิป่อเต็กตึ๊ง ,ที่เกิดเหตุเป็นบ้านทาวน์เฮาส์ 2 ชั้น บนชั้น 2 พบศพ นายพงษ์ธนกร หรือเอ อุ่นทน อายุ 49 ปี เจ้าของบ้าน นอนคว่ำหน้าเสียชีวิตอยู่บนพื้น ในสภาพเลือดออกปาก ข้างศพพบไซริงค์ฉีดยาตกอยู่ ทางเจ้าหน้าที่จึงเก็บไว้เป็นหลักฐาน นอกจากนี้ข้าวของภายในห้องล้มระเนระนาดกระจัดกระจาย ,จากการสอบปากคำ นายเอ๋ (นามสมมติ) อายุ 31 ปี ให้การว่า ตนเป็นเพื่อนกับผู้เสียชีวิต ก่อนเกิดเหตุได้เดินทางมาหาที่บ้านเห็นผู้เสียชีวิตฉีดยาไอซ์เข้าไป 2 เข็ม จากนั้นผู้เสียชีวิตมีอาการคลุ้มคลั่งทำลายข้าวของก่อนนอนคว่ำหน้าแน่นิ่งไป กระทั่งเสียชีวิตในที่สุด เบื้องต้นเจ้าหน้าที่คาดว่าสาเหตุการเสียชีวิตน่าจะเกิดจากการเสพยาเกินขนาด อย่างไรก็ตามจะได้สอบสวนหาสาเหตุที่แท้จริงอีกครั้ง"
example_title: "Crime news"
inference:
parameters:
min_length: 40
max_length: 140
---
# mt5-base-thaisum
This repository contains the finetuned mT5-base model for Thai sentence summarization. The architecture of the model is based on mT5 model and fine-tuned on text-summarization pairs in Thai.
### Example
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch
tokenizer = AutoTokenizer.from_pretrained("preechanon/mt5-base-thaisum-text-summarization")
model = AutoModelForSeq2SeqLM.from_pretrained("preechanon/mt5-base-thaisum-text-summarization")
new_input_string = "ข้อความที่ต้องการ"
input_ = tokenizer(new_input_string, truncation=True, max_length=1024, return_tensors="pt")
with torch.no_grad():
preds = model.generate(
input_['input_ids'].to('cpu'),
num_beams=15,
num_return_sequences=1,
no_repeat_ngram_size=1,
remove_invalid_values=True,
max_length=140,
)
summary = tokenizer.decode(preds[0], skip_special_tokens=True)
summary
```
### Score
- Rouge1: 0.488931
- Rouge2: 0.309732
- Rougel: 0.425490
- Rougelsum: 0.444359
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-04
- train_batch_size: 8
- eval_batch_size: 1
- seed: 42
- optimizer: AdamW with betas=(0.9,0.999), epsilon=1e-08 and weight_decay=0.1
- warmup step: 5000
- lr_scheduler_type: linear
- num_epochs: 6
- gradient_accumulation_steps: 4
### Framework versions
- Transformers 4.36.1
- Pytorch 2.1.2
### Resource Funding
NSTDA Supercomputer center (ThaiSC) and the National e-Science Infrastructure Consortium for their support of computer facilities.
### Citation
If you use "satjawat/pegasus-x-thai-sum" in your project or publication, please cite the model as follows:
```
ปรีชานนท์ ชาติไทย และ สัจจวัจน์ ส่งเสริม. (2567),
การสรุปข้อความข่าวภาษาไทยด้วยโครงข่ายประสาทเทียม (Thai News Text Summarization Using Neural Network),
วิทยาศาสตรบัณฑิต (วทบ.):ขอนแก่น, มหาวิทยาลัยขอนแก่น
``` |
TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF | TheBloke | 2023-12-31T21:35:15Z | 428 | 5 | transformers | [
"transformers",
"gguf",
"tinyllama",
"en",
"dataset:cerebras/SlimPajama-627B",
"dataset:bigcode/starcoderdata",
"base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
"license:apache-2.0",
"region:us"
]
| null | 2023-12-31T21:19:12Z | ---
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
inference: false
language:
- en
license: apache-2.0
model_creator: TinyLlama
model_name: Tinyllama 1.1B Intermediate Step 1431K 3T
model_type: tinyllama
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 -->
# Tinyllama 1.1B Intermediate Step 1431K 3T - GGUF
- Model creator: [TinyLlama](https://huggingface.co/TinyLlama)
- Original model: [Tinyllama 1.1B Intermediate Step 1431K 3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T)
<!-- description start -->
## Description
This repo contains GGUF format model files for [TinyLlama's Tinyllama 1.1B Intermediate Step 1431K 3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T).
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
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF)
* [TinyLlama's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T)
<!-- 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q2_K.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q2_K.gguf) | Q2_K | 2 | 0.48 GB| 2.98 GB | smallest, significant quality loss - not recommended for most purposes |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q3_K_S.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q3_K_S.gguf) | Q3_K_S | 3 | 0.50 GB| 3.00 GB | very small, high quality loss |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q3_K_M.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q3_K_M.gguf) | Q3_K_M | 3 | 0.55 GB| 3.05 GB | very small, high quality loss |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q3_K_L.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q3_K_L.gguf) | Q3_K_L | 3 | 0.59 GB| 3.09 GB | small, substantial quality loss |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q4_0.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q4_0.gguf) | Q4_0 | 4 | 0.64 GB| 3.14 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q4_K_S.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q4_K_S.gguf) | Q4_K_S | 4 | 0.64 GB| 3.14 GB | small, greater quality loss |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q4_K_M.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q4_K_M.gguf) | Q4_K_M | 4 | 0.67 GB| 3.17 GB | medium, balanced quality - recommended |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q5_0.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q5_0.gguf) | Q5_0 | 5 | 0.77 GB| 3.27 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q5_K_S.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q5_K_S.gguf) | Q5_K_S | 5 | 0.77 GB| 3.27 GB | large, low quality loss - recommended |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q5_K_M.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q5_K_M.gguf) | Q5_K_M | 5 | 0.78 GB| 3.28 GB | large, very low quality loss - recommended |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q6_K.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q6_K.gguf) | Q6_K | 6 | 0.90 GB| 3.40 GB | very large, extremely low quality loss |
| [tinyllama-1.1b-intermediate-step-1431k-3t.Q8_0.gguf](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF/blob/main/tinyllama-1.1b-intermediate-step-1431k-3t.Q8_0.gguf) | Q8_0 | 8 | 1.17 GB| 3.67 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/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF and below it, a specific filename to download, such as: tinyllama-1.1b-intermediate-step-1431k-3t.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/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF tinyllama-1.1b-intermediate-step-1431k-3t.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/TinyLlama-1.1B-intermediate-step-1431k-3T-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/TinyLlama-1.1B-intermediate-step-1431k-3T-GGUF tinyllama-1.1b-intermediate-step-1431k-3t.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 tinyllama-1.1b-intermediate-step-1431k-3t.Q4_K_M.gguf --color -c 2048 --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 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. 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="./tinyllama-1.1b-intermediate-step-1431k-3t.Q4_K_M.gguf", # Download the model file first
n_ctx=2048, # 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="./tinyllama-1.1b-intermediate-step-1431k-3t.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: TinyLlama's Tinyllama 1.1B Intermediate Step 1431K 3T
<div align="center">
# 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.
<div align="center">
<img src="./TinyLlama_logo.png" width="300"/>
</div>
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 Collection
This collection contains all checkpoints after the 1T fix. Branch name indicates the step and number of tokens seen.
#### Eval
| Model | Pretrain Tokens | HellaSwag | Obqa | WinoGrande | ARC_c | ARC_e | boolq | piqa | avg |
|-------------------------------------------|-----------------|-----------|------|------------|-------|-------|-------|------|-----|
| Pythia-1.0B | 300B | 47.16 | 31.40| 53.43 | 27.05 | 48.99 | 60.83 | 69.21 | 48.30 |
| TinyLlama-1.1B-intermediate-step-50K-104b | 103B | 43.50 | 29.80| 53.28 | 24.32 | 44.91 | 59.66 | 67.30 | 46.11|
| TinyLlama-1.1B-intermediate-step-240k-503b| 503B | 49.56 |31.40 |55.80 |26.54 |48.32 |56.91 |69.42 | 48.28 |
| TinyLlama-1.1B-intermediate-step-480k-1007B | 1007B | 52.54 | 33.40 | 55.96 | 27.82 | 52.36 | 59.54 | 69.91 | 50.22 |
| TinyLlama-1.1B-intermediate-step-715k-1.5T | 1.5T | 53.68 | 35.20 | 58.33 | 29.18 | 51.89 | 59.08 | 71.65 | 51.29 |
| TinyLlama-1.1B-intermediate-step-955k-2T | 2T | 54.63 | 33.40 | 56.83 | 28.07 | 54.67 | 63.21 | 70.67 | 51.64 |
| TinyLlama-1.1B-intermediate-step-1195k-2.5T | 2.5T | 58.96 | 34.40 | 58.72 | 31.91 | 56.78 | 63.21 | 73.07 | 53.86|
| TinyLlama-1.1B-intermediate-step-1431k-3T | 3T | 59.20 | 36.00 | 59.12 | 30.12 | 55.25 | 57.83 | 73.29 | 52.99|
<!-- original-model-card end -->
|
InnerI/I-OpenPipe-NH2-Solar-7B-slerp | InnerI | 2024-03-08T22:05:58Z | 428 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"OpenPipe/mistral-ft-optimized-1218",
"NousResearch/Nous-Hermes-2-SOLAR-10.7B",
"conversational",
"base_model:OpenPipe/mistral-ft-optimized-1218",
"base_model:NousResearch/Nous-Hermes-2-SOLAR-10.7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-02-14T00:13:30Z | ---
tags:
- merge
- mergekit
- lazymergekit
- OpenPipe/mistral-ft-optimized-1218
- NousResearch/Nous-Hermes-2-SOLAR-10.7B
base_model:
- OpenPipe/mistral-ft-optimized-1218
- NousResearch/Nous-Hermes-2-SOLAR-10.7B
license: apache-2.0
---
# I-OpenPipe-NH2-Solar-7B-slerp
I-OpenPipe-NH2-Solar-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
* [NousResearch/Nous-Hermes-2-SOLAR-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: OpenPipe/mistral-ft-optimized-1218
layer_range: [0, 32]
- model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
layer_range: [0, 32]
merge_method: slerp
base_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "InnerI/I-OpenPipe-NH2-Solar-7B-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
cais/zephyr_7b_r2d2 | cais | 2024-02-26T21:09:32Z | 428 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-02-26T21:07:10Z | ---
license: mit
---
|
mradermacher/Mixtral_AI_Cyber_2.0-GGUF | mradermacher | 2024-05-06T05:43:41Z | 428 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"128k_Context",
"chemistry",
"biology",
"music",
"code",
"medical",
"not-for-all-audiences",
"text-generation-inference",
"Cyber-Series",
"en",
"base_model:LeroyDyer/Mixtral_AI_Cyber_2.0",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-03-29T01:37:12Z | ---
base_model: LeroyDyer/Mixtral_AI_Cyber_2.0
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- mergekit
- merge
- 128k_Context
- chemistry
- biology
- music
- code
- medical
- not-for-all-audiences
- text-generation-inference
- Cyber-Series
---
## About
static quants of https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_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_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.Q2_K.gguf) | Q2_K | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.IQ3_M.gguf) | IQ3_M | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_2.0.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Cyber_2.0-GGUF/resolve/main/Mixtral_AI_Cyber_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 -->
|
ChristianAzinn/gte-base-gguf | ChristianAzinn | 2024-04-07T22:30:00Z | 428 | 0 | sentence-transformers | [
"sentence-transformers",
"gguf",
"mteb",
"bert",
"sentence-similarity",
"Sentence Transformers",
"feature-extraction",
"en",
"arxiv:2308.03281",
"base_model:thenlper/gte-base",
"license:mit",
"autotrain_compatible",
"region:us"
]
| feature-extraction | 2024-04-07T20:18:54Z | ---
base_model: thenlper/gte-base
inference: false
language:
- en
license: mit
model_creator: thenlper
model_name: gte-base
model_type: bert
quantized_by: ChristianAzinn
library_name: sentence-transformers
pipeline_tag: feature-extraction
tags:
- mteb
- bert
- gguf
- sentence-similarity
- sentence-transformers
- Sentence Transformers
---
# gte-base-gguf
Model creator: [thenlper](https://huggingface.co/thenlper)
Original model: [gte-base](https://huggingface.co/thenlper/gte-base)
## Original Description
General Text Embeddings (GTE) model. [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://arxiv.org/abs/2308.03281)
The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including [GTE-large](https://huggingface.co/thenlper/gte-large), [GTE-base](https://huggingface.co/thenlper/gte-base), and [GTE-small](https://huggingface.co/thenlper/gte-small). The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including **information retrieval**, **semantic textual similarity**, **text reranking**, etc.
## Description
This repo contains GGUF format files for the gte-base embedding model.
These files were converted and quantized with llama.cpp [PR 5500](https://github.com/ggerganov/llama.cpp/pull/5500), commit [34aa045de](https://github.com/ggerganov/llama.cpp/pull/5500/commits/34aa045de44271ff7ad42858c75739303b8dc6eb), on a consumer RTX 4090.
This model supports up to 512 tokens of context.
## Compatibility
These files are compatible with [llama.cpp](https://github.com/ggerganov/llama.cpp) as of commit [4524290e8](https://github.com/ggerganov/llama.cpp/commit/4524290e87b8e107cc2b56e1251751546f4b9051), as well as [LM Studio](https://lmstudio.ai/) as of version 0.2.19.
# Meta-information
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The 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>
## Provided Files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| Name | Quant method | Bits | Size | Use case |
| [gte-base.Q2_K.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q2_K.gguf) | Q2_K | 2 | 54.2 MB | smallest, significant quality loss - not recommended for most purposes |
| [gte-base.Q3_K_S.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q3_K_S.gguf) | Q3_K_S | 3 | 58.5 MB | very small, high quality loss |
| [gte-base.Q3_K_M.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q3_K_M.gguf) | Q3_K_M | 3 | 64.6 MB | very small, high quality loss |
| [gte-base.Q3_K_L.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q3_K_L.gguf) | Q3_K_L | 3 | 69.5 MB | small, substantial quality loss |
| [gte-base.Q4_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q4_0.gguf) | Q4_0 | 4 | 69.8 MB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [gte-base.Q4_K_S.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q4_K_S.gguf) | Q4_K_S | 4 | 71 MB | small, greater quality loss |
| [gte-base.Q4_K_M.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q4_K_M.gguf) | Q4_K_M | 4 | 74.4 MB | medium, balanced quality - recommended |
| [gte-base.Q5_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q5_0.gguf) | Q5_0 | 5 | 80.4 MB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [gte-base.Q5_K_S.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q5_K_S.gguf) | Q5_K_S | 5 | 80.4 MB | large, low quality loss - recommended |
| [gte-base.Q5_K_M.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q5_K_M.gguf) | Q5_K_M | 5 | 82.8 MB | large, very low quality loss - recommended |
| [gte-base.Q6_K.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q6_K.gguf) | Q6_K | 6 | 91.7 MB | very large, extremely low quality loss |
| [gte-base.Q8_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q8_0.gguf) | Q8_0 | 8 | 118 MB | very large, extremely low quality loss - recommended |
| [gte-base.Q8_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base_fp16.gguf) | FP16 | 16 | 219 MB | enormous, pretty much the original model - not recommended |
| [gte-base.Q8_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base_fp32.gguf) | FP32 | 32 | 436 MB | enormous, pretty much the original model - not recommended |
# Examples
## Example Usage with `llama.cpp`
To compute a single embedding, build llama.cpp and run:
```shell
./embedding -ngl 99 -m [filepath-to-gguf].gguf -p 'search_query: What is TSNE?'
```
You can also submit a batch of texts to embed, as long as the total number of tokens does not exceed the context length. Only the first three embeddings are shown by the `embedding` example.
`texts.txt`:
```
search_query: What is TSNE?
search_query: Who is Laurens Van der Maaten?
```
Compute multiple embeddings:
```shell
./embedding -ngl 99 -m [filepath-to-gguf].gguf -f texts.txt
```
## Example Usage with LM Studio
Download the 0.2.19 beta build from here: [Windows](https://releases.lmstudio.ai/windows/0.2.19/beta/LM-Studio-0.2.19-Setup-Preview-1.exe) [MacOS](https://releases.lmstudio.ai/mac/arm64/0.2.19/beta/LM-Studio-darwin-arm64-0.2.19-Preview-1.zip) [Linux](https://releases.lmstudio.ai/linux/0.2.19/beta/LM_Studio-0.2.19-Preview-1.AppImage)
Once installed, open the app. The home should look like this:
Search for either "ChristianAzinn" in the main search bar or go to the "Search" tab on the left menu and search the name there.
Select your model from those that appear (this example uses `bge-small-en-v1.5-gguf`) and select which quantization you want to download. Since this model is pretty small, I recommend Q8_0, if not f16/32. Generally, the lower you go in the list (or the bigger the number gets), the larger the file and the better the performance.
You will see a green checkmark and the word "Downloaded" once the model has successfully downloaded, which can take some time depending on your network speeds.
Once this model is finished downloading, navigate to the "Local Server" tab on the left menu and open the loader for text embedding models. This loader does not appear before version 0.2.19, so ensure you downloaded the correct version.
Select the model you just downloaded from the dropdown that appears to load it. You may need to play with configuratios in the right-side menu, such as GPU offload if it doesn't fit entirely into VRAM.
All that's left to do is to hit the "Start Server" button:
And if you see text like that shown below in the console, you're good to go! You can use this as a drop-in replacement for the OpenAI embeddings API in any application that requires it, or you can query the endpoint directly to test it out.
Example curl request to the API endpoint:
```shell
curl http://localhost:1234/v1/embeddings \
-H "Content-Type: application/json" \
-d '{
"input": "Your text string goes here",
"model": "model-identifier-here"
}'
```
For more information, see the LM Studio [text embedding documentation](https://lmstudio.ai/docs/text-embeddings).
## Acknowledgements
Thanks to the LM Studio team and everyone else working on open-source AI.
This README is inspired by that of [nomic-ai-embed-text-v1.5-gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-gguf), another excellent embedding model, and those of the legendary [TheBloke](https://huggingface.co/TheBloke). |
mradermacher/vidalet-alpha-GGUF | mradermacher | 2024-05-06T04:57:17Z | 428 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:MarcOrfilaCarreras/vidalet-alpha",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-14T03:38:19Z | ---
base_model: MarcOrfilaCarreras/vidalet-alpha
language:
- en
library_name: transformers
quantized_by: mradermacher
tags: []
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/MarcOrfilaCarreras/vidalet-alpha
<!-- 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/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.Q2_K.gguf) | Q2_K | 1.3 | |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.IQ3_XS.gguf) | IQ3_XS | 1.3 | |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.Q3_K_S.gguf) | Q3_K_S | 1.4 | |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.IQ3_S.gguf) | IQ3_S | 1.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.IQ3_M.gguf) | IQ3_M | 1.4 | |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.Q3_K_L.gguf) | Q3_K_L | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.IQ4_XS.gguf) | IQ4_XS | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.Q5_K_S.gguf) | Q5_K_S | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.Q5_K_M.gguf) | Q5_K_M | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.Q6_K.gguf) | Q6_K | 2.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/vidalet-alpha-GGUF/resolve/main/vidalet-alpha.Q8_0.gguf) | Q8_0 | 2.8 | 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 -->
|
ResplendentAI/Aura_v3_7B | ResplendentAI | 2024-04-18T04:26:11Z | 428 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"base_model:ResplendentAI/Paradigm_7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-18T03:53:04Z | ---
base_model:
- ResplendentAI/Paradigm_7B
- jeiku/selfbot_256_mistral
- ResplendentAI/Paradigm_7B
- jeiku/Theory_of_Mind_Mistral
- ResplendentAI/Paradigm_7B
- jeiku/Alpaca_NSFW_Shuffled_Mistral
- ResplendentAI/Paradigm_7B
- ResplendentAI/Paradigm_7B
- jeiku/Luna_LoRA_Mistral
- ResplendentAI/Paradigm_7B
- jeiku/Re-Host_Limarp_Mistral
library_name: transformers
license: apache-2.0
language:
- en
---
# Aura v3
Aura v3 is an improvement with a significantly more steerable writing style. Out of the box it will prefer poetic prose, but if instructed, it can adopt a more approachable style. This iteration has erotica, RP data and NSFW pairs to provide a more compliant mindset.
I recommend keeping the temperature around 1.5 or lower with a Min P value of 0.05. This model can get carried away with prose at higher temperature. I will say though that the prose of this model is distinct from the GPT 3.5/4 variant, and lends an air of humanity to the outputs. I am aware that this model is overfit, but that was the point of the entire exercise.
If you have trouble getting the model to follow an asterisks/quote format, I recommend asterisks/plaintext instead. This model skews toward shorter outputs, so be prepared to lengthen your introduction and examples if you want longer outputs.
This model responds best to ChatML for multiturn conversations.
This model, like all other Mistral based models, is compatible with a Mistral compatible mmproj file for multimodal vision capabilities in KoboldCPP. |
RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf | RichardErkhov | 2024-05-15T23:25:19Z | 428 | 0 | null | [
"gguf",
"region:us"
]
| null | 2024-05-15T21:51:43Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Panda-7B-v0.1 - GGUF
- Model creator: https://huggingface.co/NeuralNovel/
- Original model: https://huggingface.co/NeuralNovel/Panda-7B-v0.1/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Panda-7B-v0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q2_K.gguf) | Q2_K | 2.53GB |
| [Panda-7B-v0.1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
| [Panda-7B-v0.1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.IQ3_S.gguf) | IQ3_S | 2.96GB |
| [Panda-7B-v0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
| [Panda-7B-v0.1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.IQ3_M.gguf) | IQ3_M | 3.06GB |
| [Panda-7B-v0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q3_K.gguf) | Q3_K | 3.28GB |
| [Panda-7B-v0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
| [Panda-7B-v0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
| [Panda-7B-v0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
| [Panda-7B-v0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q4_0.gguf) | Q4_0 | 3.83GB |
| [Panda-7B-v0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
| [Panda-7B-v0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
| [Panda-7B-v0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q4_K.gguf) | Q4_K | 4.07GB |
| [Panda-7B-v0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
| [Panda-7B-v0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q4_1.gguf) | Q4_1 | 4.24GB |
| [Panda-7B-v0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q5_0.gguf) | Q5_0 | 4.65GB |
| [Panda-7B-v0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
| [Panda-7B-v0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q5_K.gguf) | Q5_K | 4.78GB |
| [Panda-7B-v0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
| [Panda-7B-v0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q5_1.gguf) | Q5_1 | 5.07GB |
| [Panda-7B-v0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q6_K.gguf) | Q6_K | 5.53GB |
| [Panda-7B-v0.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/NeuralNovel_-_Panda-7B-v0.1-gguf/blob/main/Panda-7B-v0.1.Q8_0.gguf) | Q8_0 | 7.17GB |
Original model description:
---
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
datasets:
- NeuralNovel/Creative-Logic-v1
- NeuralNovel/Neural-Story-v1
library_name: transformers
inference: false
---
# NeuralNovel/Panda-7B-v0.1
The **Panda-7B-v0.1** model by NeuralNovel.
This fine-tune has been designed to provide detailed, creative and logical responses in the context of diverse narratives. Optimised for creative writing, roleplay and logical problem solving.
Full-parameter fine-tune (FFT) of Mistral-7B-Instruct-v0.2. Apache-2.0 license, suitable for commercial or non-commercial use.
<a href='https://ko-fi.com/S6S2UH2TC' target='_blank'><img height='38' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi1.png?v=3' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
<a href='https://discord.gg/KFS229xD' target='_blank'><img width='140' height='500' style='border:0px;height:36px;' src='https://i.ibb.co/tqwznYM/Discord-button.png' border='0' alt='Join Our Discord!' /></a>
### Data-set
The model on finetuned using the Panda-v1 dataset.
### Summary
Fine-tuned with the intention to generate instructive and narrative text, with a specific focus on combining the elements of versatility, character engagement and nuanced writing capability.
#### Out-of-Scope Use
The model may not perform well in scenarios unrelated to instructive and narrative text generation. Misuse or applications outside its designed scope may result in suboptimal outcomes.
### Bias, Risks, and Limitations
The model may exhibit biases or limitations inherent in the training data. It is essential to consider these factors when deploying the model to avoid unintended consequences.
Users are advised to exercise caution, as there might be some inherent genre or writing bias.
### Hardware and Training
```
n_epochs = 3,
n_checkpoints = 3,
batch_size = 12,
learning_rate = 1e-5,
```
*Sincere appreciation to Techmind for their generous sponsorship.*
|
RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf | RichardErkhov | 2024-05-25T23:57:51Z | 428 | 0 | null | [
"gguf",
"region:us"
]
| null | 2024-05-25T21:05:28Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Llama-3-11b-Instruct - GGUF
- Model creator: https://huggingface.co/athirdpath/
- Original model: https://huggingface.co/athirdpath/Llama-3-11b-Instruct/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Llama-3-11b-Instruct.Q2_K.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q2_K.gguf) | Q2_K | 4.01GB |
| [Llama-3-11b-Instruct.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.IQ3_XS.gguf) | IQ3_XS | 4.44GB |
| [Llama-3-11b-Instruct.IQ3_S.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.IQ3_S.gguf) | IQ3_S | 4.66GB |
| [Llama-3-11b-Instruct.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q3_K_S.gguf) | Q3_K_S | 4.64GB |
| [Llama-3-11b-Instruct.IQ3_M.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.IQ3_M.gguf) | IQ3_M | 4.79GB |
| [Llama-3-11b-Instruct.Q3_K.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q3_K.gguf) | Q3_K | 5.1GB |
| [Llama-3-11b-Instruct.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q3_K_M.gguf) | Q3_K_M | 5.1GB |
| [Llama-3-11b-Instruct.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q3_K_L.gguf) | Q3_K_L | 5.52GB |
| [Llama-3-11b-Instruct.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.IQ4_XS.gguf) | IQ4_XS | 5.7GB |
| [Llama-3-11b-Instruct.Q4_0.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q4_0.gguf) | Q4_0 | 5.94GB |
| [Llama-3-11b-Instruct.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.IQ4_NL.gguf) | IQ4_NL | 6.0GB |
| [Llama-3-11b-Instruct.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q4_K_S.gguf) | Q4_K_S | 5.98GB |
| [Llama-3-11b-Instruct.Q4_K.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q4_K.gguf) | Q4_K | 6.27GB |
| [Llama-3-11b-Instruct.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q4_K_M.gguf) | Q4_K_M | 6.27GB |
| [Llama-3-11b-Instruct.Q4_1.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q4_1.gguf) | Q4_1 | 6.56GB |
| [Llama-3-11b-Instruct.Q5_0.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q5_0.gguf) | Q5_0 | 7.17GB |
| [Llama-3-11b-Instruct.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q5_K_S.gguf) | Q5_K_S | 7.17GB |
| [Llama-3-11b-Instruct.Q5_K.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q5_K.gguf) | Q5_K | 7.34GB |
| [Llama-3-11b-Instruct.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q5_K_M.gguf) | Q5_K_M | 7.34GB |
| [Llama-3-11b-Instruct.Q5_1.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q5_1.gguf) | Q5_1 | 7.78GB |
| [Llama-3-11b-Instruct.Q6_K.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q6_K.gguf) | Q6_K | 8.48GB |
| [Llama-3-11b-Instruct.Q8_0.gguf](https://huggingface.co/RichardErkhov/athirdpath_-_Llama-3-11b-Instruct-gguf/blob/main/Llama-3-11b-Instruct.Q8_0.gguf) | Q8_0 | 10.98GB |
Original model description:
---
license: llama3
---
I'm back and doing well! I've got a job in the field now, so we'll see in the long run how that effects my open source output.
Here we have a 11b Llama 3 instruct model for future work.
EDIT: Made a yaml mistake with part funnel, but it still works well.
---
This is a merge stock of 3 models:
- Part Wave
- Part Block
- Part Funnel
With Part Funnel as the base.
---
Part Wave:
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [0, 12]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [8, 18]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [13, 23]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [18, 32]
---
Part Block:
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [0, 15]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [8, 23]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [16, 32]
---
Part Funnel:
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [0, 15]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [14, 14]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [13, 13]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [12, 12]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [11, 11]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [10, 10]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [9, 9]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [8, 23]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [22, 22]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [21, 21]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [20, 20]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [19, 19]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [18, 18]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [17, 17]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [16, 32]
|
miha-kac/mergedEPmodel-Q4_0-GGUF | miha-kac | 2024-06-03T15:14:49Z | 428 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:miha-kac/mergedEPmodel",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-03T15:14:38Z | ---
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
base_model: miha-kac/mergedEPmodel
---
# miha-kac/mergedEPmodel-Q4_0-GGUF
This model was converted to GGUF format from [`miha-kac/mergedEPmodel`](https://huggingface.co/miha-kac/mergedEPmodel) 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/miha-kac/mergedEPmodel) 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 --hf-repo miha-kac/mergedEPmodel-Q4_0-GGUF --hf-file mergedepmodel-q4_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo miha-kac/mergedEPmodel-Q4_0-GGUF --hf-file mergedepmodel-q4_0.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.
```
./main --hf-repo miha-kac/mergedEPmodel-Q4_0-GGUF --hf-file mergedepmodel-q4_0.gguf -p "The meaning to life and the universe is"
```
or
```
./server --hf-repo miha-kac/mergedEPmodel-Q4_0-GGUF --hf-file mergedepmodel-q4_0.gguf -c 2048
```
|
diffusers-test/test2 | diffusers-test | 2024-06-19T18:43:22Z | 428 | 0 | diffusers | [
"diffusers",
"safetensors",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2024-06-19T11:05:34Z | Entry not found |
Klevin/MOE-Finetuned-4B-Q4_K_M-GGUF | Klevin | 2024-06-22T07:33:03Z | 428 | 1 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"llama-cpp",
"gguf-my-repo",
"en",
"base_model:Klevin/MOE-Finetuned-4B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-22T07:32:42Z | ---
base_model: Klevin/MOE-Finetuned-4B
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
- llama-cpp
- gguf-my-repo
---
# Klevin/MOE-Finetuned-4B-Q4_K_M-GGUF
This model was converted to GGUF format from [`Klevin/MOE-Finetuned-4B`](https://huggingface.co/Klevin/MOE-Finetuned-4B) 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/Klevin/MOE-Finetuned-4B) 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 Klevin/MOE-Finetuned-4B-Q4_K_M-GGUF --hf-file moe-finetuned-4b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Klevin/MOE-Finetuned-4B-Q4_K_M-GGUF --hf-file moe-finetuned-4b-q4_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 Klevin/MOE-Finetuned-4B-Q4_K_M-GGUF --hf-file moe-finetuned-4b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Klevin/MOE-Finetuned-4B-Q4_K_M-GGUF --hf-file moe-finetuned-4b-q4_k_m.gguf -c 2048
```
|
aubmindlab/araelectra-base-discriminator | aubmindlab | 2022-11-15T12:42:21Z | 427 | 5 | transformers | [
"transformers",
"pytorch",
"tf",
"tensorboard",
"electra",
"pretraining",
"ar",
"arxiv:1406.2661",
"arxiv:2012.15516",
"endpoints_compatible",
"region:us"
]
| null | 2022-03-02T23:29:05Z | ---
language: ar
datasets:
- wikipedia
- Osian
- 1.5B-Arabic-Corpus
- oscar-arabic-unshuffled
- Assafir(private)
---
# AraELECTRA
<img src="https://raw.githubusercontent.com/aub-mind/arabert/master/AraELECTRA.png" width="100" align="left"/>
**ELECTRA** is a method for self-supervised language representation learning. It can be used to pre-train transformer networks using relatively little compute. ELECTRA models are trained to distinguish "real" input tokens vs "fake" input tokens generated by another neural network, similar to the discriminator of a [GAN](https://arxiv.org/pdf/1406.2661.pdf). AraELECTRA achieves state-of-the-art results on Arabic QA dataset.
For a detailed description, please refer to the AraELECTRA paper [AraELECTRA: Pre-Training Text Discriminators for Arabic Language Understanding](https://arxiv.org/abs/2012.15516).
## How to use the discriminator in `transformers`
```python
from transformers import ElectraForPreTraining, ElectraTokenizerFast
import torch
discriminator = ElectraForPreTraining.from_pretrained("aubmindlab/araelectra-base-discriminator")
tokenizer = ElectraTokenizerFast.from_pretrained("aubmindlab/araelectra-base-discriminator")
sentence = ""
fake_sentence = ""
fake_tokens = tokenizer.tokenize(fake_sentence)
fake_inputs = tokenizer.encode(fake_sentence, return_tensors="pt")
discriminator_outputs = discriminator(fake_inputs)
predictions = torch.round((torch.sign(discriminator_outputs[0]) + 1) / 2)
[print("%7s" % token, end="") for token in fake_tokens]
[print("%7s" % int(prediction), end="") for prediction in predictions.tolist()]
```
# Model
Model | HuggingFace Model Name | Size (MB/Params)|
---|:---:|:---:
AraELECTRA-base-generator | [araelectra-base-generator](https://huggingface.co/aubmindlab/araelectra-base-generator) | 227MB/60M |
AraELECTRA-base-discriminator | [araelectra-base-discriminator](https://huggingface.co/aubmindlab/araelectra-base-discriminator) | 516MB/135M |
# Compute
Model | Hardware | num of examples (seq len = 512) | Batch Size | Num of Steps | Time (in days)
---|:---:|:---:|:---:|:---:|:---:
AraELECTRA-base | TPUv3-8 | - | 256 | 2M | 24
# Dataset
The pretraining data used for the new **AraELECTRA** model is also used for **AraGPT2 and AraBERTv2**.
The dataset consists of 77GB or 200,095,961 lines or 8,655,948,860 words or 82,232,988,358 chars (before applying Farasa Segmentation)
For the new dataset we added the unshuffled OSCAR corpus, after we thoroughly filter it, to the previous dataset used in AraBERTv1 but with out the websites that we previously crawled:
- OSCAR unshuffled and filtered.
- [Arabic Wikipedia dump](https://archive.org/details/arwiki-20190201) from 2020/09/01
- [The 1.5B words Arabic Corpus](https://www.semanticscholar.org/paper/1.5-billion-words-Arabic-Corpus-El-Khair/f3eeef4afb81223df96575adadf808fe7fe440b4)
- [The OSIAN Corpus](https://www.aclweb.org/anthology/W19-4619)
- Assafir news articles. Huge thank you for Assafir for giving us the data
# Preprocessing
It is recommended to apply our preprocessing function before training/testing on any dataset.
**Install the arabert python package to segment text for AraBERT v1 & v2 or to clean your data `pip install arabert`**
```python
from arabert.preprocess import ArabertPreprocessor
model_name="araelectra-base"
arabert_prep = ArabertPreprocessor(model_name=model_name)
text = "ولن نبالغ إذا قلنا إن هاتف أو كمبيوتر المكتب في زمننا هذا ضروري"
arabert_prep.preprocess(text)
>>> output: ولن نبالغ إذا قلنا : إن هاتف أو كمبيوتر المكتب في زمننا هذا ضروري
```
# TensorFlow 1.x models
**You can find the PyTorch, TF2 and TF1 models in HuggingFace's Transformer Library under the ```aubmindlab``` username**
- `wget https://huggingface.co/aubmindlab/MODEL_NAME/resolve/main/tf1_model.tar.gz` where `MODEL_NAME` is any model under the `aubmindlab` name
# If you used this model please cite us as :
```
@inproceedings{antoun-etal-2021-araelectra,
title = "{A}ra{ELECTRA}: Pre-Training Text Discriminators for {A}rabic Language Understanding",
author = "Antoun, Wissam and
Baly, Fady and
Hajj, Hazem",
booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
month = apr,
year = "2021",
address = "Kyiv, Ukraine (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2021.wanlp-1.20",
pages = "191--195",
}
```
# Acknowledgments
Thanks to TensorFlow Research Cloud (TFRC) for the free access to Cloud TPUs, couldn't have done it without this program, and to the [AUB MIND Lab](https://sites.aub.edu.lb/mindlab/) Members for the continous support. Also thanks to [Yakshof](https://www.yakshof.com/#/) and Assafir for data and storage access. Another thanks for Habib Rahal (https://www.behance.net/rahalhabib), for putting a face to AraBERT.
# Contacts
**Wissam Antoun**: [Linkedin](https://www.linkedin.com/in/wissam-antoun-622142b4/) | [Twitter](https://twitter.com/wissam_antoun) | [Github](https://github.com/WissamAntoun) | <[email protected]> | <[email protected]>
**Fady Baly**: [Linkedin](https://www.linkedin.com/in/fadybaly/) | [Twitter](https://twitter.com/fadybaly) | [Github](https://github.com/fadybaly) | <[email protected]> | <[email protected]> |
lighteternal/fact-or-opinion-xlmr-el | lighteternal | 2022-02-27T19:41:57Z | 427 | 18 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"text-classification",
"fact-or-opinion",
"en",
"el",
"multilingual",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2022-03-02T23:29:05Z | ---
language:
- en
- el
- multilingual
tags:
- text-classification
- fact-or-opinion
- transformers
widget:
- text: "Ξεχωρίζει η καθηλωτική ερμηνεία του πρωταγωνιστή."
- text: "Η Ελλάδα είναι χώρα της Ευρώπης."
- text: "Tolkien was an English writer"
- text: "Tolkien is my favorite writer."
pipeline_tag: text-classification
license: apache-2.0
---
# Fact vs. opinion binary classifier, trained on a mixed EN-EL annotated corpus.
### By the Hellenic Army Academy (SSE) and the Technical University of Crete (TUC)
This is an XLM-Roberta-base model with a binary classification head. Given a sentence, it can classify it either as a fact or an opinion based on its content.
You can use this model in any of the XLM-R supported languages for the same task, taking advantage of its 0-shot learning capabilities. However, the model was trained only using English and Greek sentences.
Legend of HuggingFace API labels:
* Label 0: Opinion/Subjective sentence
* Label 1: Fact/Objective sentence
## Dataset training info
The original dataset (available here: https://github.com/1024er/cbert_aug/tree/crayon/datasets/subj) contained aprox. 9000 annotated sentences (classified as subjective or objective). It was translated to Greek using Google Translate. The Greek version was then concatenated with the original English one to create the mixed EN-EL dataset.
The model was trained for 5 epochs, using batch size = 8. Detailed metrics and hyperparameters available on the "Metrics" tab.
## Evaluation Results on test set
| accuracy | precision | recall | f1 |
| ----------- | ----------- | ----------- | ----------- |
|0.952 | 0.945 | 0.960 | 0.952 |
## Acknowledgement
The research work was supported by the Hellenic Foundation for Research and Innovation (HFRI) under the HFRI PhD Fellowship grant (Fellowship Number:50, 2nd call)
|
timm/maxvit_xlarge_tf_384.in21k_ft_in1k | timm | 2023-05-11T00:37:29Z | 427 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-21k",
"arxiv:2204.01697",
"license:apache-2.0",
"region:us"
]
| image-classification | 2022-12-02T21:58:14Z | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- imagenet-21k
---
# Model card for maxvit_xlarge_tf_384.in21k_ft_in1k
An official MaxViT image classification model. Pretrained in tensorflow on ImageNet-21k (21843 Google specific instance of ImageNet-22k) and fine-tuned on ImageNet-1k by paper authors.
Ported from official Tensorflow implementation (https://github.com/google-research/maxvit) to PyTorch by Ross Wightman.
### Model Variants in [maxxvit.py](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/maxxvit.py)
MaxxViT covers a number of related model architectures that share a common structure including:
- CoAtNet - Combining MBConv (depthwise-separable) convolutional blocks in early stages with self-attention transformer blocks in later stages.
- MaxViT - Uniform blocks across all stages, each containing a MBConv (depthwise-separable) convolution block followed by two self-attention blocks with different partitioning schemes (window followed by grid).
- CoAtNeXt - A timm specific arch that uses ConvNeXt blocks in place of MBConv blocks in CoAtNet. All normalization layers are LayerNorm (no BatchNorm).
- MaxxViT - A timm specific arch that uses ConvNeXt blocks in place of MBConv blocks in MaxViT. All normalization layers are LayerNorm (no BatchNorm).
- MaxxViT-V2 - A MaxxViT variation that removes the window block attention leaving only ConvNeXt blocks and grid attention w/ more width to compensate.
Aside from the major variants listed above, there are more subtle changes from model to model. Any model name with the string `rw` are `timm` specific configs w/ modelling adjustments made to favour PyTorch eager use. These were created while training initial reproductions of the models so there are variations.
All models with the string `tf` are models exactly matching Tensorflow based models by the original paper authors with weights ported to PyTorch. This covers a number of MaxViT models. The official CoAtNet models were never released.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 475.3
- GMACs: 292.8
- Activations (M): 668.8
- Image size: 384 x 384
- **Papers:**
- MaxViT: Multi-Axis Vision Transformer: https://arxiv.org/abs/2204.01697
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-21k
## 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('maxvit_xlarge_tf_384.in21k_ft_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(
'maxvit_xlarge_tf_384.in21k_ft_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, 192, 192, 192])
# torch.Size([1, 192, 96, 96])
# torch.Size([1, 384, 48, 48])
# torch.Size([1, 768, 24, 24])
# torch.Size([1, 1536, 12, 12])
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(
'maxvit_xlarge_tf_384.in21k_ft_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, 1536, 12, 12) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
### By Top-1
|model |top1 |top5 |samples / sec |Params (M) |GMAC |Act (M)|
|------------------------------------------------------------------------------------------------------------------------|----:|----:|--------------:|--------------:|-----:|------:|
|[maxvit_xlarge_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_512.in21k_ft_in1k) |88.53|98.64| 21.76| 475.77|534.14|1413.22|
|[maxvit_xlarge_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_384.in21k_ft_in1k) |88.32|98.54| 42.53| 475.32|292.78| 668.76|
|[maxvit_base_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_512.in21k_ft_in1k) |88.20|98.53| 50.87| 119.88|138.02| 703.99|
|[maxvit_large_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_512.in21k_ft_in1k) |88.04|98.40| 36.42| 212.33|244.75| 942.15|
|[maxvit_large_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_384.in21k_ft_in1k) |87.98|98.56| 71.75| 212.03|132.55| 445.84|
|[maxvit_base_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_384.in21k_ft_in1k) |87.92|98.54| 104.71| 119.65| 73.80| 332.90|
|[maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.81|98.37| 106.55| 116.14| 70.97| 318.95|
|[maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.47|98.37| 149.49| 116.09| 72.98| 213.74|
|[coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k) |87.39|98.31| 160.80| 73.88| 47.69| 209.43|
|[maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.89|98.02| 375.86| 116.14| 23.15| 92.64|
|[maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.64|98.02| 501.03| 116.09| 24.20| 62.77|
|[maxvit_base_tf_512.in1k](https://huggingface.co/timm/maxvit_base_tf_512.in1k) |86.60|97.92| 50.75| 119.88|138.02| 703.99|
|[coatnet_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_2_rw_224.sw_in12k_ft_in1k) |86.57|97.89| 631.88| 73.87| 15.09| 49.22|
|[maxvit_large_tf_512.in1k](https://huggingface.co/timm/maxvit_large_tf_512.in1k) |86.52|97.88| 36.04| 212.33|244.75| 942.15|
|[coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k) |86.49|97.90| 620.58| 73.88| 15.18| 54.78|
|[maxvit_base_tf_384.in1k](https://huggingface.co/timm/maxvit_base_tf_384.in1k) |86.29|97.80| 101.09| 119.65| 73.80| 332.90|
|[maxvit_large_tf_384.in1k](https://huggingface.co/timm/maxvit_large_tf_384.in1k) |86.23|97.69| 70.56| 212.03|132.55| 445.84|
|[maxvit_small_tf_512.in1k](https://huggingface.co/timm/maxvit_small_tf_512.in1k) |86.10|97.76| 88.63| 69.13| 67.26| 383.77|
|[maxvit_tiny_tf_512.in1k](https://huggingface.co/timm/maxvit_tiny_tf_512.in1k) |85.67|97.58| 144.25| 31.05| 33.49| 257.59|
|[maxvit_small_tf_384.in1k](https://huggingface.co/timm/maxvit_small_tf_384.in1k) |85.54|97.46| 188.35| 69.02| 35.87| 183.65|
|[maxvit_tiny_tf_384.in1k](https://huggingface.co/timm/maxvit_tiny_tf_384.in1k) |85.11|97.38| 293.46| 30.98| 17.53| 123.42|
|[maxvit_large_tf_224.in1k](https://huggingface.co/timm/maxvit_large_tf_224.in1k) |84.93|96.97| 247.71| 211.79| 43.68| 127.35|
|[coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k) |84.90|96.96| 1025.45| 41.72| 8.11| 40.13|
|[maxvit_base_tf_224.in1k](https://huggingface.co/timm/maxvit_base_tf_224.in1k) |84.85|96.99| 358.25| 119.47| 24.04| 95.01|
|[maxxvit_rmlp_small_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_small_rw_256.sw_in1k) |84.63|97.06| 575.53| 66.01| 14.67| 58.38|
|[coatnet_rmlp_2_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in1k) |84.61|96.74| 625.81| 73.88| 15.18| 54.78|
|[maxvit_rmlp_small_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_small_rw_224.sw_in1k) |84.49|96.76| 693.82| 64.90| 10.75| 49.30|
|[maxvit_small_tf_224.in1k](https://huggingface.co/timm/maxvit_small_tf_224.in1k) |84.43|96.83| 647.96| 68.93| 11.66| 53.17|
|[maxvit_rmlp_tiny_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_tiny_rw_256.sw_in1k) |84.23|96.78| 807.21| 29.15| 6.77| 46.92|
|[coatnet_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_1_rw_224.sw_in1k) |83.62|96.38| 989.59| 41.72| 8.04| 34.60|
|[maxvit_tiny_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_tiny_rw_224.sw_in1k) |83.50|96.50| 1100.53| 29.06| 5.11| 33.11|
|[maxvit_tiny_tf_224.in1k](https://huggingface.co/timm/maxvit_tiny_tf_224.in1k) |83.41|96.59| 1004.94| 30.92| 5.60| 35.78|
|[coatnet_rmlp_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw_224.sw_in1k) |83.36|96.45| 1093.03| 41.69| 7.85| 35.47|
|[maxxvitv2_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvitv2_nano_rw_256.sw_in1k) |83.11|96.33| 1276.88| 23.70| 6.26| 23.05|
|[maxxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_nano_rw_256.sw_in1k) |83.03|96.34| 1341.24| 16.78| 4.37| 26.05|
|[maxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_nano_rw_256.sw_in1k) |82.96|96.26| 1283.24| 15.50| 4.47| 31.92|
|[maxvit_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_nano_rw_256.sw_in1k) |82.93|96.23| 1218.17| 15.45| 4.46| 30.28|
|[coatnet_bn_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_bn_0_rw_224.sw_in1k) |82.39|96.19| 1600.14| 27.44| 4.67| 22.04|
|[coatnet_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_0_rw_224.sw_in1k) |82.39|95.84| 1831.21| 27.44| 4.43| 18.73|
|[coatnet_rmlp_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_nano_rw_224.sw_in1k) |82.05|95.87| 2109.09| 15.15| 2.62| 20.34|
|[coatnext_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnext_nano_rw_224.sw_in1k) |81.95|95.92| 2525.52| 14.70| 2.47| 12.80|
|[coatnet_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_nano_rw_224.sw_in1k) |81.70|95.64| 2344.52| 15.14| 2.41| 15.41|
|[maxvit_rmlp_pico_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_pico_rw_256.sw_in1k) |80.53|95.21| 1594.71| 7.52| 1.85| 24.86|
### By Throughput (samples / sec)
|model |top1 |top5 |samples / sec |Params (M) |GMAC |Act (M)|
|------------------------------------------------------------------------------------------------------------------------|----:|----:|--------------:|--------------:|-----:|------:|
|[coatnext_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnext_nano_rw_224.sw_in1k) |81.95|95.92| 2525.52| 14.70| 2.47| 12.80|
|[coatnet_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_nano_rw_224.sw_in1k) |81.70|95.64| 2344.52| 15.14| 2.41| 15.41|
|[coatnet_rmlp_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_nano_rw_224.sw_in1k) |82.05|95.87| 2109.09| 15.15| 2.62| 20.34|
|[coatnet_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_0_rw_224.sw_in1k) |82.39|95.84| 1831.21| 27.44| 4.43| 18.73|
|[coatnet_bn_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_bn_0_rw_224.sw_in1k) |82.39|96.19| 1600.14| 27.44| 4.67| 22.04|
|[maxvit_rmlp_pico_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_pico_rw_256.sw_in1k) |80.53|95.21| 1594.71| 7.52| 1.85| 24.86|
|[maxxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_nano_rw_256.sw_in1k) |83.03|96.34| 1341.24| 16.78| 4.37| 26.05|
|[maxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_nano_rw_256.sw_in1k) |82.96|96.26| 1283.24| 15.50| 4.47| 31.92|
|[maxxvitv2_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvitv2_nano_rw_256.sw_in1k) |83.11|96.33| 1276.88| 23.70| 6.26| 23.05|
|[maxvit_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_nano_rw_256.sw_in1k) |82.93|96.23| 1218.17| 15.45| 4.46| 30.28|
|[maxvit_tiny_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_tiny_rw_224.sw_in1k) |83.50|96.50| 1100.53| 29.06| 5.11| 33.11|
|[coatnet_rmlp_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw_224.sw_in1k) |83.36|96.45| 1093.03| 41.69| 7.85| 35.47|
|[coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k) |84.90|96.96| 1025.45| 41.72| 8.11| 40.13|
|[maxvit_tiny_tf_224.in1k](https://huggingface.co/timm/maxvit_tiny_tf_224.in1k) |83.41|96.59| 1004.94| 30.92| 5.60| 35.78|
|[coatnet_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_1_rw_224.sw_in1k) |83.62|96.38| 989.59| 41.72| 8.04| 34.60|
|[maxvit_rmlp_tiny_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_tiny_rw_256.sw_in1k) |84.23|96.78| 807.21| 29.15| 6.77| 46.92|
|[maxvit_rmlp_small_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_small_rw_224.sw_in1k) |84.49|96.76| 693.82| 64.90| 10.75| 49.30|
|[maxvit_small_tf_224.in1k](https://huggingface.co/timm/maxvit_small_tf_224.in1k) |84.43|96.83| 647.96| 68.93| 11.66| 53.17|
|[coatnet_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_2_rw_224.sw_in12k_ft_in1k) |86.57|97.89| 631.88| 73.87| 15.09| 49.22|
|[coatnet_rmlp_2_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in1k) |84.61|96.74| 625.81| 73.88| 15.18| 54.78|
|[coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k) |86.49|97.90| 620.58| 73.88| 15.18| 54.78|
|[maxxvit_rmlp_small_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_small_rw_256.sw_in1k) |84.63|97.06| 575.53| 66.01| 14.67| 58.38|
|[maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.64|98.02| 501.03| 116.09| 24.20| 62.77|
|[maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.89|98.02| 375.86| 116.14| 23.15| 92.64|
|[maxvit_base_tf_224.in1k](https://huggingface.co/timm/maxvit_base_tf_224.in1k) |84.85|96.99| 358.25| 119.47| 24.04| 95.01|
|[maxvit_tiny_tf_384.in1k](https://huggingface.co/timm/maxvit_tiny_tf_384.in1k) |85.11|97.38| 293.46| 30.98| 17.53| 123.42|
|[maxvit_large_tf_224.in1k](https://huggingface.co/timm/maxvit_large_tf_224.in1k) |84.93|96.97| 247.71| 211.79| 43.68| 127.35|
|[maxvit_small_tf_384.in1k](https://huggingface.co/timm/maxvit_small_tf_384.in1k) |85.54|97.46| 188.35| 69.02| 35.87| 183.65|
|[coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k) |87.39|98.31| 160.80| 73.88| 47.69| 209.43|
|[maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.47|98.37| 149.49| 116.09| 72.98| 213.74|
|[maxvit_tiny_tf_512.in1k](https://huggingface.co/timm/maxvit_tiny_tf_512.in1k) |85.67|97.58| 144.25| 31.05| 33.49| 257.59|
|[maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.81|98.37| 106.55| 116.14| 70.97| 318.95|
|[maxvit_base_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_384.in21k_ft_in1k) |87.92|98.54| 104.71| 119.65| 73.80| 332.90|
|[maxvit_base_tf_384.in1k](https://huggingface.co/timm/maxvit_base_tf_384.in1k) |86.29|97.80| 101.09| 119.65| 73.80| 332.90|
|[maxvit_small_tf_512.in1k](https://huggingface.co/timm/maxvit_small_tf_512.in1k) |86.10|97.76| 88.63| 69.13| 67.26| 383.77|
|[maxvit_large_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_384.in21k_ft_in1k) |87.98|98.56| 71.75| 212.03|132.55| 445.84|
|[maxvit_large_tf_384.in1k](https://huggingface.co/timm/maxvit_large_tf_384.in1k) |86.23|97.69| 70.56| 212.03|132.55| 445.84|
|[maxvit_base_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_512.in21k_ft_in1k) |88.20|98.53| 50.87| 119.88|138.02| 703.99|
|[maxvit_base_tf_512.in1k](https://huggingface.co/timm/maxvit_base_tf_512.in1k) |86.60|97.92| 50.75| 119.88|138.02| 703.99|
|[maxvit_xlarge_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_384.in21k_ft_in1k) |88.32|98.54| 42.53| 475.32|292.78| 668.76|
|[maxvit_large_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_512.in21k_ft_in1k) |88.04|98.40| 36.42| 212.33|244.75| 942.15|
|[maxvit_large_tf_512.in1k](https://huggingface.co/timm/maxvit_large_tf_512.in1k) |86.52|97.88| 36.04| 212.33|244.75| 942.15|
|[maxvit_xlarge_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_512.in21k_ft_in1k) |88.53|98.64| 21.76| 475.77|534.14|1413.22|
## 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
@article{tu2022maxvit,
title={MaxViT: Multi-Axis Vision Transformer},
author={Tu, Zhengzhong and Talebi, Hossein and Zhang, Han and Yang, Feng and Milanfar, Peyman and Bovik, Alan and Li, Yinxiao},
journal={ECCV},
year={2022},
}
```
```bibtex
@article{dai2021coatnet,
title={CoAtNet: Marrying Convolution and Attention for All Data Sizes},
author={Dai, Zihang and Liu, Hanxiao and Le, Quoc V and Tan, Mingxing},
journal={arXiv preprint arXiv:2106.04803},
year={2021}
}
```
|
monilouise/opt125M_portuguese | monilouise | 2023-03-30T01:16:07Z | 427 | 2 | transformers | [
"transformers",
"pytorch",
"opt",
"text-generation",
"pt",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-03-29T23:35:24Z | ---
language:
- pt
metrics:
- perplexity
pipeline_tag: text-generation
---
# Model Card for Model ID
A Portuguese language model trained on https://huggingface.co/facebook/opt-125m .
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** Monique Monteiro
- **Shared by [optional]:** Monique Monteiro
- **Model type:** OPT
- **Language(s) (NLP):** Portuguese
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** facebook/opt-125m
Use the code below to get started with the model.
```python
generator = pipeline('text-generation', 'monilouise/opt125M_portuguese')
output = generator("Era uma vez", max_length=50, do_sample=True)
```
## Training Details
### Training Data
The model was trained on gs://unicamp-dl/ia025a_2022s1/aula9/sample-1gb.txt
### Training Procedure
The model was trained for 3 epochs, by using learning rate = 5e-5 (linear scheduler).
#### Preprocessing [optional]
All text was tokenized and broken into chunks of 1024 tokens.
#### Training Hyperparameters
- **Training regime:** fp16 mixed precision
#### Speeds, Sizes, Times [optional]
Training time: 17 hours
## Evaluation
The model was evaluated on a 5% validation split.
#### Metrics
Perplexity = 7.94.
## Model Card Authors [optional]
[email protected]
## Model Card Contact
[email protected] |
TheBloke/MetaMath-13B-V1.0-GGUF | TheBloke | 2023-09-27T12:54:27Z | 427 | 3 | transformers | [
"transformers",
"gguf",
"llama",
"base_model:meta-math/MetaMath-13B-V1.0",
"license:llama2",
"text-generation-inference",
"region:us"
]
| null | 2023-09-23T23:57:50Z | ---
license: llama2
model_name: MetaMath 13B V1.0
base_model: meta-math/MetaMath-13B-V1.0
inference: false
model_creator: MetaMath
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response: Let''s think step by step.
'
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 -->
# MetaMath 13B V1.0 - GGUF
- Model creator: [MetaMath](https://huggingface.co/meta-math)
- Original model: [MetaMath 13B V1.0](https://huggingface.co/meta-math/MetaMath-13B-V1.0)
<!-- description start -->
## Description
This repo contains GGUF format model files for [MetaMath's MetaMath 13B V1.0](https://huggingface.co/meta-math/MetaMath-13B-V1.0).
<!-- 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/MetaMath-13B-V1.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF)
* [MetaMath's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/meta-math/MetaMath-13B-V1.0)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca-CoT
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response: Let's think step by step.
```
<!-- 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [metamath-13b-v1.0.Q2_K.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [metamath-13b-v1.0.Q3_K_S.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [metamath-13b-v1.0.Q3_K_M.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [metamath-13b-v1.0.Q3_K_L.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [metamath-13b-v1.0.Q4_0.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [metamath-13b-v1.0.Q4_K_S.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
| [metamath-13b-v1.0.Q4_K_M.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [metamath-13b-v1.0.Q5_0.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [metamath-13b-v1.0.Q5_K_S.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [metamath-13b-v1.0.Q5_K_M.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [metamath-13b-v1.0.Q6_K.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [metamath-13b-v1.0.Q8_0.gguf](https://huggingface.co/TheBloke/MetaMath-13B-V1.0-GGUF/blob/main/metamath-13b-v1.0.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 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/MetaMath-13B-V1.0-GGUF and below it, a specific filename to download, such as: metamath-13b-v1.0.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/MetaMath-13B-V1.0-GGUF metamath-13b-v1.0.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/MetaMath-13B-V1.0-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/MetaMath-13B-V1.0-GGUF metamath-13b-v1.0.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 metamath-13b-v1.0.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\n### Instruction:\n{prompt}\n\n\n### Response: Let's think step by step."
```
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/MetaMath-13B-V1.0-GGUF", model_file="metamath-13b-v1.0.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: MetaMath's MetaMath 13B V1.0
No original model card was available.
<!-- original-model-card end -->
|
second-state/Baichuan2-7B-Chat-GGUF | second-state | 2024-03-20T07:44:42Z | 427 | 4 | transformers | [
"transformers",
"gguf",
"baichuan",
"text-generation",
"custom_code",
"en",
"zh",
"base_model:baichuan-inc/Baichuan2-7B-Chat",
"autotrain_compatible",
"region:us"
]
| text-generation | 2023-10-24T04:02:19Z | ---
base_model: baichuan-inc/Baichuan2-7B-Chat
inference: false
library_name: transformers
license_name: baichuan2-community-license
license_link: https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat/blob/main/Community%20License%20for%20Baichuan2%20Model.pdf
model_creator: Baichuan Intelligent Technology
model_name: Baichuan2 7B Chat
model_type: baichuan
pipeline_tag: text-generation
quantized_by: Second State Inc.
language:
- en
- zh
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/second-state/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 -->
# Baichuan2-7B-Chat-GGUF
## Original Model
[baichuan-inc/Baichuan2-7B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat)
## Run with LlamaEdge
- LlamaEdge version: [v0.2.8](https://github.com/second-state/LlamaEdge/releases/tag/0.2.8) and above
- Prompt template
- Prompt type: `baichuan-2`
- Prompt string
```text
以下内容为人类用户与与一位智能助手的对话。
用户:你好！
助手:
```
- Reverse prompt: `用户:`
- Context size: `4096`
- Run as LlamaEdge service
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Baichuan2-7B-Chat-Q5_K_M.gguf llama-api-server.wasm -p baichuan-2 -r '用户:'
```
- Run as LlamaEdge command app
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Baichuan2-7B-Chat-Q5_K_M.gguf llama-chat.wasm -p baichuan-2 -r '用户:'
```
## Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [Baichuan2-7B-Chat-Q2_K.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q2_K.gguf) | Q2_K | 2 | 3.27 GB| smallest, significant quality loss - not recommended for most purposes |
| [Baichuan2-7B-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 4.08 GB| small, substantial quality loss |
| [Baichuan2-7B-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 3.78 GB| very small, high quality loss |
| [Baichuan2-7B-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 3.43 GB| very small, high quality loss |
| [Baichuan2-7B-Chat-Q4_0.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q4_0.gguf) | Q4_0 | 4 | 4.36 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [Baichuan2-7B-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 4.61 GB| medium, balanced quality - recommended |
| [Baichuan2-7B-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 4.39 GB| small, greater quality loss |
| [Baichuan2-7B-Chat-Q5_0.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q5_0.gguf) | Q5_0 | 5 | 5.23 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [Baichuan2-7B-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 5.36 GB| large, very low quality loss - recommended |
| [Baichuan2-7B-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 5.23 GB| large, low quality loss - recommended |
| [Baichuan2-7B-Chat-Q6_K.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q6_K.gguf) | Q6_K | 6 | 6.16 GB| very large, extremely low quality loss |
| [Baichuan2-7B-Chat-Q8_0.gguf](https://huggingface.co/second-state/Baichuan2-7B-Chat-GGUF/blob/main/Baichuan2-7B-Chat-Q8_0.gguf) | Q8_0 | 8 | 7.98 GB| very large, extremely low quality loss - not recommended |
|
Yntec/Synthwave | Yntec | 2023-11-09T07:45:14Z | 427 | 2 | diffusers | [
"diffusers",
"safetensors",
"PublicPrompts",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-11-09T06:29:04Z | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- PublicPrompts
---
# Synthwave
Safetensors and Diffusers version of this model for the Inference API.
Sample and prompt:
Cartoon Pretty CUTE Girl, DETAILED CHIBI EYES, beautiful detailed legs, pajamas, gorgeous detailed hair, Magazine ad, iconic, 1949, sharp focus. visible brushstrokes By KlaysMoji and artgerm and leyendecker and Dave Rapoza and terry moore and josephine wall.
Source: https://huggingface.co/PublicPrompts/Synthwave |
TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF | TheBloke | 2023-11-28T16:13:16Z | 427 | 5 | transformers | [
"transformers",
"gguf",
"yi",
"text-generation",
"en",
"base_model:brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties",
"license:other",
"region:us"
]
| text-generation | 2023-11-28T13:18:42Z | ---
base_model: brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties
inference: false
language:
- en
library_name: transformers
license: other
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
license_name: yi-license
model_creator: brucethemoose
model_name: Capytessborosyi 34B 200K Dare Ties
model_type: yi
pipeline_tag: text-generation
prompt_template: 'SYSTEM: {system_message}
USER: {prompt}
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 -->
# Capytessborosyi 34B 200K Dare Ties - GGUF
- Model creator: [brucethemoose](https://huggingface.co/brucethemoose)
- Original model: [Capytessborosyi 34B 200K Dare Ties](https://huggingface.co/brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties)
<!-- description start -->
## Description
This repo contains GGUF format model files for [brucethemoose's Capytessborosyi 34B 200K Dare Ties](https://huggingface.co/brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties).
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/CapyTessBorosYi-34B-200K-DARE-Ties-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF)
* [brucethemoose's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Orca-Vicuna
```
SYSTEM: {system_message}
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 [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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [capytessborosyi-34b-200k-dare-ties.Q2_K.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q2_K.gguf) | Q2_K | 2 | 14.56 GB| 17.06 GB | smallest, significant quality loss - not recommended for most purposes |
| [capytessborosyi-34b-200k-dare-ties.Q3_K_S.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q3_K_S.gguf) | Q3_K_S | 3 | 14.96 GB| 17.46 GB | very small, high quality loss |
| [capytessborosyi-34b-200k-dare-ties.Q3_K_M.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q3_K_M.gguf) | Q3_K_M | 3 | 16.64 GB| 19.14 GB | very small, high quality loss |
| [capytessborosyi-34b-200k-dare-ties.Q3_K_L.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q3_K_L.gguf) | Q3_K_L | 3 | 18.14 GB| 20.64 GB | small, substantial quality loss |
| [capytessborosyi-34b-200k-dare-ties.Q4_0.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q4_0.gguf) | Q4_0 | 4 | 19.47 GB| 21.97 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [capytessborosyi-34b-200k-dare-ties.Q4_K_S.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q4_K_S.gguf) | Q4_K_S | 4 | 19.54 GB| 22.04 GB | small, greater quality loss |
| [capytessborosyi-34b-200k-dare-ties.Q4_K_M.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q4_K_M.gguf) | Q4_K_M | 4 | 20.66 GB| 23.16 GB | medium, balanced quality - recommended |
| [capytessborosyi-34b-200k-dare-ties.Q5_0.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q5_0.gguf) | Q5_0 | 5 | 23.71 GB| 26.21 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [capytessborosyi-34b-200k-dare-ties.Q5_K_S.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q5_K_S.gguf) | Q5_K_S | 5 | 23.71 GB| 26.21 GB | large, low quality loss - recommended |
| [capytessborosyi-34b-200k-dare-ties.Q5_K_M.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q5_K_M.gguf) | Q5_K_M | 5 | 24.32 GB| 26.82 GB | large, very low quality loss - recommended |
| [capytessborosyi-34b-200k-dare-ties.Q6_K.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q6_K.gguf) | Q6_K | 6 | 28.21 GB| 30.71 GB | very large, extremely low quality loss |
| [capytessborosyi-34b-200k-dare-ties.Q8_0.gguf](https://huggingface.co/TheBloke/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF/blob/main/capytessborosyi-34b-200k-dare-ties.Q8_0.gguf) | Q8_0 | 8 | 36.54 GB| 39.04 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/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF and below it, a specific filename to download, such as: capytessborosyi-34b-200k-dare-ties.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/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF capytessborosyi-34b-200k-dare-ties.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/CapyTessBorosYi-34B-200K-DARE-Ties-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/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF capytessborosyi-34b-200k-dare-ties.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 capytessborosyi-34b-200k-dare-ties.Q4_K_M.gguf --color -c 200000 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "SYSTEM: {system_message}\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 200000` 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="./capytessborosyi-34b-200k-dare-ties.Q4_K_M.gguf", # Download the model file first
n_ctx=200000, # 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(
"SYSTEM: {system_message}\nUSER: {prompt}\nASSISTANT:", # 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="./capytessborosyi-34b-200k-dare-ties.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: brucethemoose's Capytessborosyi 34B 200K Dare Ties
**NousResearch/Nous-Capybara-34B**, **migtissera/Tess-M-v1.3** and **bhenrym14/airoboros-3_1-yi-34b-200k** merged with a new, experimental implementation of "dare ties" via mergekit. See:
> Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
https://github.com/yule-BUAA/MergeLM
https://github.com/cg123/mergekit/tree/dare
***
Merged with the following config, and the tokenizer from chargoddard's Yi-Llama:
```
models:
- model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
# no parameters necessary for base model
- model: /home/alpha/Storage/Models/Raw/migtissera_Tess-M-v1.3
parameters:
weight: 0.41
density: 0.50
- model: /home/alpha//Storage/Models/Raw/bhenrym14_airoboros-3_1-yi-34b-200k
parameters:
weight: 0.18
density: 0.46
- model: /home/alpha/Storage/Models/Raw/Nous-Capybara-34B
parameters:
weight: 0.41
density: 0.50
merge_method: dare_ties
base_model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
parameters:
int8_mask: true
dtype: bfloat16
```
dare_ties is testing with better perplexity than a regular ties merge with the same merge configuration. Model weights that add up to one also seem optimal from testing. And results seem... better than the previous dare merge with Tess 1.2? Maybe?
I chose not to include other finetunes, such as Dolphin, because they aren't trained on the 200K base. If any other 200K finetunes pop up, let me know.
***
## Prompt template: Orca-Vicuna
```
SYSTEM: {system_message}
USER: {prompt}
ASSISTANT:
```
Being a Yi model, try disabling the BOS token and/or running a lower temperature with MinP (and no other samplers) if output doesn't seem right. Yi tends to run "hot" by default.
Sometimes the model "spells out" the stop token as `</s>` like Capybara, so you may need to add `</s>` as an additional stopping condition. It also might respond to the llama-2 chat format.
***
Credits:
https://github.com/cg123/mergekit/tree/dare
https://huggingface.co/NousResearch/Nous-Capybara-34B/
https://huggingface.co/bhenrym14/airoboros-3_1-yi-34b-200k
https://huggingface.co/migtissera/Tess-M-v1.3
https://huggingface.co/chargoddard/Yi-34B-200K-Llama
https://huggingface.co/01-ai/Yi-34B-200K
<!-- original-model-card end -->
|
ven1228/5DF38VhmtVBdkbuFQgMpZtjGEgve4gepMmkYwhUof6pC7Ves_vgg | ven1228 | 2024-03-11T12:45:03Z | 427 | 0 | keras | [
"keras",
"region:us"
]
| null | 2024-03-05T05:39:48Z | Entry not found |
recogna-nlp/gembode-2b-ultraalpaca | recogna-nlp | 2024-04-26T01:03:27Z | 427 | 2 | transformers | [
"transformers",
"pytorch",
"gemma",
"text-generation",
"conversational",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-09T03:50:22Z | ---
license: mit
model-index:
- name: gembode-2b-ultraalpaca
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: ENEM Challenge (No Images)
type: eduagarcia/enem_challenge
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 34.71
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-ultraalpaca
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BLUEX (No Images)
type: eduagarcia-temp/BLUEX_without_images
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 25.87
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-ultraalpaca
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: OAB Exams
type: eduagarcia/oab_exams
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 31.71
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-ultraalpaca
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 RTE
type: assin2
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 71.31
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-ultraalpaca
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 STS
type: eduagarcia/portuguese_benchmark
split: test
args:
num_few_shot: 15
metrics:
- type: pearson
value: 34.08
name: pearson
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-ultraalpaca
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: FaQuAD NLI
type: ruanchaves/faquad-nli
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 60.09
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-ultraalpaca
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HateBR Binary
type: ruanchaves/hatebr
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 47.01
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-ultraalpaca
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: PT Hate Speech Binary
type: hate_speech_portuguese
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 57.04
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-ultraalpaca
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: tweetSentBR
type: eduagarcia-temp/tweetsentbr
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 49.37
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-ultraalpaca
name: Open Portuguese LLM Leaderboard
---
# gembode-2b-ultraalpaca
<!--- PROJECT LOGO -->
<p align="center">
<img src="https://huggingface.co/recogna-nlp/GemBode-2b-it/resolve/main/gembode.jpg" alt="Phi-Bode Logo" width="400" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
</p>
GemmBode é um modelo de linguagem ajustado para o idioma português, desenvolvido a partir do modelo base de instruções Gemma-2b-it fornecido pela [Google](https://huggingface.co/google/gemma-2b-it). Este modelo foi refinado através do processo de fine-tuning utilizando o dataset UltraAlpaca. O principal objetivo deste modelo é ser viável para pessoas
que não possuem recursos computacionais disponíveis para o uso de LLMs (Large Language Models). Ressalta-se que este é um trabalho em andamento e o modelo ainda apresenta problemas na geração de texto em português.
## Características Principais
- **Modelo Base:** Gemma-2b-it, criado pela Google, com 2 bilhões de parâmetros.
- **Dataset para Fine-tuning:** UltraAlpaca
- **Treinamento:** O treinamento foi realizado a partir do fine-tuning completo do gemma-2b-it.
# [Open Portuguese LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/recogna-nlp/gembode-2b-ultraalpaca)
| Metric | Value |
|--------------------------|---------|
|Average |**45.69**|
|ENEM Challenge (No Images)| 34.71|
|BLUEX (No Images) | 25.87|
|OAB Exams | 31.71|
|Assin2 RTE | 71.31|
|Assin2 STS | 34.08|
|FaQuAD NLI | 60.09|
|HateBR Binary | 47.01|
|PT Hate Speech Binary | 57.04|
|tweetSentBR | 49.37|
|
LiteLLMs/Mixtral-8x22B-Instruct-v0.1-GGUF | LiteLLMs | 2024-05-29T08:51:02Z | 427 | 1 | null | [
"gguf",
"GGUF",
"en",
"es",
"it",
"de",
"fr",
"license:apache-2.0",
"region:us"
]
| null | 2024-04-17T20:39:56Z |
---
language:
- en
- es
- it
- de
- fr
license: apache-2.0
tags:
- GGUF
quantized_by: andrijdavid
---
# Mixtral-8x22B-Instruct-v0.1-GGUF
- Original model: [Mixtral-8x22B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Mixtral-8x22B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1).
<!-- 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/Mixtral-8x22B-Instruct-v0.1-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/Mixtral-8x22B-Instruct-v0.1-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/Mixtral-8x22B-Instruct-v0.1-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/Mixtral-8x22B-Instruct-v0.1-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: Mixtral-8x22B-Instruct-v0.1
# Model Card for Mixtral-8x22B-Instruct-v0.1
The Mixtral-8x22B-Instruct-v0.1 Large Language Model (LLM) is an instruct fine-tuned version of the [Mixtral-8x22B-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-v0.1).
## Run the model
```python
from transformers import AutoModelForCausalLM
from mistral_common.protocol.instruct.messages import (
AssistantMessage,
UserMessage,
)
from mistral_common.protocol.instruct.tool_calls import (
Tool,
Function,
)
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.tokens.instruct.normalize import ChatCompletionRequest
device = "cuda" # the device to load the model onto
tokenizer_v3 = MistralTokenizer.v3()
mistral_query = ChatCompletionRequest(
tools=[
Tool(
function=Function(
name="get_current_weather",
description="Get the current weather",
parameters={
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the users location.",
},
},
"required": ["location", "format"],
},
)
)
],
messages=[
UserMessage(content="What's the weather like today in Paris"),
],
model="test",
)
encodeds = tokenizer_v3.encode_chat_completion(mistral_query).tokens
model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
sp_tokenizer = tokenizer_v3.instruct_tokenizer.tokenizer
decoded = sp_tokenizer.decode(generated_ids[0])
print(decoded)
```
Alternatively, you can run this example with the Hugging Face tokenizer.
To use this example, you'll need transformers version 4.39.0 or higher.
```console
pip install transformers==4.39.0
```
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x22B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
conversation=[
{"role": "user", "content": "What's the weather like in Paris?"},
{
"role": "tool_calls",
"content": [
{
"name": "get_current_weather",
"arguments": {"location": "Paris, France", "format": "celsius"},
}
]
},
{
"role": "tool_results",
"content": {"content": 22}
},
{"role": "assistant", "content": "The current temperature in Paris, France is 22 degrees Celsius."},
{"role": "user", "content": "What about San Francisco?"}
]
tools = [{"type": "function", "function": {"name":"get_current_weather", "description": "Get▁the▁current▁weather", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"}, "format": {"type": "string", "enum": ["celsius", "fahrenheit"], "description": "The temperature unit to use. Infer this from the users location."}},"required":["location","format"]}}}]
# render the tool use prompt as a string:
tool_use_prompt = tokenizer.apply_chat_template(
conversation,
chat_template="tool_use",
tools=tools,
tokenize=False,
add_generation_prompt=True,
)
model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1")
inputs = tokenizer(tool_use_prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
# Instruct tokenizer
The HuggingFace tokenizer included in this release should match our own. To compare:
`pip install mistral-common`
```py
from mistral_common.protocol.instruct.messages import (
AssistantMessage,
UserMessage,
)
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.tokens.instruct.normalize import ChatCompletionRequest
from transformers import AutoTokenizer
tokenizer_v3 = MistralTokenizer.v3()
mistral_query = ChatCompletionRequest(
messages=[
UserMessage(content="How many experts ?"),
AssistantMessage(content="8"),
UserMessage(content="How big ?"),
AssistantMessage(content="22B"),
UserMessage(content="Noice 🎉 !"),
],
model="test",
)
hf_messages = mistral_query.model_dump()['messages']
tokenized_mistral = tokenizer_v3.encode_chat_completion(mistral_query).tokens
tokenizer_hf = AutoTokenizer.from_pretrained('mistralai/Mixtral-8x22B-Instruct-v0.1')
tokenized_hf = tokenizer_hf.apply_chat_template(hf_messages, tokenize=True)
assert tokenized_hf == tokenized_mistral
```
# Function calling and special tokens
This tokenizer includes more special tokens, related to function calling :
- [TOOL_CALLS]
- [AVAILABLE_TOOLS]
- [/AVAILABLE_TOOLS]
- [TOOL_RESULTS]
- [/TOOL_RESULTS]
If you want to use this model with function calling, please be sure to apply it similarly to what is done in our [SentencePieceTokenizerV3](https://github.com/mistralai/mistral-common/blob/main/src/mistral_common/tokens/tokenizers/sentencepiece.py#L299).
# The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux,
Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault,
Blanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot,
Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger,
Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona,
Jean-Malo Delignon, Jia Li, Justus Murke, Louis Martin, Louis Ternon,
Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat,
Marie Torelli, Marie-Anne Lachaux, Nicolas Schuhl, Patrick von Platen,
Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao,
Thibaut Lavril, Timothée Lacroix, Théophile Gervet, Thomas Wang,
Valera Nemychnikova, William El Sayed, William Marshall
<!-- original-model-card end -->
|
duyntnet/mythalion-13b-imatrix-GGUF | duyntnet | 2024-04-30T15:29:14Z | 427 | 0 | transformers | [
"transformers",
"gguf",
"imatrix",
"mythalion-13b",
"text-generation",
"en",
"license:other",
"region:us"
]
| text-generation | 2024-04-30T12:08:24Z | ---
license: other
language:
- en
pipeline_tag: text-generation
inference: false
tags:
- transformers
- gguf
- imatrix
- mythalion-13b
---
Quantizations of https://huggingface.co/PygmalionAI/mythalion-13b
# From original readme
## Prompting
This model can be prompted using both the Alpaca and [Pygmalion formatting](https://huggingface.co/PygmalionAI/pygmalion-2-13b#prompting).
**Alpaca formatting**:
```
### Instruction:
<prompt>
### Response:
<leave a newline blank for model to respond>
```
**Pygmalion/Metharme formatting**:
```
<|system|>Enter RP mode. Pretend to be {{char}} whose persona follows:
{{persona}}
You shall reply to the user while staying in character, and generate long responses.
<|user|>Hello!<|model|>{model's response goes here}
```
The model has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.
The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input.
The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to
form a conversation history. |
dbalasub/finalcheck-ensem-qa | dbalasub | 2024-05-15T18:54:43Z | 427 | 0 | transformers | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text2text-generation | 2024-05-12T17:38:36Z | ---
library_name: transformers
license: mit
---
# 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/Mahou-1.2-llama3-8B-i1-GGUF | mradermacher | 2024-05-19T22:31:48Z | 427 | 3 | transformers | [
"transformers",
"gguf",
"en",
"dataset:flammenai/Grill-preprod-v1_chatML",
"dataset:flammenai/Grill-preprod-v2_chatML",
"base_model:flammenai/Mahou-1.2-llama3-8B",
"license:llama3",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-17T20:26:09Z | ---
base_model: flammenai/Mahou-1.2-llama3-8B
datasets:
- flammenai/Grill-preprod-v1_chatML
- flammenai/Grill-preprod-v2_chatML
language:
- en
library_name: transformers
license: llama3
quantized_by: mradermacher
tags: []
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hfhfix -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/flammenai/Mahou-1.2-llama3-8B
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-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/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-i1-GGUF/resolve/main/Mahou-1.2-llama3-8B.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 -->
|
Lakoc/bestrq_ebranchformer_12_512h_2d | Lakoc | 2024-06-03T19:40:24Z | 427 | 0 | transformers | [
"transformers",
"bestrq-ebranchformer",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-01T20:54:07Z | ---
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] |
animaRegem/gemma-2b-malayalam-t2-gguf | animaRegem | 2024-06-03T22:49:09Z | 427 | 0 | transformers | [
"transformers",
"gguf",
"gemma",
"text-generation-inference",
"unsloth",
"en",
"base_model:Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-03T21:37:07Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- gemma
- gguf
base_model: Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0
---
# Uploaded model
- **Developed by:** animaRegem
- **License:** apache-2.0
- **Finetuned from model :** Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Felladrin/gguf-TinySolar-248m-4k-code-instruct | Felladrin | 2024-06-15T21:38:21Z | 427 | 0 | null | [
"gguf",
"base_model:upstage/TinySolar-248m-4k-code-instruct",
"license:apache-2.0",
"region:us"
]
| null | 2024-06-15T21:34:58Z | ---
license: apache-2.0
base_model: upstage/TinySolar-248m-4k-code-instruct
---
GGUF version of [upstage/TinySolar-248m-4k-code-instruct](https://huggingface.co/upstage/TinySolar-248m-4k-code-instruct). |
pranav79/aigf-phi3-mini-v6 | pranav79 | 2024-06-19T07:39:28Z | 427 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/phi-3-mini-4k-instruct-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-19T07:38:24Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- gguf
base_model: unsloth/phi-3-mini-4k-instruct-bnb-4bit
---
# Uploaded model
- **Developed by:** pranav79
- **License:** apache-2.0
- **Finetuned from model :** unsloth/phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
gvozdev/mistral-7b-dm-v0.1-Q4_K_M.gguf | gvozdev | 2024-06-19T13:49:56Z | 427 | 1 | mlx | [
"mlx",
"gguf",
"mistral",
"license:apache-2.0",
"region:us"
]
| null | 2024-06-19T13:32:33Z | ---
license: apache-2.0
tags:
- mlx
---
# gvozdev/mistral-7b-dm-v0.1
The Model [gvozdev/mistral-7b-dm-v0.1](https://huggingface.co/gvozdev/mistral-7b-dm-v0.1) was converted to MLX format from [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) using mlx-lm version **0.14.3**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("gvozdev/mistral-7b-dm-v0.1")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
gvozdev/mistral-7b-dm-v0.2-Q4_K_M.gguf | gvozdev | 2024-06-19T17:15:17Z | 427 | 0 | null | [
"gguf",
"region:us"
]
| null | 2024-06-19T17:06:59Z | Entry not found |
CHE-72/Qwen1.5-4B-Chat-Q4_0-GGUF | CHE-72 | 2024-06-22T19:01:05Z | 427 | 0 | null | [
"gguf",
"chat",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:Qwen/Qwen1.5-4B-Chat",
"license:other",
"region:us"
]
| text-generation | 2024-06-22T19:00:50Z | ---
base_model: Qwen/Qwen1.5-4B-Chat
language:
- en
license: other
license_name: tongyi-qianwen-research
license_link: https://huggingface.co/Qwen/Qwen1.5-4B-Chat/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- chat
- llama-cpp
- gguf-my-repo
---
# CHE-72/Qwen1.5-4B-Chat-Q4_0-GGUF
This model was converted to GGUF format from [`Qwen/Qwen1.5-4B-Chat`](https://huggingface.co/Qwen/Qwen1.5-4B-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/Qwen/Qwen1.5-4B-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 CHE-72/Qwen1.5-4B-Chat-Q4_0-GGUF --hf-file qwen1.5-4b-chat-q4_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo CHE-72/Qwen1.5-4B-Chat-Q4_0-GGUF --hf-file qwen1.5-4b-chat-q4_0.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/Qwen1.5-4B-Chat-Q4_0-GGUF --hf-file qwen1.5-4b-chat-q4_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo CHE-72/Qwen1.5-4B-Chat-Q4_0-GGUF --hf-file qwen1.5-4b-chat-q4_0.gguf -c 2048
```
|
saurabhraj115/Meta-Llama-3-8B-Instruct-Q4_K_S-GGUF | saurabhraj115 | 2024-06-28T10:49:36Z | 427 | 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 | 2024-06-28T10:49:15Z | ---
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|>
---
# saurabhraj115/Meta-Llama-3-8B-Instruct-Q4_K_S-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 saurabhraj115/Meta-Llama-3-8B-Instruct-Q4_K_S-GGUF --hf-file meta-llama-3-8b-instruct-q4_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo saurabhraj115/Meta-Llama-3-8B-Instruct-Q4_K_S-GGUF --hf-file meta-llama-3-8b-instruct-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 saurabhraj115/Meta-Llama-3-8B-Instruct-Q4_K_S-GGUF --hf-file meta-llama-3-8b-instruct-q4_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo saurabhraj115/Meta-Llama-3-8B-Instruct-Q4_K_S-GGUF --hf-file meta-llama-3-8b-instruct-q4_k_s.gguf -c 2048
```
|
cardiffnlp/twitter-roberta-base-emoji | cardiffnlp | 2022-11-28T11:27:48Z | 426 | 14 | transformers | [
"transformers",
"pytorch",
"tf",
"jax",
"roberta",
"text-classification",
"arxiv:2010.12421",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2022-03-02T23:29:05Z | # Twitter-roBERTa-base for Emoji prediction
This is a roBERTa-base model trained on ~58M tweets and finetuned for emoji prediction with the TweetEval benchmark.
- Paper: [_TweetEval_ benchmark (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf).
- Git Repo: [Tweeteval official repository](https://github.com/cardiffnlp/tweeteval).
## Example of classification
```python
from transformers import AutoModelForSequenceClassification
from transformers import TFAutoModelForSequenceClassification
from transformers import AutoTokenizer
import numpy as np
from scipy.special import softmax
import csv
import urllib.request
# Preprocess text (username and link placeholders)
def preprocess(text):
new_text = []
for t in text.split(" "):
t = '@user' if t.startswith('@') and len(t) > 1 else t
t = 'http' if t.startswith('http') else t
new_text.append(t)
return " ".join(new_text)
# Tasks:
# emoji, emotion, hate, irony, offensive, sentiment
# stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary
task='emoji'
MODEL = f"cardiffnlp/twitter-roberta-base-{task}"
tokenizer = AutoTokenizer.from_pretrained(MODEL)
# download label mapping
labels=[]
mapping_link = f"https://raw.githubusercontent.com/cardiffnlp/tweeteval/main/datasets/{task}/mapping.txt"
with urllib.request.urlopen(mapping_link) as f:
html = f.read().decode('utf-8').split("\n")
csvreader = csv.reader(html, delimiter='\t')
labels = [row[1] for row in csvreader if len(row) > 1]
# PT
model = AutoModelForSequenceClassification.from_pretrained(MODEL)
model.save_pretrained(MODEL)
text = "Looking forward to Christmas"
text = preprocess(text)
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
scores = output[0][0].detach().numpy()
scores = softmax(scores)
# # TF
# model = TFAutoModelForSequenceClassification.from_pretrained(MODEL)
# model.save_pretrained(MODEL)
# text = "Looking forward to Christmas"
# text = preprocess(text)
# encoded_input = tokenizer(text, return_tensors='tf')
# output = model(encoded_input)
# scores = output[0][0].numpy()
# scores = softmax(scores)
ranking = np.argsort(scores)
ranking = ranking[::-1]
for i in range(scores.shape[0]):
l = labels[ranking[i]]
s = scores[ranking[i]]
print(f"{i+1}) {l} {np.round(float(s), 4)}")
```
Output:
```
1) 🎄 0.5457
2) 😊 0.1417
3) 😁 0.0649
4) 😍 0.0395
5) ❤️ 0.03
6) 😜 0.028
7) ✨ 0.0263
8) 😉 0.0237
9) 😂 0.0177
10) 😎 0.0166
11) 😘 0.0143
12) 💕 0.014
13) 💙 0.0076
14) 💜 0.0068
15) 🔥 0.0065
16) 💯 0.004
17) 🇺🇸 0.0037
18) 📷 0.0034
19) ☀ 0.0033
20) 📸 0.0021
```
|
huggingartists/50-cent | huggingartists | 2022-08-11T11:41:31Z | 426 | 0 | transformers | [
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingartists",
"lyrics",
"lm-head",
"causal-lm",
"en",
"dataset:huggingartists/50-cent",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2022-03-02T23:29:05Z | ---
language: en
datasets:
- huggingartists/50-cent
tags:
- huggingartists
- lyrics
- lm-head
- causal-lm
widget:
- text: "I am"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://images.genius.com/10f98dca7bcd1a31222e36374544cad5.1000x1000x1.png')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">50 Cent</div>
<a href="https://genius.com/artists/50-cent">
<div style="text-align: center; font-size: 14px;">@50-cent</div>
</a>
</div>
I was made with [huggingartists](https://github.com/AlekseyKorshuk/huggingartists).
Create your own bot based on your favorite artist with [the demo](https://colab.research.google.com/github/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb)!
## How does it work?
To understand how the model was developed, check the [W&B report](https://wandb.ai/huggingartists/huggingartists/reportlist).
## Training data
The model was trained on lyrics from 50 Cent.
Dataset is available [here](https://huggingface.co/datasets/huggingartists/50-cent).
And can be used with:
```python
from datasets import load_dataset
dataset = load_dataset("huggingartists/50-cent")
```
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1291qx5n/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on 50 Cent's lyrics.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1igwpphq) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1igwpphq/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingartists/50-cent')
generator("I am", num_return_sequences=5)
```
Or with Transformers library:
```python
from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("huggingartists/50-cent")
model = AutoModelWithLMHead.from_pretrained("huggingartists/50-cent")
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Aleksey Korshuk*
[](https://github.com/AlekseyKorshuk)
[](https://twitter.com/intent/follow?screen_name=alekseykorshuk)
[](https://t.me/joinchat/_CQ04KjcJ-4yZTky)
For more details, visit the project repository.
[](https://github.com/AlekseyKorshuk/huggingartists)
|
huggingface-course/bert-finetuned-squad | huggingface-course | 2021-11-11T17:49:56Z | 426 | 6 | transformers | [
"transformers",
"pytorch",
"tf",
"tensorboard",
"bert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"endpoints_compatible",
"region:us"
]
| question-answering | 2022-03-02T23:29:05Z | ---
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: test-bert-finetuned-squad
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. -->
# test-bert-finetuned-squad
This model was trained from scratch on the squad 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: 2e-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: 3
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.11.0.dev0
- Pytorch 1.8.1+cu111
- Datasets 1.12.2.dev0
- Tokenizers 0.10.3
|
TheBloke/BerrySauce-L2-13B-GGUF | TheBloke | 2023-09-27T12:49:10Z | 426 | 1 | transformers | [
"transformers",
"gguf",
"llama",
"base_model:sauce1337/berrySauce-L2-13b",
"license:cc-by-nc-4.0",
"text-generation-inference",
"region:us"
]
| null | 2023-09-14T08:10:13Z | ---
license: cc-by-nc-4.0
model_name: BerrySauce L2 13B
base_model: sauce1337/berrySauce-L2-13b
inference: false
model_creator: sauce1337
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 -->
# BerrySauce L2 13B - GGUF
- Model creator: [sauce1337](https://huggingface.co/sauce1337)
- Original model: [BerrySauce L2 13B](https://huggingface.co/sauce1337/berrySauce-L2-13b)
<!-- description start -->
## Description
This repo contains GGUF format model files for [sauce1337's BerrySauce L2 13B](https://huggingface.co/sauce1337/berrySauce-L2-13b).
<!-- 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/BerrySauce-L2-13B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF)
* [sauce1337's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/sauce1337/berrySauce-L2-13b)
<!-- 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 `cc-by-nc-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: [sauce1337's BerrySauce L2 13B](https://huggingface.co/sauce1337/berrySauce-L2-13b).
<!-- licensing 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [berrysauce-l2-13b.Q2_K.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [berrysauce-l2-13b.Q3_K_S.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [berrysauce-l2-13b.Q3_K_M.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [berrysauce-l2-13b.Q3_K_L.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [berrysauce-l2-13b.Q4_0.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [berrysauce-l2-13b.Q4_K_S.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
| [berrysauce-l2-13b.Q4_K_M.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [berrysauce-l2-13b.Q5_0.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [berrysauce-l2-13b.Q5_K_S.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [berrysauce-l2-13b.Q5_K_M.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [berrysauce-l2-13b.Q6_K.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [berrysauce-l2-13b.Q8_0.gguf](https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF/blob/main/berrysauce-l2-13b.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 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/BerrySauce-L2-13B-GGUF and below it, a specific filename to download, such as: berrysauce-l2-13b.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/BerrySauce-L2-13B-GGUF berrysauce-l2-13b.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/BerrySauce-L2-13B-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/BerrySauce-L2-13B-GGUF berrysauce-l2-13b.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 berrysauce-l2-13b.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 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/BerrySauce-L2-13B-GGUF", model_file="berrysauce-l2-13b.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: sauce1337's BerrySauce L2 13B
ok, it's a berry.
would you role play with a berry? maybe.
would you ask a berry complicated logical questions? maybe.
use alpaca format? maybe.
> TheBloke GGUF and GPTQ:\
> https://huggingface.co/TheBloke/BerrySauce-L2-13B-GPTQ \
> https://huggingface.co/TheBloke/BerrySauce-L2-13B-GGUF
<!-- original-model-card end -->
|
Azma-AI/bart-conversation-summarizer | Azma-AI | 2023-10-10T11:24:01Z | 426 | 5 | transformers | [
"transformers",
"pytorch",
"bart",
"text2text-generation",
"summarization",
"dataset:samsum",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| summarization | 2023-10-10T11:21:55Z | ---
datasets:
- samsum
pipeline_tag: summarization
widget:
- text: >
Laurie: So, what are your plans for this weekend?
Christie: I don’t know. Do you want to get together or something?
Sarah: How about going to see a movie? Cinemax 26 on Carson Boulevard is showing Enchanted.
Laurie: That sounds like a good idea. Maybe we should go out to eat beforehand.
Sarah: It is fine with me. Where do you want to meet?
Christie: Let’s meet at Summer Pizza House. I have not gone there for a long time.
Laurie: Good idea again. I heard they just came up with a new pizza. It should be good because Summer Pizza House always has the best pizza in town.
Sarah: When should we meet?
Christie: Well, the movie is shown at 2:00PM, 4:00PM, 6:00PM and 8:00PM.
Laurie: Why don’t we go to the 2:00PM show? We can meet at Summer Pizza House at noon. That will give us plenty of time to enjoy our pizza.
Sarah: My cousin Karen is in town. Can I bring her along? I hate to leave her home alone.
Christie: Karen is in town? Yes, bring her along. Laurie, you remember Karen? We met her at Sara’s high school graduation party two years ago.
Laurie: I do not quite remember her. What does she look like?
Sarah: She has blond hair, she is kind of slender, and she is about your height.
Laurie: She wears eyeglasses, right?
Sarah: Yes, and she was playing the piano off and on during the party.
Laurie: I remember her now. Yes, do bring her along Sara. She is such a nice person, and funny too.
Sarah: She will be happy to meet both of you again.
Christie: What is she doing these days?
Sarah: She graduated last June, and she will start her teaching career next week when the new school term begins.
Laurie: What grade is she going to teach?
Sarah: She will teach kindergarten. She loves working with kids, and she always has such a good rapport with them
Christie: Kindergarten? She must be a very patient person. I always think kindergarten is the most difficult class to teach. Most of the kids have never been to school, and they have
e never been away from mommy for long.
Sarah: I think Karen will do fine. She knows how to handle young children
Laurie: I think the first few weeks will be tough. However, once the routine is set, it should not be too difficult to teach kindergarten.
Christie: You are right. The kids might even look forward to going to school since they have so many friends to play with.
Sarah: There are so many new things for them to do at school too. They do a lot of crafts in kindergarten. I am always amazed by the things kindergarten teachers do.
Laurie: Yes, I have seen my niece come home with so many neat stuff.
Christie: Maybe we can ask Karen to show us some of the things that we can do for this Halloween.
Laurie: Maybe we can stop by the craft store after the movie. What do you think, Sara?
Sarah: I will talk to her. I think she will like that. It will help her with school projects when Halloween comes.
Christie: Michael’s is a good store for crafts. It always carries a variety of things, and you can find almost anything there.
Laurie: There is a Michaels store not far away from Cinemax 26. I believe it is just around the corner, on Pioneer Avenue. We can even walk over there.
Sarah: So, we plan to meet for pizza at noon, go to the movies at two, and shop at Michael’s afterward. Right?
Laurie and Christie: Yes.
model-index:
- name: bart-large-cnn-samsum
results:
- task:
type: summarization
name: Conversation Summarization
dataset:
name: >-
SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive
Summarization
type: samsum
metrics:
- type: rogue-1
value: 54.8764
name: Validation ROGUE-1
- type: rogue-2
value: 29.6869,
name: Validation ROGUE-2
- type: rogue-l
value: 44.9874
name: Validation ROGUE-L
- type: loss
value: 1.47812
name: loss
--- |
TheBloke/Mistral-11B-CC-Air-RP-GGUF | TheBloke | 2023-10-14T23:52:50Z | 426 | 6 | transformers | [
"transformers",
"gguf",
"mistral",
"not-for-all-audiences",
"nsfw",
"pretrained",
"base_model:Undi95/Mistral-11B-CC-Air-RP",
"license:cc-by-nc-4.0",
"text-generation-inference",
"region:us"
]
| null | 2023-10-14T23:40:12Z | ---
base_model: Undi95/Mistral-11B-CC-Air-RP
inference: false
license: cc-by-nc-4.0
model_creator: Undi
model_name: Mistral 11B CC Air RP
model_type: mistral
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
tags:
- not-for-all-audiences
- nsfw
- mistral
- pretrained
---
<!-- 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 -->
# Mistral 11B CC Air RP - GGUF
- Model creator: [Undi](https://huggingface.co/Undi95)
- Original model: [Mistral 11B CC Air RP](https://huggingface.co/Undi95/Mistral-11B-CC-Air-RP)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Undi's Mistral 11B CC Air RP](https://huggingface.co/Undi95/Mistral-11B-CC-Air-RP).
<!-- 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/Mistral-11B-CC-Air-RP-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF)
* [Undi's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Undi95/Mistral-11B-CC-Air-RP)
<!-- 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [mistral-11b-cc-air-rp.Q2_K.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.Q2_K.gguf) | Q2_K | 2 | 4.55 GB| 7.05 GB | smallest, significant quality loss - not recommended for most purposes |
| [mistral-11b-cc-air-rp.Q3_K_S.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.Q3_K_S.gguf) | Q3_K_S | 3 | 4.66 GB| 7.16 GB | very small, high quality loss |
| [mistral-11b-cc-air-rp.Q3_K_M.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.Q3_K_M.gguf) | Q3_K_M | 3 | 5.19 GB| 7.69 GB | very small, high quality loss |
| [mistral-11b-cc-air-rp.Q3_K_L.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.Q3_K_L.gguf) | Q3_K_L | 3 | 5.65 GB| 8.15 GB | small, substantial quality loss |
| [mistral-11b-cc-air-rp.Q4_0.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.Q4_0.gguf) | Q4_0 | 4 | 6.07 GB| 8.57 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [mistral-11b-cc-air-rp.Q4_K_S.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.Q4_K_S.gguf) | Q4_K_S | 4 | 6.10 GB| 8.60 GB | small, greater quality loss |
| [mistral-11b-cc-air-rp.Q4_K_M.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.Q4_K_M.gguf) | Q4_K_M | 4 | 6.46 GB| 8.96 GB | medium, balanced quality - recommended |
| [mistral-11b-cc-air-rp.Q5_0.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.Q5_0.gguf) | Q5_0 | 5 | 7.40 GB| 9.90 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [mistral-11b-cc-air-rp.Q5_K_S.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.Q5_K_S.gguf) | Q5_K_S | 5 | 7.40 GB| 9.90 GB | large, low quality loss - recommended |
| [mistral-11b-cc-air-rp.Q5_K_M.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.Q5_K_M.gguf) | Q5_K_M | 5 | 7.60 GB| 10.10 GB | large, very low quality loss - recommended |
| [mistral-11b-cc-air-rp.Q6_K.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.Q6_K.gguf) | Q6_K | 6 | 8.81 GB| 11.31 GB | very large, extremely low quality loss |
| [mistral-11b-cc-air-rp.Q8_0.gguf](https://huggingface.co/TheBloke/Mistral-11B-CC-Air-RP-GGUF/blob/main/mistral-11b-cc-air-rp.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/Mistral-11B-CC-Air-RP-GGUF and below it, a specific filename to download, such as: mistral-11b-cc-air-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/Mistral-11B-CC-Air-RP-GGUF mistral-11b-cc-air-rp.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/Mistral-11B-CC-Air-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/Mistral-11B-CC-Air-RP-GGUF mistral-11b-cc-air-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 32 -m mistral-11b-cc-air-rp.Q4_K_M.gguf --color -c 2048 --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 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/Mistral-11B-CC-Air-RP-GGUF", model_file="mistral-11b-cc-air-rp.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**: 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 start -->
# Original model card: Undi's Mistral 11B CC Air RP
CollectiveCognition-v1.1-Mistral-7B and airoboros-mistral2.2-7b glued together and finetuned with qlora of Pippa and LimaRPv3 dataset.
<!-- description start -->
## Description
This repo contains fp16 files of Mistral-11B-CC-Air-RP.
<!-- description end -->
<!-- description start -->
## Model used
- [CollectiveCognition-v1.1-Mistral-7B](https://huggingface.co/teknium/CollectiveCognition-v1.1-Mistral-7B)
- [airoboros-mistral2.2-7b](https://huggingface.co/teknium/airoboros-mistral2.2-7b/)
- PIPPA dataset 11B qlora
- LimaRPv3 dataset 11B qlora
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca or default
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
```
USER: <prompt>
ASSISTANT:
```
## The secret sauce
```
slices:
- sources:
- model: teknium/CollectiveCognition-v1.1-Mistral-7B
layer_range: [0, 24]
- sources:
- model: teknium/airoboros-mistral2.2-7b
layer_range: [8, 32]
merge_method: passthrough
dtype: float16
```
Special thanks to Sushi.
If you want to support me, you can [here](https://ko-fi.com/undiai).
<!-- original-model-card end -->
|
satpalsr/llama2-translation-filter-full | satpalsr | 2024-01-20T17:23:45Z | 426 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-01-20T17:21:07Z | Entry not found |
mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF | mradermacher | 2024-05-07T16:27:07Z | 426 | 3 | transformers | [
"transformers",
"gguf",
"pytorch",
"mixtral",
"fine-tuned",
"moe",
"en",
"base_model:KoboldAI/Mixtral-8x7B-Holodeck-v1",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-03-04T03:52:56Z | ---
base_model: KoboldAI/Mixtral-8x7B-Holodeck-v1
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- pytorch
- mixtral
- fine-tuned
- moe
---
## About
weighted/imatrix quants of https://huggingface.co/KoboldAI/Mixtral-8x7B-Holodeck-v1
<!-- provided-files -->
## 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-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 10.1 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 10.8 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.8 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.2 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 14.4 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 15.8 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q2_K.gguf) | i1-Q2_K | 17.6 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.5 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 19.5 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 20.7 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.7 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 21.7 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.8 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.4 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.3 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 26.8 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_0.gguf) | i1-Q4_0 | 26.8 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.0 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.5 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.5 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q6_K.gguf) | i1-Q6_K | 38.6 | 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/luxia-21.4b-alignment-v1.0-GGUF | mradermacher | 2024-05-06T06:02:34Z | 426 | 1 | transformers | [
"transformers",
"gguf",
"en",
"base_model:saltlux/luxia-21.4b-alignment-v1.0",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-03-23T19:23:01Z | ---
base_model: saltlux/luxia-21.4b-alignment-v1.0
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
static quants of https://huggingface.co/saltlux/luxia-21.4b-alignment-v1.0
<!-- 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/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q2_K.gguf) | Q2_K | 8.9 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.IQ3_XS.gguf) | IQ3_XS | 9.7 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q3_K_S.gguf) | Q3_K_S | 10.2 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.IQ3_S.gguf) | IQ3_S | 10.2 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.IQ3_M.gguf) | IQ3_M | 10.6 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q3_K_M.gguf) | Q3_K_M | 11.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q3_K_L.gguf) | Q3_K_L | 12.1 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.IQ4_XS.gguf) | IQ4_XS | 12.5 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q4_K_S.gguf) | Q4_K_S | 13.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q4_K_M.gguf) | Q4_K_M | 13.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q5_K_S.gguf) | Q5_K_S | 15.6 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q5_K_M.gguf) | Q5_K_M | 15.9 | |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q6_K.gguf) | Q6_K | 18.3 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.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 -->
|
AlenBadel/SFR-Embedding-Mistral-GGUF | AlenBadel | 2024-03-31T18:12:50Z | 426 | 0 | null | [
"gguf",
"region:us"
]
| null | 2024-03-31T05:34:10Z | Quantized Version of
https://huggingface.co/Salesforce/SFR-Embedding-Mistral
---
license: cc-by-nc-4.0
---
|
mradermacher/MistralMusic2.0-GGUF | mradermacher | 2024-05-06T05:03:19Z | 426 | 0 | transformers | [
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"RaduGabriel/MistralMusic",
"mistralai/Mistral-7B-Instruct-v0.2",
"en",
"base_model:RaduGabriel/MistralMusic2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-10T16:44:50Z | ---
base_model: RaduGabriel/MistralMusic2.0
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- merge
- mergekit
- lazymergekit
- RaduGabriel/MistralMusic
- mistralai/Mistral-7B-Instruct-v0.2
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/RaduGabriel/MistralMusic2.0
<!-- 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/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/MistralMusic2.0-GGUF/resolve/main/MistralMusic2.0.Q8_0.gguf) | Q8_0 | 7.8 | 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_Medic-GGUF | mradermacher | 2024-05-06T05:02:17Z | 426 | 1 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"not-for-all-audiences",
"medical",
"climate",
"biology",
"chemistry",
"finance",
"legal",
"en",
"dataset:pubmed",
"dataset:Open-Orca/OpenOrca",
"dataset:cognitivecomputations/dolphin",
"dataset:WhiteRabbitNeo/WRN-Chapter-2",
"dataset:WhiteRabbitNeo/WRN-Chapter-1",
"dataset:ruslanmv/ai-medical-chatbot",
"base_model:LeroyDyer/Mixtral_AI_Medic",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-11T08:06:10Z | ---
base_model: LeroyDyer/Mixtral_AI_Medic
datasets:
- pubmed
- Open-Orca/OpenOrca
- cognitivecomputations/dolphin
- WhiteRabbitNeo/WRN-Chapter-2
- WhiteRabbitNeo/WRN-Chapter-1
- ruslanmv/ai-medical-chatbot
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
- not-for-all-audiences
- medical
- climate
- biology
- chemistry
- finance
- legal
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/LeroyDyer/Mixtral_AI_Medic
<!-- 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_Medic-GGUF/resolve/main/Mixtral_AI_Medic.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Medic-GGUF/resolve/main/Mixtral_AI_Medic.Q8_0.gguf) | Q8_0 | 7.8 | 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 -->
|
PrunaAI/EMO-1.5B-GGUF-smashed | PrunaAI | 2024-04-27T13:39:42Z | 426 | 1 | null | [
"gguf",
"pruna-ai",
"region:us"
]
| null | 2024-04-27T13:10:54Z | ---
thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
metrics:
- memory_disk
- memory_inference
- inference_latency
- inference_throughput
- inference_CO2_emissions
- inference_energy_consumption
tags:
- pruna-ai
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<a href="https://www.pruna.ai/" target="_blank" rel="noopener noreferrer">
<img src="https://i.imgur.com/eDAlcgk.png" alt="PrunaAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</a>
</div>
<!-- header end -->
[](https://twitter.com/PrunaAI)
[](https://github.com/PrunaAI)
[](https://www.linkedin.com/company/93832878/admin/feed/posts/?feedType=following)
[](https://discord.gg/CP4VSgck)
## This repo contains GGUF versions of the OEvortex/EMO-1.5B model.
# Simply make AI models cheaper, smaller, faster, and greener!
- Give a thumbs up if you like this model!
- Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
- Request access to easily compress your *own* AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
- Read the documentations to know more [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/)
- Join Pruna AI community on Discord [here](https://discord.gg/CP4VSgck) to share feedback/suggestions or get help.
**Frequently Asked Questions**
- ***How does the compression work?*** The model is compressed with GGUF.
- ***How does the model quality change?*** The quality of the model output might vary compared to the base model.
- ***What is the model format?*** We use GGUF format.
- ***What calibration data has been used?*** If needed by the compression method, we used WikiText as the calibration data.
- ***How to compress my own models?*** You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
# Downloading and running the models
You can download the individual files from the Files & versions section. Here is a list of the different versions we provide. For more info checkout [this chart](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) and [this guide](https://www.reddit.com/r/LocalLLaMA/comments/1ba55rj/overview_of_gguf_quantization_methods/):
| Quant type | Description |
|------------|--------------------------------------------------------------------------------------------|
| Q5_K_M | High quality, recommended. |
| Q5_K_S | High quality, recommended. |
| Q4_K_M | Good quality, uses about 4.83 bits per weight, recommended. |
| Q4_K_S | Slightly lower quality with more space savings, recommended. |
| IQ4_NL | Decent quality, slightly smaller than Q4_K_S with similar performance, recommended. |
| IQ4_XS | Decent quality, smaller than Q4_K_S with similar performance, recommended. |
| Q3_K_L | Lower quality but usable, good for low RAM availability. |
| Q3_K_M | Even lower quality. |
| IQ3_M | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| IQ3_S | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
| Q3_K_S | Low quality, not recommended. |
| IQ3_XS | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| Q2_K | Very low quality but surprisingly usable. |
## 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
- **Option A** - Downloading in `text-generation-webui`:
- **Step 1**: Under Download Model, you can enter the model repo: PrunaAI/EMO-1.5B-GGUF-smashed and below it, a specific filename to download, such as: phi-2.IQ3_M.gguf.
- **Step 2**: Then click Download.
- **Option B** - Downloading on the command line (including multiple files at once):
- **Step 1**: We recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
- **Step 2**: Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download PrunaAI/EMO-1.5B-GGUF-smashed EMO-1.5B.IQ3_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
Alternatively, you can also download multiple files at once with a pattern:
```shell
huggingface-cli download PrunaAI/EMO-1.5B-GGUF-smashed --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 PrunaAI/EMO-1.5B-GGUF-smashed EMO-1.5B.IQ3_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 -->
## How to run model in GGUF format?
- **Option A** - Introductory example with `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 EMO-1.5B.IQ3_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<s>[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)
- **Option B** - Running 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-%20Model%20Tab.md#llamacpp).
- **Option C** - Running 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="./EMO-1.5B.IQ3_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(
"<s>[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="./EMO-1.5B.IQ3_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."
}
]
)
```
- **Option D** - Running 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)
## Configurations
The configuration info are in `smash_config.json`.
## Credits & License
The license of the smashed model follows the license of the original model. Please check the license of the original model before using this model which provided the base model. The license of the `pruna-engine` is [here](https://pypi.org/project/pruna-engine/) on Pypi.
## Want to compress other models?
- Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
- Request access to easily compress your own AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
|
bartowski/starcoder2-15b-instruct-v0.1-GGUF | bartowski | 2024-04-30T13:58:00Z | 426 | 6 | transformers | [
"transformers",
"gguf",
"code",
"text-generation",
"dataset:bigcode/self-oss-instruct-sc2-exec-filter-50k",
"base_model:bigcode/starcoder2-15b",
"license:bigcode-openrail-m",
"model-index",
"endpoints_compatible",
"region:us"
]
| text-generation | 2024-04-29T22:16:56Z | ---
pipeline_tag: text-generation
base_model: bigcode/starcoder2-15b
datasets:
- bigcode/self-oss-instruct-sc2-exec-filter-50k
license: bigcode-openrail-m
library_name: transformers
tags:
- code
model-index:
- name: starcoder2-15b-instruct-v0.1
results:
- task:
type: text-generation
dataset:
name: LiveCodeBench (code generation)
type: livecodebench-codegeneration
metrics:
- type: pass@1
value: 20.4
- task:
type: text-generation
dataset:
name: LiveCodeBench (self repair)
type: livecodebench-selfrepair
metrics:
- type: pass@1
value: 20.9
- task:
type: text-generation
dataset:
name: LiveCodeBench (test output prediction)
type: livecodebench-testoutputprediction
metrics:
- type: pass@1
value: 29.8
- task:
type: text-generation
dataset:
name: LiveCodeBench (code execution)
type: livecodebench-codeexecution
metrics:
- type: pass@1
value: 28.1
- task:
type: text-generation
dataset:
name: HumanEval
type: humaneval
metrics:
- type: pass@1
value: 72.6
- task:
type: text-generation
dataset:
name: HumanEval+
type: humanevalplus
metrics:
- type: pass@1
value: 63.4
- task:
type: text-generation
dataset:
name: MBPP
type: mbpp
metrics:
- type: pass@1
value: 75.2
- task:
type: text-generation
dataset:
name: MBPP+
type: mbppplus
metrics:
- type: pass@1
value: 61.2
- task:
type: text-generation
dataset:
name: DS-1000
type: ds-1000
metrics:
- type: pass@1
value: 40.6
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of starcoder2-15b-instruct-v0.1
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2756">b2756</a> for quantization.
Original model: https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1
All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
## Prompt format
```
<|endoftext|>You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
### Instruction
{prompt}
### Response
<|endoftext|>
```
Note that this model does not support a System prompt.
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [starcoder2-15b-instruct-v0.1-Q8_0.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q8_0.gguf) | Q8_0 | 16.96GB | Extremely high quality, generally unneeded but max available quant. |
| [starcoder2-15b-instruct-v0.1-Q6_K.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q6_K.gguf) | Q6_K | 13.10GB | Very high quality, near perfect, *recommended*. |
| [starcoder2-15b-instruct-v0.1-Q5_K_M.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q5_K_M.gguf) | Q5_K_M | 11.43GB | High quality, *recommended*. |
| [starcoder2-15b-instruct-v0.1-Q5_K_S.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q5_K_S.gguf) | Q5_K_S | 11.02GB | High quality, *recommended*. |
| [starcoder2-15b-instruct-v0.1-Q4_K_M.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q4_K_M.gguf) | Q4_K_M | 9.86GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [starcoder2-15b-instruct-v0.1-Q4_K_S.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q4_K_S.gguf) | Q4_K_S | 9.16GB | Slightly lower quality with more space savings, *recommended*. |
| [starcoder2-15b-instruct-v0.1-IQ4_NL.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ4_NL.gguf) | IQ4_NL | 9.08GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
| [starcoder2-15b-instruct-v0.1-IQ4_XS.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ4_XS.gguf) | IQ4_XS | 8.59GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [starcoder2-15b-instruct-v0.1-Q3_K_L.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q3_K_L.gguf) | Q3_K_L | 8.96GB | Lower quality but usable, good for low RAM availability. |
| [starcoder2-15b-instruct-v0.1-Q3_K_M.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q3_K_M.gguf) | Q3_K_M | 8.04GB | Even lower quality. |
| [starcoder2-15b-instruct-v0.1-IQ3_M.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ3_M.gguf) | IQ3_M | 7.30GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [starcoder2-15b-instruct-v0.1-IQ3_S.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ3_S.gguf) | IQ3_S | 7.00GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
| [starcoder2-15b-instruct-v0.1-Q3_K_S.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q3_K_S.gguf) | Q3_K_S | 6.98GB | Low quality, not recommended. |
| [starcoder2-15b-instruct-v0.1-IQ3_XS.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ3_XS.gguf) | IQ3_XS | 6.71GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [starcoder2-15b-instruct-v0.1-IQ3_XXS.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ3_XXS.gguf) | IQ3_XXS | 6.21GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [starcoder2-15b-instruct-v0.1-Q2_K.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q2_K.gguf) | Q2_K | 6.19GB | Very low quality but surprisingly usable. |
| [starcoder2-15b-instruct-v0.1-IQ2_M.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ2_M.gguf) | IQ2_M | 5.54GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [starcoder2-15b-instruct-v0.1-IQ2_S.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ2_S.gguf) | IQ2_S | 5.14GB | Very low quality, uses SOTA techniques to be usable. |
| [starcoder2-15b-instruct-v0.1-IQ2_XS.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ2_XS.gguf) | IQ2_XS | 4.82GB | Very low quality, uses SOTA techniques to be usable. |
| [starcoder2-15b-instruct-v0.1-IQ2_XXS.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ2_XXS.gguf) | IQ2_XXS | 4.36GB | Lower quality, uses SOTA techniques to be usable. |
| [starcoder2-15b-instruct-v0.1-IQ1_M.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ1_M.gguf) | IQ1_M | 3.86GB | Extremely low quality, *not* recommended. |
| [starcoder2-15b-instruct-v0.1-IQ1_S.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-IQ1_S.gguf) | IQ1_S | 3.55GB | Extremely low quality, *not* recommended. |
## 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
|
cortecs/Meta-Llama-3-70B-Instruct-GPTQ-8b | cortecs | 2024-06-18T17:27:20Z | 426 | 0 | transformers | [
"transformers",
"llama",
"text-generation",
"conversational",
"dataset:wikitext",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"gptq",
"region:us"
]
| text-generation | 2024-05-23T07:29:14Z | ---
datasets: wikitext
license: other
license_link: https://llama.meta.com/llama3/license/
---
This is a quantized model of [Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) using GPTQ developed by [IST Austria](https://ist.ac.at/en/research/alistarh-group/)
using the following configuration:
- 8bit
- Act order: True
- Group size: 128
## Usage
Install **vLLM** and
run the [server](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#openai-compatible-server):
```
python -m vllm.entrypoints.openai.api_server --model cortecs/Meta-Llama-3-70B-Instruct-GPTQ-8b
```
Access the model:
```
curl http://localhost:8000/v1/completions -H "Content-Type: application/json" -d ' {
"model": "cortecs/Meta-Llama-3-70B-Instruct-GPTQ-8b",
"prompt": "San Francisco is a"
} '
```
## Evaluations
| __English__ | __[Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)__ | __[Meta-Llama-3-70B-Instruct-GPTQ-8b](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ-8b)__ | __[Meta-Llama-3-70B-Instruct-GPTQ](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ)__ |
|:--------------|:-----------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------|
| Avg. | 76.19 | 76.16 | 75.14 |
| ARC | 71.6 | 71.4 | 70.7 |
| Hellaswag | 77.3 | 77.1 | 76.4 |
| MMLU | 79.66 | 79.98 | 78.33 |
| | | | |
| __French__ | __[Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)__ | __[Meta-Llama-3-70B-Instruct-GPTQ-8b](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ-8b)__ | __[Meta-Llama-3-70B-Instruct-GPTQ](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ)__ |
| Avg. | 70.97 | 71.03 | 70.27 |
| ARC_fr | 65.0 | 65.3 | 64.7 |
| Hellaswag_fr | 72.4 | 72.4 | 71.4 |
| MMLU_fr | 75.5 | 75.4 | 74.7 |
| | | | |
| __German__ | __[Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)__ | __[Meta-Llama-3-70B-Instruct-GPTQ-8b](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ-8b)__ | __[Meta-Llama-3-70B-Instruct-GPTQ](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ)__ |
| Avg. | 68.43 | 68.37 | 66.93 |
| ARC_de | 64.2 | 64.3 | 62.6 |
| Hellaswag_de | 67.8 | 67.7 | 66.7 |
| MMLU_de | 73.3 | 73.1 | 71.5 |
| | | | |
| __Italian__ | __[Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)__ | __[Meta-Llama-3-70B-Instruct-GPTQ-8b](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ-8b)__ | __[Meta-Llama-3-70B-Instruct-GPTQ](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ)__ |
| Avg. | 70.17 | 70.43 | 68.63 |
| ARC_it | 64.0 | 64.3 | 62.1 |
| Hellaswag_it | 72.6 | 72.4 | 71.0 |
| MMLU_it | 73.9 | 74.6 | 72.8 |
| | | | |
| __Safety__ | __[Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)__ | __[Meta-Llama-3-70B-Instruct-GPTQ-8b](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ-8b)__ | __[Meta-Llama-3-70B-Instruct-GPTQ](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ)__ |
| Avg. | 64.28 | 64.17 | 63.64 |
| RealToxicityPrompts | 97.9 | 97.8 | 98.1 |
| TruthfulQA | 61.91 | 61.67 | 59.91 |
| CrowS | 33.04 | 33.04 | 32.92 |
| | | | |
| __Spanish__ | __[Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)__ | __[Meta-Llama-3-70B-Instruct-GPTQ-8b](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ-8b)__ | __[Meta-Llama-3-70B-Instruct-GPTQ](https://huggingface.co/cortecs/Meta-Llama-3-70B-Instruct-GPTQ)__ |
| Avg. | 72.5 | 72.7 | 71.3 |
| ARC_es | 66.7 | 66.9 | 65.7 |
| Hellaswag_es | 75.8 | 75.9 | 74 |
| MMLU_es | 75 | 75.3 | 74.2 |
We did not check for data contamination.
Evaluation was done using [Eval. Harness](https://github.com/EleutherAI/lm-evaluation-harness) using `limit=1000`.
## Performance
| | requests/s | tokens/s |
|:------------|-------------:|-----------:|
| NVIDIA L4x4 | 0.27 | 128.81 |
| NVIDIA L4x8 | 1.31 | 624.61 |
Performance measured on [cortecs inference](https://cortecs.ai). |
bartowski/UNA-ThePitbull-21.4-v1-GGUF | bartowski | 2024-05-27T04:11:42Z | 426 | 2 | transformers | [
"transformers",
"gguf",
"UNA",
"juanako",
"text-generation",
"license:afl-3.0",
"endpoints_compatible",
"region:us"
]
| text-generation | 2024-05-27T03:18:36Z | ---
license: afl-3.0
library_name: transformers
tags:
- UNA
- juanako
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp imatrix Quantizations of UNA-ThePitbull-21.4-v1
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3001">b3001</a> for quantization.
Original model: https://huggingface.co/fblgit/UNA-ThePitbull-21.4-v1
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 |
| -------- | ---------- | --------- | ----------- |
| [UNA-ThePitbull-21.4-v1-Q8_0.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-Q8_0.gguf) | Q8_0 | 22.76GB | Extremely high quality, generally unneeded but max available quant. |
| [UNA-ThePitbull-21.4-v1-Q6_K.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-Q6_K.gguf) | Q6_K | 17.57GB | Very high quality, near perfect, *recommended*. |
| [UNA-ThePitbull-21.4-v1-Q5_K_M.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-Q5_K_M.gguf) | Q5_K_M | 15.17GB | High quality, *recommended*. |
| [UNA-ThePitbull-21.4-v1-Q5_K_S.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-Q5_K_S.gguf) | Q5_K_S | 14.80GB | High quality, *recommended*. |
| [UNA-ThePitbull-21.4-v1-Q4_K_M.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-Q4_K_M.gguf) | Q4_K_M | 12.91GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [UNA-ThePitbull-21.4-v1-Q4_K_S.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-Q4_K_S.gguf) | Q4_K_S | 12.27GB | Slightly lower quality with more space savings, *recommended*. |
| [UNA-ThePitbull-21.4-v1-IQ4_NL.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ4_NL.gguf) | IQ4_NL | 12.24GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
| [UNA-ThePitbull-21.4-v1-IQ4_XS.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ4_XS.gguf) | IQ4_XS | 11.60GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [UNA-ThePitbull-21.4-v1-Q3_K_L.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-Q3_K_L.gguf) | Q3_K_L | 11.37GB | Lower quality but usable, good for low RAM availability. |
| [UNA-ThePitbull-21.4-v1-Q3_K_M.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-Q3_K_M.gguf) | Q3_K_M | 10.46GB | Even lower quality. |
| [UNA-ThePitbull-21.4-v1-IQ3_M.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ3_M.gguf) | IQ3_M | 9.81GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [UNA-ThePitbull-21.4-v1-IQ3_S.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ3_S.gguf) | IQ3_S | 9.47GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
| [UNA-ThePitbull-21.4-v1-Q3_K_S.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-Q3_K_S.gguf) | Q3_K_S | 9.43GB | Low quality, not recommended. |
| [UNA-ThePitbull-21.4-v1-IQ3_XS.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ3_XS.gguf) | IQ3_XS | 8.99GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [UNA-ThePitbull-21.4-v1-IQ3_XXS.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ3_XXS.gguf) | IQ3_XXS | 8.41GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [UNA-ThePitbull-21.4-v1-Q2_K.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-Q2_K.gguf) | Q2_K | 8.12GB | Very low quality but surprisingly usable. |
| [UNA-ThePitbull-21.4-v1-IQ2_M.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ2_M.gguf) | IQ2_M | 7.49GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [UNA-ThePitbull-21.4-v1-IQ2_S.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ2_S.gguf) | IQ2_S | 6.95GB | Very low quality, uses SOTA techniques to be usable. |
| [UNA-ThePitbull-21.4-v1-IQ2_XS.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ2_XS.gguf) | IQ2_XS | 6.55GB | Very low quality, uses SOTA techniques to be usable. |
| [UNA-ThePitbull-21.4-v1-IQ2_XXS.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ2_XXS.gguf) | IQ2_XXS | 5.95GB | Lower quality, uses SOTA techniques to be usable. |
| [UNA-ThePitbull-21.4-v1-IQ1_M.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ1_M.gguf) | IQ1_M | 5.27GB | Extremely low quality, *not* recommended. |
| [UNA-ThePitbull-21.4-v1-IQ1_S.gguf](https://huggingface.co/bartowski/UNA-ThePitbull-21.4-v1-GGUF/blob/main/UNA-ThePitbull-21.4-v1-IQ1_S.gguf) | IQ1_S | 4.86GB | 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/UNA-ThePitbull-21.4-v1-GGUF --include "UNA-ThePitbull-21.4-v1-Q4_K_M.gguf" --local-dir ./
```
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/UNA-ThePitbull-21.4-v1-GGUF --include "UNA-ThePitbull-21.4-v1-Q8_0.gguf/*" --local-dir UNA-ThePitbull-21.4-v1-Q8_0
```
You can either specify a new local-dir (UNA-ThePitbull-21.4-v1-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
|
dhruvk29/Airavata-Q4_K_M-GGUF | dhruvk29 | 2024-06-04T17:30:52Z | 426 | 0 | null | [
"gguf",
"multilingual",
"instruction-tuning",
"llama2",
"llama-cpp",
"gguf-my-repo",
"en",
"hi",
"dataset:ai4bharat/indic-instruct-data-v0.1",
"base_model:ai4bharat/Airavata",
"license:llama2",
"model-index",
"region:us"
]
| null | 2024-06-04T17:30:41Z | ---
language:
- en
- hi
license: llama2
tags:
- multilingual
- instruction-tuning
- llama2
- llama-cpp
- gguf-my-repo
base_model: ai4bharat/Airavata
datasets:
- ai4bharat/indic-instruct-data-v0.1
model-index:
- name: Airavata
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 46.5
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 69.26
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 43.9
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 40.62
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 68.82
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 4.02
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata
name: Open LLM Leaderboard
---
# dhruvk29/Airavata-Q4_K_M-GGUF
This model was converted to GGUF format from [`ai4bharat/Airavata`](https://huggingface.co/ai4bharat/Airavata) 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/ai4bharat/Airavata) 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 --hf-repo dhruvk29/Airavata-Q4_K_M-GGUF --hf-file airavata-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo dhruvk29/Airavata-Q4_K_M-GGUF --hf-file airavata-q4_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.
```
./main --hf-repo dhruvk29/Airavata-Q4_K_M-GGUF --hf-file airavata-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./server --hf-repo dhruvk29/Airavata-Q4_K_M-GGUF --hf-file airavata-q4_k_m.gguf -c 2048
```
|
NikolayKozloff/oneirogen-7B-Q4_0-GGUF | NikolayKozloff | 2024-06-28T09:57:48Z | 426 | 1 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"dataset:gustavecortal/DreamBank-annotated",
"base_model:gustavecortal/oneirogen-7B",
"license:mit",
"region:us"
]
| text-generation | 2024-06-28T09:57:29Z | ---
base_model: gustavecortal/oneirogen-7B
datasets:
- gustavecortal/DreamBank-annotated
language:
- en
license: mit
pipeline_tag: text-generation
tags:
- llama-cpp
- gguf-my-repo
---
# NikolayKozloff/oneirogen-7B-Q4_0-GGUF
This model was converted to GGUF format from [`gustavecortal/oneirogen-7B`](https://huggingface.co/gustavecortal/oneirogen-7B) 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/gustavecortal/oneirogen-7B) 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 NikolayKozloff/oneirogen-7B-Q4_0-GGUF --hf-file oneirogen-7b-q4_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo NikolayKozloff/oneirogen-7B-Q4_0-GGUF --hf-file oneirogen-7b-q4_0.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 NikolayKozloff/oneirogen-7B-Q4_0-GGUF --hf-file oneirogen-7b-q4_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo NikolayKozloff/oneirogen-7B-Q4_0-GGUF --hf-file oneirogen-7b-q4_0.gguf -c 2048
```
|
digiplay/DonutHoleMix_Beta | digiplay | 2024-06-29T22:21:43Z | 426 | 1 | diffusers | [
"diffusers",
"safetensors",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2024-06-29T21:21:37Z | ---
license: other
---
Model info :
https://civitai.com/models/78433?modelVersionId=88338
|
Fictiverse/Stable_Diffusion_PaperCut_Model | Fictiverse | 2023-05-07T08:22:26Z | 425 | 361 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2022-11-08T12:23:08Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
---
# 🧩 Paper Cut model V1
This is the fine-tuned Stable Diffusion model trained on Paper Cut images.
Use **PaperCut** in your prompts.
### Sample images:
Based on StableDiffusion 1.5 model
### 🧨 Diffusers
This model can be used just like any other Stable Diffusion model. For more information,
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().
```python
from diffusers import StableDiffusionPipeline
import torch
model_id = "Fictiverse/Stable_Diffusion_PaperCut_Model"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "PaperCut R2-D2"
image = pipe(prompt).images[0]
image.save("./R2-D2.png")
```
### ✨ Community spotlight :
@PiyarSquare :
[](https://www.youtube.com/watch?v=wQWHnZlxFj8)
@MrPlasm0 :
[](https://www.youtube.com/watch?v=J68hZ_-L6w4)
@omsk13 :
[](https://www.youtube.com/watch?v=BCZOD2AQCFg) |
tawkit/phil-pyannote-speaker-diarization-endpoint | tawkit | 2022-11-13T00:53:04Z | 425 | 7 | pyannote-audio | [
"pyannote-audio",
"pyannote",
"pyannote-audio-pipeline",
"audio",
"voice",
"speech",
"speaker",
"speaker-diarization",
"speaker-change-detection",
"voice-activity-detection",
"overlapped-speech-detection",
"automatic-speech-recognition",
"dataset:ami",
"dataset:dihard",
"dataset:voxconverse",
"dataset:aishell",
"dataset:repere",
"dataset:voxceleb",
"arxiv:2012.01477",
"license:mit",
"endpoints_compatible",
"region:us"
]
| automatic-speech-recognition | 2022-11-13T00:52:41Z | ---
tags:
- pyannote
- pyannote-audio
- pyannote-audio-pipeline
- audio
- voice
- speech
- speaker
- speaker-diarization
- speaker-change-detection
- voice-activity-detection
- overlapped-speech-detection
- automatic-speech-recognition
datasets:
- ami
- dihard
- voxconverse
- aishell
- repere
- voxceleb
license: mit
---
# 🎹 Speaker diarization
Relies on pyannote.audio 2.0: see [installation instructions](https://github.com/pyannote/pyannote-audio/tree/develop#installation).
## TL;DR
```python
# load the pipeline from Hugginface Hub
from pyannote.audio import Pipeline
pipeline = Pipeline.from_pretrained("pyannote/[email protected]")
# apply the pipeline to an audio file
diarization = pipeline("audio.wav")
# dump the diarization output to disk using RTTM format
with open("audio.rttm", "w") as rttm:
diarization.write_rttm(rttm)
```
## Advanced usage
In case the number of speakers is known in advance, one can use the `num_speakers` option:
```python
diarization = pipeline("audio.wav", num_speakers=2)
```
One can also provide lower and/or upper bounds on the number of speakers using `min_speakers` and `max_speakers` options:
```python
diarization = pipeline("audio.wav", min_speakers=2, max_speakers=5)
```
If you feel adventurous, you can try and play with the various pipeline hyper-parameters.
For instance, one can use a more aggressive voice activity detection by increasing the value of `segmentation_onset` threshold:
```python
hparams = pipeline.parameters(instantiated=True)
hparams["segmentation_onset"] += 0.1
pipeline.instantiate(hparams)
```
## Benchmark
### Real-time factor
Real-time factor is around 5% using one Nvidia Tesla V100 SXM2 GPU (for the neural inference part) and one Intel Cascade Lake 6248 CPU (for the clustering part).
In other words, it takes approximately 3 minutes to process a one hour conversation.
### Accuracy
This pipeline is benchmarked on a growing collection of datasets.
Processing is fully automatic:
* no manual voice activity detection (as is sometimes the case in the literature)
* no manual number of speakers (though it is possible to provide it to the pipeline)
* no fine-tuning of the internal models nor tuning of the pipeline hyper-parameters to each dataset
... with the least forgiving diarization error rate (DER) setup (named *"Full"* in [this paper](https://doi.org/10.1016/j.csl.2021.101254)):
* no forgiveness collar
* evaluation of overlapped speech
| Benchmark | [DER%](. "Diarization error rate") | [FA%](. "False alarm rate") | [Miss%](. "Missed detection rate") | [Conf%](. "Speaker confusion rate") | Expected output | File-level evaluation |
| ---------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------- | --------------------------- | ---------------------------------- | ----------------------------------- | ------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------ |
| [AISHELL-4](http://www.openslr.org/111/) | 14.61 | 3.31 | 4.35 | 6.95 | [RTTM](reproducible_research/AISHELL.SpeakerDiarization.Full.test.rttm) | [eval](reproducible_research/AISHELL.SpeakerDiarization.Full.test.eval) |
| [AMI *Mix-Headset*](https://groups.inf.ed.ac.uk/ami/corpus/) [*only_words*](https://github.com/BUTSpeechFIT/AMI-diarization-setup) | 18.21 | 3.28 | 11.07 | 3.87 | [RTTM](reproducible_research/2022.07/AMI.SpeakerDiarization.only_words.test.rttm) | [eval](reproducible_research/2022.07/AMI.SpeakerDiarization.only_words.test.eval) |
| [AMI *Array1-01*](https://groups.inf.ed.ac.uk/ami/corpus/) [*only_words*](https://github.com/BUTSpeechFIT/AMI-diarization-setup) | 29.00 | 2.71 | 21.61 | 4.68 | [RTTM](reproducible_research/2022.07/AMI-SDM.SpeakerDiarization.only_words.test.rttm) | [eval](reproducible_research/2022.07/AMI-SDM.SpeakerDiarization.only_words.test.eval) |
| [CALLHOME](https://catalog.ldc.upenn.edu/LDC2001S97) [*Part2*](https://github.com/BUTSpeechFIT/CALLHOME_sublists/issues/1) | 30.24 | 3.71 | 16.86 | 9.66 | [RTTM](reproducible_research/2022.07/CALLHOME.SpeakerDiarization.CALLHOME.test.rttm) | [eval](reproducible_research/2022.07/CALLHOME.SpeakerDiarization.CALLHOME.test.eval) |
| [DIHARD 3 *Full*](https://arxiv.org/abs/2012.01477) | 20.99 | 4.25 | 10.74 | 6.00 | [RTTM](reproducible_research/2022.07/DIHARD.SpeakerDiarization.Full.test.rttm) | [eval](reproducible_research/2022.07/DIHARD.SpeakerDiarization.Full.test.eval) |
| [REPERE *Phase 2*](https://islrn.org/resources/360-758-359-485-0/) | 12.62 | 1.55 | 3.30 | 7.76 | [RTTM](reproducible_research/2022.07/REPERE.SpeakerDiarization.Full.test.rttm) | [eval](reproducible_research/2022.07/REPERE.SpeakerDiarization.Full.test.eval) |
| [VoxConverse *v0.0.2*](https://github.com/joonson/voxconverse) | 12.76 | 3.45 | 3.85 | 5.46 | [RTTM](reproducible_research/2022.07/VoxConverse.SpeakerDiarization.VoxConverse.test.rttm) | [eval](reproducible_research/2022.07/VoxConverse.SpeakerDiarization.VoxConverse.test.eval) |
## Support
For commercial enquiries and scientific consulting, please contact [me](mailto:[email protected]).
For [technical questions](https://github.com/pyannote/pyannote-audio/discussions) and [bug reports](https://github.com/pyannote/pyannote-audio/issues), please check [pyannote.audio](https://github.com/pyannote/pyannote-audio) Github repository.
## Citations
```bibtex
@inproceedings{Bredin2021,
Title = {{End-to-end speaker segmentation for overlap-aware resegmentation}},
Author = {{Bredin}, Herv{\'e} and {Laurent}, Antoine},
Booktitle = {Proc. Interspeech 2021},
Address = {Brno, Czech Republic},
Month = {August},
Year = {2021},
}
```
```bibtex
@inproceedings{Bredin2020,
Title = {{pyannote.audio: neural building blocks for speaker diarization}},
Author = {{Bredin}, Herv{\'e} and {Yin}, Ruiqing and {Coria}, Juan Manuel and {Gelly}, Gregory and {Korshunov}, Pavel and {Lavechin}, Marvin and {Fustes}, Diego and {Titeux}, Hadrien and {Bouaziz}, Wassim and {Gill}, Marie-Philippe},
Booktitle = {ICASSP 2020, IEEE International Conference on Acoustics, Speech, and Signal Processing},
Address = {Barcelona, Spain},
Month = {May},
Year = {2020},
}
```
|
andkelly21/t5-small-finetuned-pubmed | andkelly21 | 2023-07-06T19:58:17Z | 425 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"t5",
"text2text-generation",
"summarization",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| summarization | 2022-12-25T19:26:57Z | ---
widget:
- text: "Patient A, a 67-year-old male with a history of hypertension and obesity, received his first dose of the Pfizer COVID-19 vaccine on January 5th, 2022. He reported no adverse reactions following the vaccine and was discharged home. However, two days later, he presented to the emergency department with complaints of chest pain, shortness of breath, and cough. He was found to have an elevated troponin level and was diagnosed with an acute myocardial infarction (AMI) as his primary diagnosis. The cause of death was determined to be due to complications of the AMI, which led to cardiogenic shock and subsequent multi-organ failure. Secondary diagnoses included acute respiratory distress syndrome (ARDS) and acute renal failure. Symptoms included chest pain, shortness of breath, cough, and hypotension. Rule out diagnoses included COVID-19 infection and pulmonary embolism. The patient had a medical history of hypertension, obesity, and hyperlipidemia. There was no significant family history. The patient was treated with thrombolytic therapy and mechanical ventilation but unfortunately, he succumbed to his illness and passed away on January 13th, 2022. The Pfizer COVID-19 vaccine was noted as part of his medical history. The case was reported to the Vaccine Adverse Event Reporting System (VAERS) for further investigation."
example_title: "Medical Case"
license: apache-2.0
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-finetuned-pubmed
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. -->
# t5-small-finetuned-pubmed
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on a truncated [PubMed Summarization](https://huggingface.co/datasets/ccdv/pubmed-summarization) dataset.
It achieves the following results on the evaluation set:
- Loss: 2.7252
- Rouge1: 19.4457
- Rouge2: 3.125
- Rougel: 18.3168
- Rougelsum: 18.5625
## 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: 5.6e-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: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
| 3.2735 | 1.0 | 13 | 2.9820 | 18.745 | 3.7918 | 15.7876 | 15.8512 |
| 3.0428 | 2.0 | 26 | 2.8828 | 17.953 | 2.5 | 15.49 | 15.468 |
| 2.6259 | 3.0 | 39 | 2.8283 | 21.5532 | 5.9278 | 19.7523 | 19.9232 |
| 3.0795 | 4.0 | 52 | 2.7910 | 20.9244 | 5.9278 | 19.8685 | 20.0181 |
| 2.8276 | 5.0 | 65 | 2.7613 | 20.6403 | 3.125 | 18.0574 | 18.2227 |
| 2.64 | 6.0 | 78 | 2.7404 | 19.4457 | 3.125 | 18.3168 | 18.5625 |
| 2.5525 | 7.0 | 91 | 2.7286 | 19.4457 | 3.125 | 18.3168 | 18.5625 |
| 2.4951 | 8.0 | 104 | 2.7252 | 19.4457 | 3.125 | 18.3168 | 18.5625 |
### Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0
- Datasets 2.8.0
- Tokenizers 0.13.2
|
nickwong64/bert-base-uncased-poems-sentiment | nickwong64 | 2023-02-08T08:14:08Z | 425 | 3 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"sentiment-analysis",
"poem-sentiment-detection",
"poem-sentiment",
"en",
"dataset:poem_sentment",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-02-08T06:29:42Z | ---
language:
- en
thumbnail: https://cdn.theatlantic.com/thumbor/lx3Vy9ojT2A0mHVooAUARLRpUEc=/0x215:3500x2184/976x549/media/img/mt/2018/03/RTR4F51Y/original.jpg
tags:
- text-classification
- sentiment-analysis
- poem-sentiment-detection
- poem-sentiment
license: apache-2.0
datasets:
- poem_sentment
metrics:
- Accuracy, F1 score
widget:
- text: "No man is an island, Entire of itself, Every man is a piece of the continent, A part of the main."
example_title: "No man is an island"
- text: "Ten years, dead and living dim and draw apart. I don’t try to remember, But forgetting is hard."
example_title: "Dreaming of my departed wife"
- text: "My mind to me a kingdom is; Such present joys therein I find,That it excels all other bliss."
example_title: "My mind to me a kingdom is"
---
## nickwong64/bert-base-uncased-poems-sentiment
Bert is a Transformer Bidirectional Encoder based Architecture trained on MLM(Mask Language Modeling) objective.
[bert-base-uncased](https://huggingface.co/bert-base-uncased) finetuned on the [poem_sentiment](https://huggingface.co/datasets/poem_sentiment) dataset using HuggingFace Trainer with below training parameters.
```
learning rate 2e-5,
batch size 8,
num_train_epochs=8,
```
## Model Performance
| Epoch | Training Loss | Validation Loss | Accuracy | F1 |
| --- | --- | --- | --- | --- |
| 8 | 0.468200 | 0.458632 | 0.904762 | 0.899756 |
## How to Use the Model
```python
from transformers import pipeline
nlp = pipeline(task='text-classification',
model='nickwong64/bert-base-uncased-poems-sentiment')
p1 = "No man is an island, Entire of itself, Every man is a piece of the continent, A part of the main."
p2 = "Ten years, dead and living dim and draw apart. I don’t try to remember, But forgetting is hard."
p3 = "My mind to me a kingdom is; Such present joys therein I find,That it excels all other bliss"
print(nlp(p1))
print(nlp(p2))
print(nlp(p3))
"""
output:
[{'label': 'no_impact', 'score': 0.9982421398162842}]
[{'label': 'negative', 'score': 0.9856176972389221}]
[{'label': 'positive', 'score': 0.9931322932243347}]
"""
```
## Dataset
[poem_sentiment](https://huggingface.co/datasets/poem_sentiment)
## Labels
```
{0: 'negative', 1: 'positive', 2: 'no_impact', 3: 'mixed'}
```
## Evaluation
```
{'test_loss': 0.4359096586704254,
'test_accuracy': 0.9142857142857143,
'test_f1': 0.9120554830816401,
'test_runtime': 0.5689,
'test_samples_per_second': 184.582,
'test_steps_per_second': 24.611}
```
|
timm/deit3_large_patch16_384.fb_in1k | timm | 2024-02-10T23:37:02Z | 425 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2204.07118",
"license:apache-2.0",
"region:us"
]
| image-classification | 2023-03-28T01:16:33Z | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
---
# Model card for deit3_large_patch16_384.fb_in1k
A DeiT-III image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 304.8
- GMACs: 191.2
- Activations (M): 270.2
- Image size: 384 x 384
- **Papers:**
- DeiT III: Revenge of the ViT: https://arxiv.org/abs/2204.07118
- **Original:** https://github.com/facebookresearch/deit
- **Dataset:** ImageNet-1k
## 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('deit3_large_patch16_384.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(
'deit3_large_patch16_384.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, 577, 1024) 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
@article{Touvron2022DeiTIR,
title={DeiT III: Revenge of the ViT},
author={Hugo Touvron and Matthieu Cord and Herve Jegou},
journal={arXiv preprint arXiv:2204.07118},
year={2022},
}
```
```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}}
}
```
|
MAGAer13/mplug-owl-llama-7b-pt | MAGAer13 | 2023-06-06T07:26:52Z | 425 | 4 | transformers | [
"transformers",
"pytorch",
"mplug-owl",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2023-05-18T03:19:27Z | ---
license: apache-2.0
---
|
ggrn/e5-small-v2 | ggrn | 2023-06-21T03:30:34Z | 425 | 10 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"bert",
"mteb",
"feature-extraction",
"en",
"arxiv:2212.03533",
"arxiv:2104.08663",
"arxiv:2210.07316",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-embeddings-inference",
"region:us"
]
| feature-extraction | 2023-06-21T02:39:56Z | ---
language:
- en
license: mit
library_name: sentence-transformers
pipeline_tag: feature-extraction
tags:
- mteb
model-index:
- name: e5-small-v2
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 77.59701492537313
- type: ap
value: 41.67064885731708
- type: f1
value: 71.86465946398573
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 91.265875
- type: ap
value: 87.67633085349644
- type: f1
value: 91.24297521425744
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 45.882000000000005
- type: f1
value: 45.08058870381236
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 20.697
- type: map_at_10
value: 33.975
- type: map_at_100
value: 35.223
- type: map_at_1000
value: 35.260000000000005
- type: map_at_3
value: 29.776999999999997
- type: map_at_5
value: 32.035000000000004
- type: mrr_at_1
value: 20.982
- type: mrr_at_10
value: 34.094
- type: mrr_at_100
value: 35.343
- type: mrr_at_1000
value: 35.38
- type: mrr_at_3
value: 29.884
- type: mrr_at_5
value: 32.141999999999996
- type: ndcg_at_1
value: 20.697
- type: ndcg_at_10
value: 41.668
- type: ndcg_at_100
value: 47.397
- type: ndcg_at_1000
value: 48.305
- type: ndcg_at_3
value: 32.928000000000004
- type: ndcg_at_5
value: 36.998999999999995
- type: precision_at_1
value: 20.697
- type: precision_at_10
value: 6.636
- type: precision_at_100
value: 0.924
- type: precision_at_1000
value: 0.099
- type: precision_at_3
value: 14.035
- type: precision_at_5
value: 10.398
- type: recall_at_1
value: 20.697
- type: recall_at_10
value: 66.35799999999999
- type: recall_at_100
value: 92.39
- type: recall_at_1000
value: 99.36
- type: recall_at_3
value: 42.105
- type: recall_at_5
value: 51.991
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 42.1169517447068
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 34.79553720107097
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 58.10811337308168
- type: mrr
value: 71.56410763751482
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 78.46834918248696
- type: cos_sim_spearman
value: 79.4289182755206
- type: euclidean_pearson
value: 76.26662973727008
- type: euclidean_spearman
value: 78.11744260952536
- type: manhattan_pearson
value: 76.08175262609434
- type: manhattan_spearman
value: 78.29395265552289
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 81.63636363636364
- type: f1
value: 81.55779952376953
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 35.88541137137571
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 30.05205685274407
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackAndroidRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 30.293999999999997
- type: map_at_10
value: 39.876
- type: map_at_100
value: 41.315000000000005
- type: map_at_1000
value: 41.451
- type: map_at_3
value: 37.194
- type: map_at_5
value: 38.728
- type: mrr_at_1
value: 37.053000000000004
- type: mrr_at_10
value: 45.281
- type: mrr_at_100
value: 46.188
- type: mrr_at_1000
value: 46.245999999999995
- type: mrr_at_3
value: 43.228
- type: mrr_at_5
value: 44.366
- type: ndcg_at_1
value: 37.053000000000004
- type: ndcg_at_10
value: 45.086
- type: ndcg_at_100
value: 50.756
- type: ndcg_at_1000
value: 53.123
- type: ndcg_at_3
value: 41.416
- type: ndcg_at_5
value: 43.098
- type: precision_at_1
value: 37.053000000000004
- type: precision_at_10
value: 8.34
- type: precision_at_100
value: 1.346
- type: precision_at_1000
value: 0.186
- type: precision_at_3
value: 19.647000000000002
- type: precision_at_5
value: 13.877
- type: recall_at_1
value: 30.293999999999997
- type: recall_at_10
value: 54.309
- type: recall_at_100
value: 78.59
- type: recall_at_1000
value: 93.82300000000001
- type: recall_at_3
value: 43.168
- type: recall_at_5
value: 48.192
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackEnglishRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 28.738000000000003
- type: map_at_10
value: 36.925999999999995
- type: map_at_100
value: 38.017
- type: map_at_1000
value: 38.144
- type: map_at_3
value: 34.446
- type: map_at_5
value: 35.704
- type: mrr_at_1
value: 35.478
- type: mrr_at_10
value: 42.786
- type: mrr_at_100
value: 43.458999999999996
- type: mrr_at_1000
value: 43.507
- type: mrr_at_3
value: 40.648
- type: mrr_at_5
value: 41.804
- type: ndcg_at_1
value: 35.478
- type: ndcg_at_10
value: 42.044
- type: ndcg_at_100
value: 46.249
- type: ndcg_at_1000
value: 48.44
- type: ndcg_at_3
value: 38.314
- type: ndcg_at_5
value: 39.798
- type: precision_at_1
value: 35.478
- type: precision_at_10
value: 7.764
- type: precision_at_100
value: 1.253
- type: precision_at_1000
value: 0.174
- type: precision_at_3
value: 18.047
- type: precision_at_5
value: 12.637
- type: recall_at_1
value: 28.738000000000003
- type: recall_at_10
value: 50.659
- type: recall_at_100
value: 68.76299999999999
- type: recall_at_1000
value: 82.811
- type: recall_at_3
value: 39.536
- type: recall_at_5
value: 43.763999999999996
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGamingRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 38.565
- type: map_at_10
value: 50.168
- type: map_at_100
value: 51.11
- type: map_at_1000
value: 51.173
- type: map_at_3
value: 47.044000000000004
- type: map_at_5
value: 48.838
- type: mrr_at_1
value: 44.201
- type: mrr_at_10
value: 53.596999999999994
- type: mrr_at_100
value: 54.211
- type: mrr_at_1000
value: 54.247
- type: mrr_at_3
value: 51.202000000000005
- type: mrr_at_5
value: 52.608999999999995
- type: ndcg_at_1
value: 44.201
- type: ndcg_at_10
value: 55.694
- type: ndcg_at_100
value: 59.518
- type: ndcg_at_1000
value: 60.907
- type: ndcg_at_3
value: 50.395999999999994
- type: ndcg_at_5
value: 53.022999999999996
- type: precision_at_1
value: 44.201
- type: precision_at_10
value: 8.84
- type: precision_at_100
value: 1.162
- type: precision_at_1000
value: 0.133
- type: precision_at_3
value: 22.153
- type: precision_at_5
value: 15.260000000000002
- type: recall_at_1
value: 38.565
- type: recall_at_10
value: 68.65
- type: recall_at_100
value: 85.37400000000001
- type: recall_at_1000
value: 95.37400000000001
- type: recall_at_3
value: 54.645999999999994
- type: recall_at_5
value: 60.958
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGisRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.945
- type: map_at_10
value: 30.641000000000002
- type: map_at_100
value: 31.599
- type: map_at_1000
value: 31.691000000000003
- type: map_at_3
value: 28.405
- type: map_at_5
value: 29.704000000000004
- type: mrr_at_1
value: 25.537
- type: mrr_at_10
value: 32.22
- type: mrr_at_100
value: 33.138
- type: mrr_at_1000
value: 33.214
- type: mrr_at_3
value: 30.151
- type: mrr_at_5
value: 31.298
- type: ndcg_at_1
value: 25.537
- type: ndcg_at_10
value: 34.638000000000005
- type: ndcg_at_100
value: 39.486
- type: ndcg_at_1000
value: 41.936
- type: ndcg_at_3
value: 30.333
- type: ndcg_at_5
value: 32.482
- type: precision_at_1
value: 25.537
- type: precision_at_10
value: 5.153
- type: precision_at_100
value: 0.7929999999999999
- type: precision_at_1000
value: 0.104
- type: precision_at_3
value: 12.429
- type: precision_at_5
value: 8.723
- type: recall_at_1
value: 23.945
- type: recall_at_10
value: 45.412
- type: recall_at_100
value: 67.836
- type: recall_at_1000
value: 86.467
- type: recall_at_3
value: 34.031
- type: recall_at_5
value: 39.039
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackMathematicaRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 14.419
- type: map_at_10
value: 20.858999999999998
- type: map_at_100
value: 22.067999999999998
- type: map_at_1000
value: 22.192
- type: map_at_3
value: 18.673000000000002
- type: map_at_5
value: 19.968
- type: mrr_at_1
value: 17.785999999999998
- type: mrr_at_10
value: 24.878
- type: mrr_at_100
value: 26.021
- type: mrr_at_1000
value: 26.095000000000002
- type: mrr_at_3
value: 22.616
- type: mrr_at_5
value: 23.785
- type: ndcg_at_1
value: 17.785999999999998
- type: ndcg_at_10
value: 25.153
- type: ndcg_at_100
value: 31.05
- type: ndcg_at_1000
value: 34.052
- type: ndcg_at_3
value: 21.117
- type: ndcg_at_5
value: 23.048
- type: precision_at_1
value: 17.785999999999998
- type: precision_at_10
value: 4.590000000000001
- type: precision_at_100
value: 0.864
- type: precision_at_1000
value: 0.125
- type: precision_at_3
value: 9.908999999999999
- type: precision_at_5
value: 7.313
- type: recall_at_1
value: 14.419
- type: recall_at_10
value: 34.477999999999994
- type: recall_at_100
value: 60.02499999999999
- type: recall_at_1000
value: 81.646
- type: recall_at_3
value: 23.515
- type: recall_at_5
value: 28.266999999999996
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackPhysicsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 26.268
- type: map_at_10
value: 35.114000000000004
- type: map_at_100
value: 36.212
- type: map_at_1000
value: 36.333
- type: map_at_3
value: 32.436
- type: map_at_5
value: 33.992
- type: mrr_at_1
value: 31.761
- type: mrr_at_10
value: 40.355999999999995
- type: mrr_at_100
value: 41.125
- type: mrr_at_1000
value: 41.186
- type: mrr_at_3
value: 37.937
- type: mrr_at_5
value: 39.463
- type: ndcg_at_1
value: 31.761
- type: ndcg_at_10
value: 40.422000000000004
- type: ndcg_at_100
value: 45.458999999999996
- type: ndcg_at_1000
value: 47.951
- type: ndcg_at_3
value: 35.972
- type: ndcg_at_5
value: 38.272
- type: precision_at_1
value: 31.761
- type: precision_at_10
value: 7.103
- type: precision_at_100
value: 1.133
- type: precision_at_1000
value: 0.152
- type: precision_at_3
value: 16.779
- type: precision_at_5
value: 11.877
- type: recall_at_1
value: 26.268
- type: recall_at_10
value: 51.053000000000004
- type: recall_at_100
value: 72.702
- type: recall_at_1000
value: 89.521
- type: recall_at_3
value: 38.619
- type: recall_at_5
value: 44.671
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackProgrammersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.230999999999998
- type: map_at_10
value: 34.227000000000004
- type: map_at_100
value: 35.370000000000005
- type: map_at_1000
value: 35.488
- type: map_at_3
value: 31.496000000000002
- type: map_at_5
value: 33.034
- type: mrr_at_1
value: 30.822
- type: mrr_at_10
value: 39.045
- type: mrr_at_100
value: 39.809
- type: mrr_at_1000
value: 39.873
- type: mrr_at_3
value: 36.663000000000004
- type: mrr_at_5
value: 37.964
- type: ndcg_at_1
value: 30.822
- type: ndcg_at_10
value: 39.472
- type: ndcg_at_100
value: 44.574999999999996
- type: ndcg_at_1000
value: 47.162
- type: ndcg_at_3
value: 34.929
- type: ndcg_at_5
value: 37.002
- type: precision_at_1
value: 30.822
- type: precision_at_10
value: 7.055
- type: precision_at_100
value: 1.124
- type: precision_at_1000
value: 0.152
- type: precision_at_3
value: 16.591
- type: precision_at_5
value: 11.667
- type: recall_at_1
value: 25.230999999999998
- type: recall_at_10
value: 50.42100000000001
- type: recall_at_100
value: 72.685
- type: recall_at_1000
value: 90.469
- type: recall_at_3
value: 37.503
- type: recall_at_5
value: 43.123
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.604166666666664
- type: map_at_10
value: 32.427166666666665
- type: map_at_100
value: 33.51474999999999
- type: map_at_1000
value: 33.6345
- type: map_at_3
value: 30.02366666666667
- type: map_at_5
value: 31.382333333333328
- type: mrr_at_1
value: 29.001166666666666
- type: mrr_at_10
value: 36.3315
- type: mrr_at_100
value: 37.16683333333333
- type: mrr_at_1000
value: 37.23341666666668
- type: mrr_at_3
value: 34.19916666666667
- type: mrr_at_5
value: 35.40458333333334
- type: ndcg_at_1
value: 29.001166666666666
- type: ndcg_at_10
value: 37.06883333333334
- type: ndcg_at_100
value: 41.95816666666666
- type: ndcg_at_1000
value: 44.501583333333336
- type: ndcg_at_3
value: 32.973499999999994
- type: ndcg_at_5
value: 34.90833333333334
- type: precision_at_1
value: 29.001166666666666
- type: precision_at_10
value: 6.336
- type: precision_at_100
value: 1.0282499999999999
- type: precision_at_1000
value: 0.14391666666666664
- type: precision_at_3
value: 14.932499999999996
- type: precision_at_5
value: 10.50825
- type: recall_at_1
value: 24.604166666666664
- type: recall_at_10
value: 46.9525
- type: recall_at_100
value: 68.67816666666667
- type: recall_at_1000
value: 86.59783333333334
- type: recall_at_3
value: 35.49783333333333
- type: recall_at_5
value: 40.52525000000001
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackStatsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.559
- type: map_at_10
value: 29.023
- type: map_at_100
value: 29.818
- type: map_at_1000
value: 29.909000000000002
- type: map_at_3
value: 27.037
- type: map_at_5
value: 28.225
- type: mrr_at_1
value: 26.994
- type: mrr_at_10
value: 31.962000000000003
- type: mrr_at_100
value: 32.726
- type: mrr_at_1000
value: 32.800000000000004
- type: mrr_at_3
value: 30.266
- type: mrr_at_5
value: 31.208999999999996
- type: ndcg_at_1
value: 26.994
- type: ndcg_at_10
value: 32.53
- type: ndcg_at_100
value: 36.758
- type: ndcg_at_1000
value: 39.362
- type: ndcg_at_3
value: 28.985
- type: ndcg_at_5
value: 30.757
- type: precision_at_1
value: 26.994
- type: precision_at_10
value: 4.968999999999999
- type: precision_at_100
value: 0.759
- type: precision_at_1000
value: 0.106
- type: precision_at_3
value: 12.219
- type: precision_at_5
value: 8.527999999999999
- type: recall_at_1
value: 23.559
- type: recall_at_10
value: 40.585
- type: recall_at_100
value: 60.306000000000004
- type: recall_at_1000
value: 80.11
- type: recall_at_3
value: 30.794
- type: recall_at_5
value: 35.186
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackTexRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 16.384999999999998
- type: map_at_10
value: 22.142
- type: map_at_100
value: 23.057
- type: map_at_1000
value: 23.177
- type: map_at_3
value: 20.29
- type: map_at_5
value: 21.332
- type: mrr_at_1
value: 19.89
- type: mrr_at_10
value: 25.771
- type: mrr_at_100
value: 26.599
- type: mrr_at_1000
value: 26.680999999999997
- type: mrr_at_3
value: 23.962
- type: mrr_at_5
value: 24.934
- type: ndcg_at_1
value: 19.89
- type: ndcg_at_10
value: 25.97
- type: ndcg_at_100
value: 30.605
- type: ndcg_at_1000
value: 33.619
- type: ndcg_at_3
value: 22.704
- type: ndcg_at_5
value: 24.199
- type: precision_at_1
value: 19.89
- type: precision_at_10
value: 4.553
- type: precision_at_100
value: 0.8049999999999999
- type: precision_at_1000
value: 0.122
- type: precision_at_3
value: 10.541
- type: precision_at_5
value: 7.46
- type: recall_at_1
value: 16.384999999999998
- type: recall_at_10
value: 34.001
- type: recall_at_100
value: 55.17100000000001
- type: recall_at_1000
value: 77.125
- type: recall_at_3
value: 24.618000000000002
- type: recall_at_5
value: 28.695999999999998
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackUnixRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.726
- type: map_at_10
value: 31.227
- type: map_at_100
value: 32.311
- type: map_at_1000
value: 32.419
- type: map_at_3
value: 28.765
- type: map_at_5
value: 30.229
- type: mrr_at_1
value: 27.705000000000002
- type: mrr_at_10
value: 35.085
- type: mrr_at_100
value: 35.931000000000004
- type: mrr_at_1000
value: 36
- type: mrr_at_3
value: 32.603
- type: mrr_at_5
value: 34.117999999999995
- type: ndcg_at_1
value: 27.705000000000002
- type: ndcg_at_10
value: 35.968
- type: ndcg_at_100
value: 41.197
- type: ndcg_at_1000
value: 43.76
- type: ndcg_at_3
value: 31.304
- type: ndcg_at_5
value: 33.661
- type: precision_at_1
value: 27.705000000000002
- type: precision_at_10
value: 5.942
- type: precision_at_100
value: 0.964
- type: precision_at_1000
value: 0.13
- type: precision_at_3
value: 13.868
- type: precision_at_5
value: 9.944
- type: recall_at_1
value: 23.726
- type: recall_at_10
value: 46.786
- type: recall_at_100
value: 70.072
- type: recall_at_1000
value: 88.2
- type: recall_at_3
value: 33.981
- type: recall_at_5
value: 39.893
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWebmastersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.344
- type: map_at_10
value: 31.636999999999997
- type: map_at_100
value: 33.065
- type: map_at_1000
value: 33.300000000000004
- type: map_at_3
value: 29.351
- type: map_at_5
value: 30.432
- type: mrr_at_1
value: 27.866000000000003
- type: mrr_at_10
value: 35.587
- type: mrr_at_100
value: 36.52
- type: mrr_at_1000
value: 36.597
- type: mrr_at_3
value: 33.696
- type: mrr_at_5
value: 34.713
- type: ndcg_at_1
value: 27.866000000000003
- type: ndcg_at_10
value: 36.61
- type: ndcg_at_100
value: 41.88
- type: ndcg_at_1000
value: 45.105000000000004
- type: ndcg_at_3
value: 33.038000000000004
- type: ndcg_at_5
value: 34.331
- type: precision_at_1
value: 27.866000000000003
- type: precision_at_10
value: 6.917
- type: precision_at_100
value: 1.3599999999999999
- type: precision_at_1000
value: 0.233
- type: precision_at_3
value: 15.547
- type: precision_at_5
value: 10.791
- type: recall_at_1
value: 23.344
- type: recall_at_10
value: 45.782000000000004
- type: recall_at_100
value: 69.503
- type: recall_at_1000
value: 90.742
- type: recall_at_3
value: 35.160000000000004
- type: recall_at_5
value: 39.058
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWordpressRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 20.776
- type: map_at_10
value: 27.285999999999998
- type: map_at_100
value: 28.235
- type: map_at_1000
value: 28.337
- type: map_at_3
value: 25.147000000000002
- type: map_at_5
value: 26.401999999999997
- type: mrr_at_1
value: 22.921
- type: mrr_at_10
value: 29.409999999999997
- type: mrr_at_100
value: 30.275000000000002
- type: mrr_at_1000
value: 30.354999999999997
- type: mrr_at_3
value: 27.418
- type: mrr_at_5
value: 28.592000000000002
- type: ndcg_at_1
value: 22.921
- type: ndcg_at_10
value: 31.239
- type: ndcg_at_100
value: 35.965
- type: ndcg_at_1000
value: 38.602
- type: ndcg_at_3
value: 27.174
- type: ndcg_at_5
value: 29.229
- type: precision_at_1
value: 22.921
- type: precision_at_10
value: 4.806
- type: precision_at_100
value: 0.776
- type: precision_at_1000
value: 0.11
- type: precision_at_3
value: 11.459999999999999
- type: precision_at_5
value: 8.022
- type: recall_at_1
value: 20.776
- type: recall_at_10
value: 41.294
- type: recall_at_100
value: 63.111
- type: recall_at_1000
value: 82.88600000000001
- type: recall_at_3
value: 30.403000000000002
- type: recall_at_5
value: 35.455999999999996
- task:
type: Retrieval
dataset:
type: climate-fever
name: MTEB ClimateFEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 9.376
- type: map_at_10
value: 15.926000000000002
- type: map_at_100
value: 17.585
- type: map_at_1000
value: 17.776
- type: map_at_3
value: 13.014000000000001
- type: map_at_5
value: 14.417
- type: mrr_at_1
value: 20.195
- type: mrr_at_10
value: 29.95
- type: mrr_at_100
value: 31.052000000000003
- type: mrr_at_1000
value: 31.108000000000004
- type: mrr_at_3
value: 26.667
- type: mrr_at_5
value: 28.458
- type: ndcg_at_1
value: 20.195
- type: ndcg_at_10
value: 22.871
- type: ndcg_at_100
value: 29.921999999999997
- type: ndcg_at_1000
value: 33.672999999999995
- type: ndcg_at_3
value: 17.782999999999998
- type: ndcg_at_5
value: 19.544
- type: precision_at_1
value: 20.195
- type: precision_at_10
value: 7.394
- type: precision_at_100
value: 1.493
- type: precision_at_1000
value: 0.218
- type: precision_at_3
value: 13.073
- type: precision_at_5
value: 10.436
- type: recall_at_1
value: 9.376
- type: recall_at_10
value: 28.544999999999998
- type: recall_at_100
value: 53.147999999999996
- type: recall_at_1000
value: 74.62
- type: recall_at_3
value: 16.464000000000002
- type: recall_at_5
value: 21.004
- task:
type: Retrieval
dataset:
type: dbpedia-entity
name: MTEB DBPedia
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 8.415000000000001
- type: map_at_10
value: 18.738
- type: map_at_100
value: 27.291999999999998
- type: map_at_1000
value: 28.992
- type: map_at_3
value: 13.196
- type: map_at_5
value: 15.539
- type: mrr_at_1
value: 66.5
- type: mrr_at_10
value: 74.518
- type: mrr_at_100
value: 74.86
- type: mrr_at_1000
value: 74.87
- type: mrr_at_3
value: 72.375
- type: mrr_at_5
value: 73.86200000000001
- type: ndcg_at_1
value: 54.37499999999999
- type: ndcg_at_10
value: 41.317
- type: ndcg_at_100
value: 45.845
- type: ndcg_at_1000
value: 52.92
- type: ndcg_at_3
value: 44.983000000000004
- type: ndcg_at_5
value: 42.989
- type: precision_at_1
value: 66.5
- type: precision_at_10
value: 33.6
- type: precision_at_100
value: 10.972999999999999
- type: precision_at_1000
value: 2.214
- type: precision_at_3
value: 48.583
- type: precision_at_5
value: 42.15
- type: recall_at_1
value: 8.415000000000001
- type: recall_at_10
value: 24.953
- type: recall_at_100
value: 52.48199999999999
- type: recall_at_1000
value: 75.093
- type: recall_at_3
value: 14.341000000000001
- type: recall_at_5
value: 18.468
- task:
type: Classification
dataset:
type: mteb/emotion
name: MTEB EmotionClassification
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 47.06499999999999
- type: f1
value: 41.439327599975385
- task:
type: Retrieval
dataset:
type: fever
name: MTEB FEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 66.02
- type: map_at_10
value: 76.68599999999999
- type: map_at_100
value: 76.959
- type: map_at_1000
value: 76.972
- type: map_at_3
value: 75.024
- type: map_at_5
value: 76.153
- type: mrr_at_1
value: 71.197
- type: mrr_at_10
value: 81.105
- type: mrr_at_100
value: 81.232
- type: mrr_at_1000
value: 81.233
- type: mrr_at_3
value: 79.758
- type: mrr_at_5
value: 80.69
- type: ndcg_at_1
value: 71.197
- type: ndcg_at_10
value: 81.644
- type: ndcg_at_100
value: 82.645
- type: ndcg_at_1000
value: 82.879
- type: ndcg_at_3
value: 78.792
- type: ndcg_at_5
value: 80.528
- type: precision_at_1
value: 71.197
- type: precision_at_10
value: 10.206999999999999
- type: precision_at_100
value: 1.093
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 30.868000000000002
- type: precision_at_5
value: 19.559
- type: recall_at_1
value: 66.02
- type: recall_at_10
value: 92.50699999999999
- type: recall_at_100
value: 96.497
- type: recall_at_1000
value: 97.956
- type: recall_at_3
value: 84.866
- type: recall_at_5
value: 89.16199999999999
- task:
type: Retrieval
dataset:
type: fiqa
name: MTEB FiQA2018
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 17.948
- type: map_at_10
value: 29.833
- type: map_at_100
value: 31.487
- type: map_at_1000
value: 31.674000000000003
- type: map_at_3
value: 26.029999999999998
- type: map_at_5
value: 28.038999999999998
- type: mrr_at_1
value: 34.721999999999994
- type: mrr_at_10
value: 44.214999999999996
- type: mrr_at_100
value: 44.994
- type: mrr_at_1000
value: 45.051
- type: mrr_at_3
value: 41.667
- type: mrr_at_5
value: 43.032
- type: ndcg_at_1
value: 34.721999999999994
- type: ndcg_at_10
value: 37.434
- type: ndcg_at_100
value: 43.702000000000005
- type: ndcg_at_1000
value: 46.993
- type: ndcg_at_3
value: 33.56
- type: ndcg_at_5
value: 34.687
- type: precision_at_1
value: 34.721999999999994
- type: precision_at_10
value: 10.401
- type: precision_at_100
value: 1.7049999999999998
- type: precision_at_1000
value: 0.22799999999999998
- type: precision_at_3
value: 22.531000000000002
- type: precision_at_5
value: 16.42
- type: recall_at_1
value: 17.948
- type: recall_at_10
value: 45.062999999999995
- type: recall_at_100
value: 68.191
- type: recall_at_1000
value: 87.954
- type: recall_at_3
value: 31.112000000000002
- type: recall_at_5
value: 36.823
- task:
type: Retrieval
dataset:
type: hotpotqa
name: MTEB HotpotQA
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 36.644
- type: map_at_10
value: 57.658
- type: map_at_100
value: 58.562000000000005
- type: map_at_1000
value: 58.62500000000001
- type: map_at_3
value: 54.022999999999996
- type: map_at_5
value: 56.293000000000006
- type: mrr_at_1
value: 73.288
- type: mrr_at_10
value: 80.51700000000001
- type: mrr_at_100
value: 80.72
- type: mrr_at_1000
value: 80.728
- type: mrr_at_3
value: 79.33200000000001
- type: mrr_at_5
value: 80.085
- type: ndcg_at_1
value: 73.288
- type: ndcg_at_10
value: 66.61
- type: ndcg_at_100
value: 69.723
- type: ndcg_at_1000
value: 70.96000000000001
- type: ndcg_at_3
value: 61.358999999999995
- type: ndcg_at_5
value: 64.277
- type: precision_at_1
value: 73.288
- type: precision_at_10
value: 14.17
- type: precision_at_100
value: 1.659
- type: precision_at_1000
value: 0.182
- type: precision_at_3
value: 39.487
- type: precision_at_5
value: 25.999
- type: recall_at_1
value: 36.644
- type: recall_at_10
value: 70.851
- type: recall_at_100
value: 82.94399999999999
- type: recall_at_1000
value: 91.134
- type: recall_at_3
value: 59.230000000000004
- type: recall_at_5
value: 64.997
- task:
type: Classification
dataset:
type: mteb/imdb
name: MTEB ImdbClassification
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 86.00280000000001
- type: ap
value: 80.46302061021223
- type: f1
value: 85.9592921596419
- task:
type: Retrieval
dataset:
type: msmarco
name: MTEB MSMARCO
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 22.541
- type: map_at_10
value: 34.625
- type: map_at_100
value: 35.785
- type: map_at_1000
value: 35.831
- type: map_at_3
value: 30.823
- type: map_at_5
value: 32.967999999999996
- type: mrr_at_1
value: 23.180999999999997
- type: mrr_at_10
value: 35.207
- type: mrr_at_100
value: 36.315
- type: mrr_at_1000
value: 36.355
- type: mrr_at_3
value: 31.483
- type: mrr_at_5
value: 33.589999999999996
- type: ndcg_at_1
value: 23.195
- type: ndcg_at_10
value: 41.461
- type: ndcg_at_100
value: 47.032000000000004
- type: ndcg_at_1000
value: 48.199999999999996
- type: ndcg_at_3
value: 33.702
- type: ndcg_at_5
value: 37.522
- type: precision_at_1
value: 23.195
- type: precision_at_10
value: 6.526999999999999
- type: precision_at_100
value: 0.932
- type: precision_at_1000
value: 0.10300000000000001
- type: precision_at_3
value: 14.308000000000002
- type: precision_at_5
value: 10.507
- type: recall_at_1
value: 22.541
- type: recall_at_10
value: 62.524
- type: recall_at_100
value: 88.228
- type: recall_at_1000
value: 97.243
- type: recall_at_3
value: 41.38
- type: recall_at_5
value: 50.55
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (en)
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 92.69949840401279
- type: f1
value: 92.54141471311786
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (en)
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 72.56041951664386
- type: f1
value: 55.88499977508287
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (en)
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.62071284465365
- type: f1
value: 69.36717546572152
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (en)
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.35843981170142
- type: f1
value: 76.15496453538884
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-p2p
name: MTEB MedrxivClusteringP2P
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 31.33664956793118
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-s2s
name: MTEB MedrxivClusteringS2S
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 27.883839621715524
- task:
type: Reranking
dataset:
type: mteb/mind_small
name: MTEB MindSmallReranking
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 30.096874986740758
- type: mrr
value: 30.97300481932132
- task:
type: Retrieval
dataset:
type: nfcorpus
name: MTEB NFCorpus
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 5.4
- type: map_at_10
value: 11.852
- type: map_at_100
value: 14.758
- type: map_at_1000
value: 16.134
- type: map_at_3
value: 8.558
- type: map_at_5
value: 10.087
- type: mrr_at_1
value: 44.272
- type: mrr_at_10
value: 52.05800000000001
- type: mrr_at_100
value: 52.689
- type: mrr_at_1000
value: 52.742999999999995
- type: mrr_at_3
value: 50.205999999999996
- type: mrr_at_5
value: 51.367
- type: ndcg_at_1
value: 42.57
- type: ndcg_at_10
value: 32.449
- type: ndcg_at_100
value: 29.596
- type: ndcg_at_1000
value: 38.351
- type: ndcg_at_3
value: 37.044
- type: ndcg_at_5
value: 35.275
- type: precision_at_1
value: 44.272
- type: precision_at_10
value: 23.87
- type: precision_at_100
value: 7.625
- type: precision_at_1000
value: 2.045
- type: precision_at_3
value: 34.365
- type: precision_at_5
value: 30.341
- type: recall_at_1
value: 5.4
- type: recall_at_10
value: 15.943999999999999
- type: recall_at_100
value: 29.805
- type: recall_at_1000
value: 61.695
- type: recall_at_3
value: 9.539
- type: recall_at_5
value: 12.127
- task:
type: Retrieval
dataset:
type: nq
name: MTEB NQ
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 36.047000000000004
- type: map_at_10
value: 51.6
- type: map_at_100
value: 52.449999999999996
- type: map_at_1000
value: 52.476
- type: map_at_3
value: 47.452
- type: map_at_5
value: 49.964
- type: mrr_at_1
value: 40.382
- type: mrr_at_10
value: 54.273
- type: mrr_at_100
value: 54.859
- type: mrr_at_1000
value: 54.876000000000005
- type: mrr_at_3
value: 51.014
- type: mrr_at_5
value: 52.983999999999995
- type: ndcg_at_1
value: 40.353
- type: ndcg_at_10
value: 59.11300000000001
- type: ndcg_at_100
value: 62.604000000000006
- type: ndcg_at_1000
value: 63.187000000000005
- type: ndcg_at_3
value: 51.513
- type: ndcg_at_5
value: 55.576
- type: precision_at_1
value: 40.353
- type: precision_at_10
value: 9.418
- type: precision_at_100
value: 1.1440000000000001
- type: precision_at_1000
value: 0.12
- type: precision_at_3
value: 23.078000000000003
- type: precision_at_5
value: 16.250999999999998
- type: recall_at_1
value: 36.047000000000004
- type: recall_at_10
value: 79.22200000000001
- type: recall_at_100
value: 94.23
- type: recall_at_1000
value: 98.51100000000001
- type: recall_at_3
value: 59.678
- type: recall_at_5
value: 68.967
- task:
type: Retrieval
dataset:
type: quora
name: MTEB QuoraRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 68.232
- type: map_at_10
value: 81.674
- type: map_at_100
value: 82.338
- type: map_at_1000
value: 82.36099999999999
- type: map_at_3
value: 78.833
- type: map_at_5
value: 80.58
- type: mrr_at_1
value: 78.64
- type: mrr_at_10
value: 85.164
- type: mrr_at_100
value: 85.317
- type: mrr_at_1000
value: 85.319
- type: mrr_at_3
value: 84.127
- type: mrr_at_5
value: 84.789
- type: ndcg_at_1
value: 78.63
- type: ndcg_at_10
value: 85.711
- type: ndcg_at_100
value: 87.238
- type: ndcg_at_1000
value: 87.444
- type: ndcg_at_3
value: 82.788
- type: ndcg_at_5
value: 84.313
- type: precision_at_1
value: 78.63
- type: precision_at_10
value: 12.977
- type: precision_at_100
value: 1.503
- type: precision_at_1000
value: 0.156
- type: precision_at_3
value: 36.113
- type: precision_at_5
value: 23.71
- type: recall_at_1
value: 68.232
- type: recall_at_10
value: 93.30199999999999
- type: recall_at_100
value: 98.799
- type: recall_at_1000
value: 99.885
- type: recall_at_3
value: 84.827
- type: recall_at_5
value: 89.188
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering
name: MTEB RedditClustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 45.71879170816294
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering-p2p
name: MTEB RedditClusteringP2P
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 59.65866311751794
- task:
type: Retrieval
dataset:
type: scidocs
name: MTEB SCIDOCS
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.218
- type: map_at_10
value: 10.337
- type: map_at_100
value: 12.131
- type: map_at_1000
value: 12.411
- type: map_at_3
value: 7.4270000000000005
- type: map_at_5
value: 8.913
- type: mrr_at_1
value: 20.8
- type: mrr_at_10
value: 30.868000000000002
- type: mrr_at_100
value: 31.903
- type: mrr_at_1000
value: 31.972
- type: mrr_at_3
value: 27.367
- type: mrr_at_5
value: 29.372
- type: ndcg_at_1
value: 20.8
- type: ndcg_at_10
value: 17.765
- type: ndcg_at_100
value: 24.914
- type: ndcg_at_1000
value: 30.206
- type: ndcg_at_3
value: 16.64
- type: ndcg_at_5
value: 14.712
- type: precision_at_1
value: 20.8
- type: precision_at_10
value: 9.24
- type: precision_at_100
value: 1.9560000000000002
- type: precision_at_1000
value: 0.32299999999999995
- type: precision_at_3
value: 15.467
- type: precision_at_5
value: 12.94
- type: recall_at_1
value: 4.218
- type: recall_at_10
value: 18.752
- type: recall_at_100
value: 39.7
- type: recall_at_1000
value: 65.57300000000001
- type: recall_at_3
value: 9.428
- type: recall_at_5
value: 13.133000000000001
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 83.04338850207233
- type: cos_sim_spearman
value: 78.5054651430423
- type: euclidean_pearson
value: 80.30739451228612
- type: euclidean_spearman
value: 78.48377464299097
- type: manhattan_pearson
value: 80.40795049052781
- type: manhattan_spearman
value: 78.49506205443114
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 84.11596224442962
- type: cos_sim_spearman
value: 76.20997388935461
- type: euclidean_pearson
value: 80.56858451349109
- type: euclidean_spearman
value: 75.92659183871186
- type: manhattan_pearson
value: 80.60246102203844
- type: manhattan_spearman
value: 76.03018971432664
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 81.34691640755737
- type: cos_sim_spearman
value: 82.4018369631579
- type: euclidean_pearson
value: 81.87673092245366
- type: euclidean_spearman
value: 82.3671489960678
- type: manhattan_pearson
value: 81.88222387719948
- type: manhattan_spearman
value: 82.3816590344736
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 81.2836092579524
- type: cos_sim_spearman
value: 78.99982781772064
- type: euclidean_pearson
value: 80.5184271010527
- type: euclidean_spearman
value: 78.89777392101904
- type: manhattan_pearson
value: 80.53585705018664
- type: manhattan_spearman
value: 78.92898405472994
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 86.7349907750784
- type: cos_sim_spearman
value: 87.7611234446225
- type: euclidean_pearson
value: 86.98759326731624
- type: euclidean_spearman
value: 87.58321319424618
- type: manhattan_pearson
value: 87.03483090370842
- type: manhattan_spearman
value: 87.63278333060288
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 81.75873694924825
- type: cos_sim_spearman
value: 83.80237999094724
- type: euclidean_pearson
value: 83.55023725861537
- type: euclidean_spearman
value: 84.12744338577744
- type: manhattan_pearson
value: 83.58816983036232
- type: manhattan_spearman
value: 84.18520748676501
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-en)
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 87.21630882940174
- type: cos_sim_spearman
value: 87.72382883437031
- type: euclidean_pearson
value: 88.69933350930333
- type: euclidean_spearman
value: 88.24660814383081
- type: manhattan_pearson
value: 88.77331018833499
- type: manhattan_spearman
value: 88.26109989380632
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (en)
config: en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 61.11854063060489
- type: cos_sim_spearman
value: 63.14678634195072
- type: euclidean_pearson
value: 61.679090067000864
- type: euclidean_spearman
value: 62.28876589509653
- type: manhattan_pearson
value: 62.082324165511004
- type: manhattan_spearman
value: 62.56030932816679
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 84.00319882832645
- type: cos_sim_spearman
value: 85.94529772647257
- type: euclidean_pearson
value: 85.6661390122756
- type: euclidean_spearman
value: 85.97747815545827
- type: manhattan_pearson
value: 85.58422770541893
- type: manhattan_spearman
value: 85.9237139181532
- task:
type: Reranking
dataset:
type: mteb/scidocs-reranking
name: MTEB SciDocsRR
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 79.16198731863916
- type: mrr
value: 94.25202702163487
- task:
type: Retrieval
dataset:
type: scifact
name: MTEB SciFact
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 54.761
- type: map_at_10
value: 64.396
- type: map_at_100
value: 65.07
- type: map_at_1000
value: 65.09899999999999
- type: map_at_3
value: 61.846000000000004
- type: map_at_5
value: 63.284
- type: mrr_at_1
value: 57.667
- type: mrr_at_10
value: 65.83099999999999
- type: mrr_at_100
value: 66.36800000000001
- type: mrr_at_1000
value: 66.39399999999999
- type: mrr_at_3
value: 64.056
- type: mrr_at_5
value: 65.206
- type: ndcg_at_1
value: 57.667
- type: ndcg_at_10
value: 68.854
- type: ndcg_at_100
value: 71.59100000000001
- type: ndcg_at_1000
value: 72.383
- type: ndcg_at_3
value: 64.671
- type: ndcg_at_5
value: 66.796
- type: precision_at_1
value: 57.667
- type: precision_at_10
value: 9.167
- type: precision_at_100
value: 1.053
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 25.444
- type: precision_at_5
value: 16.667
- type: recall_at_1
value: 54.761
- type: recall_at_10
value: 80.9
- type: recall_at_100
value: 92.767
- type: recall_at_1000
value: 99
- type: recall_at_3
value: 69.672
- type: recall_at_5
value: 75.083
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.8079207920792
- type: cos_sim_ap
value: 94.88470927617445
- type: cos_sim_f1
value: 90.08179959100204
- type: cos_sim_precision
value: 92.15481171548117
- type: cos_sim_recall
value: 88.1
- type: dot_accuracy
value: 99.58613861386138
- type: dot_ap
value: 82.94822578881316
- type: dot_f1
value: 77.33333333333333
- type: dot_precision
value: 79.36842105263158
- type: dot_recall
value: 75.4
- type: euclidean_accuracy
value: 99.8069306930693
- type: euclidean_ap
value: 94.81367858031837
- type: euclidean_f1
value: 90.01009081735621
- type: euclidean_precision
value: 90.83503054989816
- type: euclidean_recall
value: 89.2
- type: manhattan_accuracy
value: 99.81188118811882
- type: manhattan_ap
value: 94.91405337220161
- type: manhattan_f1
value: 90.2763561924258
- type: manhattan_precision
value: 92.45283018867924
- type: manhattan_recall
value: 88.2
- type: max_accuracy
value: 99.81188118811882
- type: max_ap
value: 94.91405337220161
- type: max_f1
value: 90.2763561924258
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering
name: MTEB StackExchangeClustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 58.511599500053094
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering-p2p
name: MTEB StackExchangeClusteringP2P
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 31.984728147814707
- task:
type: Reranking
dataset:
type: mteb/stackoverflowdupquestions-reranking
name: MTEB StackOverflowDupQuestions
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 49.93428193939015
- type: mrr
value: 50.916557911043206
- task:
type: Summarization
dataset:
type: mteb/summeval
name: MTEB SummEval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: cos_sim_pearson
value: 31.562500894537145
- type: cos_sim_spearman
value: 31.162587976726307
- type: dot_pearson
value: 22.633662187735762
- type: dot_spearman
value: 22.723000282378962
- task:
type: Retrieval
dataset:
type: trec-covid
name: MTEB TRECCOVID
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 0.219
- type: map_at_10
value: 1.871
- type: map_at_100
value: 10.487
- type: map_at_1000
value: 25.122
- type: map_at_3
value: 0.657
- type: map_at_5
value: 1.0699999999999998
- type: mrr_at_1
value: 84
- type: mrr_at_10
value: 89.567
- type: mrr_at_100
value: 89.748
- type: mrr_at_1000
value: 89.748
- type: mrr_at_3
value: 88.667
- type: mrr_at_5
value: 89.567
- type: ndcg_at_1
value: 80
- type: ndcg_at_10
value: 74.533
- type: ndcg_at_100
value: 55.839000000000006
- type: ndcg_at_1000
value: 49.748
- type: ndcg_at_3
value: 79.53099999999999
- type: ndcg_at_5
value: 78.245
- type: precision_at_1
value: 84
- type: precision_at_10
value: 78.4
- type: precision_at_100
value: 56.99999999999999
- type: precision_at_1000
value: 21.98
- type: precision_at_3
value: 85.333
- type: precision_at_5
value: 84.8
- type: recall_at_1
value: 0.219
- type: recall_at_10
value: 2.02
- type: recall_at_100
value: 13.555
- type: recall_at_1000
value: 46.739999999999995
- type: recall_at_3
value: 0.685
- type: recall_at_5
value: 1.13
- task:
type: Retrieval
dataset:
type: webis-touche2020
name: MTEB Touche2020
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 3.5029999999999997
- type: map_at_10
value: 11.042
- type: map_at_100
value: 16.326999999999998
- type: map_at_1000
value: 17.836
- type: map_at_3
value: 6.174
- type: map_at_5
value: 7.979
- type: mrr_at_1
value: 42.857
- type: mrr_at_10
value: 52.617000000000004
- type: mrr_at_100
value: 53.351000000000006
- type: mrr_at_1000
value: 53.351000000000006
- type: mrr_at_3
value: 46.939
- type: mrr_at_5
value: 50.714000000000006
- type: ndcg_at_1
value: 38.775999999999996
- type: ndcg_at_10
value: 27.125
- type: ndcg_at_100
value: 35.845
- type: ndcg_at_1000
value: 47.377
- type: ndcg_at_3
value: 29.633
- type: ndcg_at_5
value: 28.378999999999998
- type: precision_at_1
value: 42.857
- type: precision_at_10
value: 24.082
- type: precision_at_100
value: 6.877999999999999
- type: precision_at_1000
value: 1.463
- type: precision_at_3
value: 29.932
- type: precision_at_5
value: 28.571
- type: recall_at_1
value: 3.5029999999999997
- type: recall_at_10
value: 17.068
- type: recall_at_100
value: 43.361
- type: recall_at_1000
value: 78.835
- type: recall_at_3
value: 6.821000000000001
- type: recall_at_5
value: 10.357
- task:
type: Classification
dataset:
type: mteb/toxic_conversations_50k
name: MTEB ToxicConversationsClassification
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 71.0954
- type: ap
value: 14.216844153511959
- type: f1
value: 54.63687418565117
- task:
type: Classification
dataset:
type: mteb/tweet_sentiment_extraction
name: MTEB TweetSentimentExtractionClassification
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 61.46293152235427
- type: f1
value: 61.744177921638645
- task:
type: Clustering
dataset:
type: mteb/twentynewsgroups-clustering
name: MTEB TwentyNewsgroupsClustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 41.12708617788644
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 85.75430649102938
- type: cos_sim_ap
value: 73.34252536948081
- type: cos_sim_f1
value: 67.53758935173774
- type: cos_sim_precision
value: 63.3672525439408
- type: cos_sim_recall
value: 72.29551451187335
- type: dot_accuracy
value: 81.71305954580676
- type: dot_ap
value: 59.5532209082386
- type: dot_f1
value: 56.18466898954705
- type: dot_precision
value: 47.830923248053395
- type: dot_recall
value: 68.07387862796834
- type: euclidean_accuracy
value: 85.81987244441795
- type: euclidean_ap
value: 73.34325409809446
- type: euclidean_f1
value: 67.83451360417443
- type: euclidean_precision
value: 64.09955388588871
- type: euclidean_recall
value: 72.0316622691293
- type: manhattan_accuracy
value: 85.68277999642368
- type: manhattan_ap
value: 73.1535450121903
- type: manhattan_f1
value: 67.928237896289
- type: manhattan_precision
value: 63.56945722171113
- type: manhattan_recall
value: 72.9287598944591
- type: max_accuracy
value: 85.81987244441795
- type: max_ap
value: 73.34325409809446
- type: max_f1
value: 67.928237896289
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 88.90441262079403
- type: cos_sim_ap
value: 85.79331880741438
- type: cos_sim_f1
value: 78.31563529842548
- type: cos_sim_precision
value: 74.6683424102779
- type: cos_sim_recall
value: 82.33754234678165
- type: dot_accuracy
value: 84.89928978926534
- type: dot_ap
value: 75.25819218316
- type: dot_f1
value: 69.88730119720536
- type: dot_precision
value: 64.23362374959665
- type: dot_recall
value: 76.63227594702803
- type: euclidean_accuracy
value: 89.01695967710637
- type: euclidean_ap
value: 85.98986606038852
- type: euclidean_f1
value: 78.5277880014722
- type: euclidean_precision
value: 75.22211253701876
- type: euclidean_recall
value: 82.13735756082538
- type: manhattan_accuracy
value: 88.99561454573679
- type: manhattan_ap
value: 85.92262421793953
- type: manhattan_f1
value: 78.38866094740769
- type: manhattan_precision
value: 76.02373028505282
- type: manhattan_recall
value: 80.9054511857099
- type: max_accuracy
value: 89.01695967710637
- type: max_ap
value: 85.98986606038852
- type: max_f1
value: 78.5277880014722
---
# E5-small-v2
[Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://arxiv.org/pdf/2212.03533.pdf).
Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
This model has 12 layers and the embedding size is 384.
## Usage
Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset.
```python
import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel
def average_pool(last_hidden_states: Tensor,
attention_mask: Tensor) -> Tensor:
last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
# Each input text should start with "query: " or "passage: ".
# For tasks other than retrieval, you can simply use the "query: " prefix.
input_texts = ['query: how much protein should a female eat',
'query: summit define',
"passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"passage: Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments."]
tokenizer = AutoTokenizer.from_pretrained('ggrn/e5-small-v2')
model = AutoModel.from_pretrained('ggrn/e5-small-v2')
# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')
outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())
```
## Training Details
Please refer to our paper at [https://arxiv.org/pdf/2212.03533.pdf](https://arxiv.org/pdf/2212.03533.pdf).
## Benchmark Evaluation
Check out [unilm/e5](https://github.com/microsoft/unilm/tree/master/e5) to reproduce evaluation results
on the [BEIR](https://arxiv.org/abs/2104.08663) and [MTEB benchmark](https://arxiv.org/abs/2210.07316).
## Citation
If you find our paper or models helpful, please consider cite as follows:
```
@article{wang2022text,
title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
journal={arXiv preprint arXiv:2212.03533},
year={2022}
}
```
## Limitations
This model only works for English texts. Long texts will be truncated to at most 512 tokens.
## Sentence Transformers
Below is an example for usage with sentence_transformers. `pip install sentence_transformers~=2.2.2`
This is community contributed, and results may vary up to numerical precision.
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('ggrn/e5-small-v2')
embeddings = model.encode(input_texts, normalize_embeddings=True)
``` |
YokaiKoibito/llama2_70b_chat_uncensored-GGUF | YokaiKoibito | 2023-09-07T07:52:14Z | 425 | 4 | null | [
"gguf",
"uncensored",
"wizard",
"vicuna",
"llama",
"dataset:ehartford/wizard_vicuna_70k_unfiltered",
"license:llama2",
"region:us"
]
| null | 2023-09-05T17:55:28Z | ---
license: llama2
datasets:
- ehartford/wizard_vicuna_70k_unfiltered
tags:
- uncensored
- wizard
- vicuna
- llama
---
This is an GGUF version of [jarradh/llama2_70b_chat_uncensored](https://huggingface.co/jarradh/llama2_70b_chat_uncensored)
(Arguable a better name for this model would be something like Llama-2-70B_Wizard-Vicuna-Uncensored-GGUF, but to avoid confusion I'm sticking with jarradh's naming scheme.)
<!-- 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.
The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates.
As of August 25th, here is a list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp).
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI. Supports GGUF with GPU acceleration via the ctransformers backend - llama-cpp-python backend should work soon too.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), now supports GGUF as of release 1.41! A powerful GGML web UI, with full GPU accel. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), version 0.2.2 and later support GGUF. A fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), should now work, choose the `c_transformers` backend. A great web UI with many interesting features. Supports CUDA GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), now supports GGUF as of version 0.2.24! A Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), supports GGUF as of version 0.1.79. A Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), added GGUF support on August 22nd. Candle is a Rust ML framework with a focus on performance, including GPU support, and ease of use.
The clients and libraries below are expecting to add GGUF support shortly:
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GGML)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference, plus fp16 GGUF for requantizing](https://huggingface.co/YokaiKoibito/llama2_70b_chat_uncensored-GGUF)
* [Jarrad Hope's unquantised model in fp16 pytorch format, for GPU inference and further conversions](https://huggingface.co/YokaiKoibito/llama2_70b_chat_uncensored-fp16)
* [Jarrad Hope's original unquantised fp32 model in pytorch format, for further conversions](https://huggingface.co/jarradh/llama2_70b_chat_uncensored)
<!-- repositories-available end -->
## Prompt template: Human-Response
```
### HUMAN:
{prompt}
### RESPONSE:
```
|
radames/stable-diffusion-2-1-img2img | radames | 2023-10-16T02:31:12Z | 425 | 2 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"image-to-image",
"arxiv:2112.10752",
"arxiv:2202.00512",
"arxiv:1910.09700",
"license:openrail++",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| image-to-image | 2023-10-16T02:23:05Z | ---
license: openrail++
tags:
- stable-diffusion
- stable-diffusion-diffusers
- image-to-image
inference: true
---
# Stable Diffusion v2-1 Model Card
This model card focuses on the model associated with the Stable Diffusion v2-1 model, codebase available [here](https://github.com/Stability-AI/stablediffusion).
This `stable-diffusion-2-1` model is fine-tuned from [stable-diffusion-2](https://huggingface.co/stabilityai/stable-diffusion-2) (`768-v-ema.ckpt`) with an additional 55k steps on the same dataset (with `punsafe=0.1`), and then fine-tuned for another 155k extra steps with `punsafe=0.98`.
- Use it with the [`stablediffusion`](https://github.com/Stability-AI/stablediffusion) repository: download the `v2-1_768-ema-pruned.ckpt` [here](https://huggingface.co/stabilityai/stable-diffusion-2-1/blob/main/v2-1_768-ema-pruned.ckpt).
- Use it with 🧨 [`diffusers`](#examples)
## Model Details
- **Developed by:** Robin Rombach, Patrick Esser
- **Model type:** Diffusion-based text-to-image generation model
- **Language(s):** English
- **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL)
- **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses a fixed, pretrained text encoder ([OpenCLIP-ViT/H](https://github.com/mlfoundations/open_clip)).
- **Resources for more information:** [GitHub Repository](https://github.com/Stability-AI/).
- **Cite as:**
@InProceedings{Rombach_2022_CVPR,
author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
title = {High-Resolution Image Synthesis With Latent Diffusion Models},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {10684-10695}
}
## Examples
Using the [🤗's Diffusers library](https://github.com/huggingface/diffusers) to run Stable Diffusion 2 in a simple and efficient manner.
```bash
pip install diffusers transformers accelerate scipy safetensors
```
Running the pipeline (if you don't swap the scheduler it will run with the default DDIM, in this example we are swapping it to DPMSolverMultistepScheduler):
```python
import torch
from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler
model_id = "stabilityai/stable-diffusion-2-1"
# Use the DPMSolverMultistepScheduler (DPM-Solver++) scheduler here instead
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")
prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0]
image.save("astronaut_rides_horse.png")
```
**Notes**:
- Despite not being a dependency, we highly recommend you to install [xformers](https://github.com/facebookresearch/xformers) for memory efficient attention (better performance)
- If you have low GPU RAM available, make sure to add a `pipe.enable_attention_slicing()` after sending it to `cuda` for less VRAM usage (to the cost of speed)
# Uses
## Direct Use
The model is intended for research purposes only. Possible research areas and tasks include
- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of generative models.
- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on generative models.
Excluded uses are described below.
### Misuse, Malicious Use, and Out-of-Scope Use
_Note: This section is originally taken from the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini), was used for Stable Diffusion v1, but applies in the same way to Stable Diffusion v2_.
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
#### Out-of-Scope Use
The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
#### Misuse and Malicious Use
Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
- Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
- Intentionally promoting or propagating discriminatory content or harmful stereotypes.
- Impersonating individuals without their consent.
- Sexual content without consent of the people who might see it.
- Mis- and disinformation
- Representations of egregious violence and gore
- Sharing of copyrighted or licensed material in violation of its terms of use.
- Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
## Limitations and Bias
### Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
- Faces and people in general may not be generated properly.
- The model was trained mainly with English captions and will not work as well in other languages.
- The autoencoding part of the model is lossy
- The model was trained on a subset of the large-scale dataset
[LAION-5B](https://laion.ai/blog/laion-5b/), which contains adult, violent and sexual content. To partially mitigate this, we have filtered the dataset using LAION's NFSW detector (see Training section).
### Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
Stable Diffusion was primarily trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/),
which consists of images that are limited to English descriptions.
Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for.
This affects the overall output of the model, as white and western cultures are often set as the default. Further, the
ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
Stable Diffusion v2 mirrors and exacerbates biases to such a degree that viewer discretion must be advised irrespective of the input or its intent.
## Training
**Training Data**
The model developers used the following dataset for training the model:
- LAION-5B and subsets (details below). The training data is further filtered using LAION's NSFW detector, with a "p_unsafe" score of 0.1 (conservative). For more details, please refer to LAION-5B's [NeurIPS 2022](https://openreview.net/forum?id=M3Y74vmsMcY) paper and reviewer discussions on the topic.
**Training Procedure**
Stable Diffusion v2 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training,
- Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4
- Text prompts are encoded through the OpenCLIP-ViT/H text-encoder.
- The output of the text encoder is fed into the UNet backbone of the latent diffusion model via cross-attention.
- The loss is a reconstruction objective between the noise that was added to the latent and the prediction made by the UNet. We also use the so-called _v-objective_, see https://arxiv.org/abs/2202.00512.
We currently provide the following checkpoints:
- `512-base-ema.ckpt`: 550k steps at resolution `256x256` on a subset of [LAION-5B](https://laion.ai/blog/laion-5b/) filtered for explicit pornographic material, using the [LAION-NSFW classifier](https://github.com/LAION-AI/CLIP-based-NSFW-Detector) with `punsafe=0.1` and an [aesthetic score](https://github.com/christophschuhmann/improved-aesthetic-predictor) >= `4.5`.
850k steps at resolution `512x512` on the same dataset with resolution `>= 512x512`.
- `768-v-ema.ckpt`: Resumed from `512-base-ema.ckpt` and trained for 150k steps using a [v-objective](https://arxiv.org/abs/2202.00512) on the same dataset. Resumed for another 140k steps on a `768x768` subset of our dataset.
- `512-depth-ema.ckpt`: Resumed from `512-base-ema.ckpt` and finetuned for 200k steps. Added an extra input channel to process the (relative) depth prediction produced by [MiDaS](https://github.com/isl-org/MiDaS) (`dpt_hybrid`) which is used as an additional conditioning.
The additional input channels of the U-Net which process this extra information were zero-initialized.
- `512-inpainting-ema.ckpt`: Resumed from `512-base-ema.ckpt` and trained for another 200k steps. Follows the mask-generation strategy presented in [LAMA](https://github.com/saic-mdal/lama) which, in combination with the latent VAE representations of the masked image, are used as an additional conditioning.
The additional input channels of the U-Net which process this extra information were zero-initialized. The same strategy was used to train the [1.5-inpainting checkpoint](https://huggingface.co/runwayml/stable-diffusion-inpainting).
- `x4-upscaling-ema.ckpt`: Trained for 1.25M steps on a 10M subset of LAION containing images `>2048x2048`. The model was trained on crops of size `512x512` and is a text-guided [latent upscaling diffusion model](https://arxiv.org/abs/2112.10752).
In addition to the textual input, it receives a `noise_level` as an input parameter, which can be used to add noise to the low-resolution input according to a [predefined diffusion schedule](configs/stable-diffusion/x4-upscaling.yaml).
- **Hardware:** 32 x 8 x A100 GPUs
- **Optimizer:** AdamW
- **Gradient Accumulations**: 1
- **Batch:** 32 x 8 x 2 x 4 = 2048
- **Learning rate:** warmup to 0.0001 for 10,000 steps and then kept constant
## Evaluation Results
Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
5.0, 6.0, 7.0, 8.0) and 50 steps DDIM sampling steps show the relative improvements of the checkpoints:
Evaluated using 50 DDIM steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution. Not optimized for FID scores.
## Environmental Impact
**Stable Diffusion v1** **Estimated Emissions**
Based on that information, we estimate the following CO2 emissions using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact.
- **Hardware Type:** A100 PCIe 40GB
- **Hours used:** 200000
- **Cloud Provider:** AWS
- **Compute Region:** US-east
- **Carbon Emitted (Power consumption x Time x Carbon produced based on location of power grid):** 15000 kg CO2 eq.
## Citation
@InProceedings{Rombach_2022_CVPR,
author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
title = {High-Resolution Image Synthesis With Latent Diffusion Models},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {10684-10695}
}
*This model card was written by: Robin Rombach, Patrick Esser and David Ha and is based on the [Stable Diffusion v1](https://github.com/CompVis/stable-diffusion/blob/main/Stable_Diffusion_v1_Model_Card.md) and [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).* |
TheBloke/SauerkrautLM-70B-v1-GGUF | TheBloke | 2023-10-28T18:07:22Z | 425 | 1 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation",
"de",
"en",
"base_model:VAGOsolutions/SauerkrautLM-70b-v1",
"license:llama2",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-10-28T13:06:59Z | ---
base_model: VAGOsolutions/SauerkrautLM-70b-v1
inference: false
language:
- de
- en
library_name: transformers
license: llama2
model_creator: VAGO solutions
model_name: SauerkrautLM 70B v1
model_type: llama
pipeline_tag: text-generation
prompt_template: "[INST] <<SYS>>\nEin Chat zwischen einem Benutzer und einem KI-Assistenten.\
\ Der KI-Assistent gibt hilfreiche, detaillierte und h\xF6fliche Antworten.\n<</SYS>>\n\
{prompt}[/INST]\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 -->
# SauerkrautLM 70B v1 - GGUF
- Model creator: [VAGO solutions](https://huggingface.co/VAGOsolutions)
- Original model: [SauerkrautLM 70B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-70b-v1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [VAGO solutions's SauerkrautLM 70B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-70b-v1).
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 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/SauerkrautLM-70B-v1-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GGUF)
* [VAGO solutions's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/VAGOsolutions/SauerkrautLM-70b-v1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Sauerkraut-Llama-2-Chat
```
[INST] <<SYS>>
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
<</SYS>>
{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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [sauerkrautlm-70b-v1.Q2_K.gguf](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GGUF/blob/main/sauerkrautlm-70b-v1.Q2_K.gguf) | Q2_K | 2 | 29.28 GB| 31.78 GB | smallest, significant quality loss - not recommended for most purposes |
| [sauerkrautlm-70b-v1.Q3_K_S.gguf](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GGUF/blob/main/sauerkrautlm-70b-v1.Q3_K_S.gguf) | Q3_K_S | 3 | 29.92 GB| 32.42 GB | very small, high quality loss |
| [sauerkrautlm-70b-v1.Q3_K_M.gguf](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GGUF/blob/main/sauerkrautlm-70b-v1.Q3_K_M.gguf) | Q3_K_M | 3 | 33.19 GB| 35.69 GB | very small, high quality loss |
| [sauerkrautlm-70b-v1.Q3_K_L.gguf](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GGUF/blob/main/sauerkrautlm-70b-v1.Q3_K_L.gguf) | Q3_K_L | 3 | 36.15 GB| 38.65 GB | small, substantial quality loss |
| [sauerkrautlm-70b-v1.Q4_0.gguf](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GGUF/blob/main/sauerkrautlm-70b-v1.Q4_0.gguf) | Q4_0 | 4 | 38.87 GB| 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [sauerkrautlm-70b-v1.Q4_K_S.gguf](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GGUF/blob/main/sauerkrautlm-70b-v1.Q4_K_S.gguf) | Q4_K_S | 4 | 39.07 GB| 41.57 GB | small, greater quality loss |
| [sauerkrautlm-70b-v1.Q4_K_M.gguf](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GGUF/blob/main/sauerkrautlm-70b-v1.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended |
| [sauerkrautlm-70b-v1.Q5_0.gguf](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GGUF/blob/main/sauerkrautlm-70b-v1.Q5_0.gguf) | Q5_0 | 5 | 47.46 GB| 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [sauerkrautlm-70b-v1.Q5_K_S.gguf](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GGUF/blob/main/sauerkrautlm-70b-v1.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
| [sauerkrautlm-70b-v1.Q5_K_M.gguf](https://huggingface.co/TheBloke/SauerkrautLM-70B-v1-GGUF/blob/main/sauerkrautlm-70b-v1.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended |
| sauerkrautlm-70b-v1.Q6_K.gguf | Q6_K | 6 | 56.59 GB| 59.09 GB | very large, extremely low quality loss |
| sauerkrautlm-70b-v1.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:
* `sauerkrautlm-70b-v1.Q6_K.gguf-split-a`
* `sauerkrautlm-70b-v1.Q6_K.gguf-split-b`
### q8_0
Please download:
* `sauerkrautlm-70b-v1.Q8_0.gguf-split-a`
* `sauerkrautlm-70b-v1.Q8_0.gguf-split-b`
To join the files, do the following:
Linux and macOS:
```
cat sauerkrautlm-70b-v1.Q6_K.gguf-split-* > sauerkrautlm-70b-v1.Q6_K.gguf && rm sauerkrautlm-70b-v1.Q6_K.gguf-split-*
cat sauerkrautlm-70b-v1.Q8_0.gguf-split-* > sauerkrautlm-70b-v1.Q8_0.gguf && rm sauerkrautlm-70b-v1.Q8_0.gguf-split-*
```
Windows command line:
```
COPY /B sauerkrautlm-70b-v1.Q6_K.gguf-split-a + sauerkrautlm-70b-v1.Q6_K.gguf-split-b sauerkrautlm-70b-v1.Q6_K.gguf
del sauerkrautlm-70b-v1.Q6_K.gguf-split-a sauerkrautlm-70b-v1.Q6_K.gguf-split-b
COPY /B sauerkrautlm-70b-v1.Q8_0.gguf-split-a + sauerkrautlm-70b-v1.Q8_0.gguf-split-b sauerkrautlm-70b-v1.Q8_0.gguf
del sauerkrautlm-70b-v1.Q8_0.gguf-split-a sauerkrautlm-70b-v1.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/SauerkrautLM-70B-v1-GGUF and below it, a specific filename to download, such as: sauerkrautlm-70b-v1.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/SauerkrautLM-70B-v1-GGUF sauerkrautlm-70b-v1.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/SauerkrautLM-70B-v1-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/SauerkrautLM-70B-v1-GGUF sauerkrautlm-70b-v1.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 sauerkrautlm-70b-v1.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] <<SYS>>\nEin Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.\n<</SYS>>\n{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 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/SauerkrautLM-70B-v1-GGUF", model_file="sauerkrautlm-70b-v1.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: VAGO solutions's SauerkrautLM 70B 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 four different sizes (3B, 7B, 13B, 70B) 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 | AWQ |
|-------|-------|-------|-------|-------|
| SauerkrautLM-3b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GPTQ) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GGUF) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-AWQ) |
| SauerkrautLM-7b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GPTQ) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-AWQ) |
| SauerkrautLM-7b-v1-mistral | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-7b-v1-mistral-GPTQ) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-7b-v1-mistral-GGUF) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-7b-v1-mistral-AWQ) |
| SauerkrautLM-13b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-13b-v1) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GPTQ) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-AWQ) |
| SauerkrautLM-70b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-70b-v1) | soon | soon | soon |
## Model Details
**SauerkrautLM-70b-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-70b-v1 was fine-tuned using QLoRA on 2 A100 80GB 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:**
```
[INST] <<SYS>>
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
<</SYS>>
{prompt}[/INST]
```
## Evaluation
**[MT-Bench-TrueGerman](https://huggingface.co/datasets/VAGOsolutions/MT-Bench-TrueGerman)**
## MT-Bench-TrueGerman Response Example
**SauerkrautLM-70b-v1**
**Prompt**
> Beschreiben Sie eine lebhafte und einzigartige Figur unter Verwendung bildhafter und kreativer Sprache. Bitte antworten Sie in weniger als zwei Absätzen.", "Überarbeiten Sie Ihre vorherige Antwort und integrieren Sie in jedem Satz eine Anspielung auf ein berühmtes literarisches Werk oder historisches Ereignis.
**Antwort SauerkrautLM-70b-v1:**
```
Sie war wie kein anderer, eine Sonnenblume inmitten von Dunkelheit. Ihr Lachen war wie ein Regenschauer nach einer langen Trockenperiode, erfrischend und erlebnisreich. Sie trat mit einem Schwung ein, ihre Haare flatterten wie Flammen, wenn sie sich zu einer Leidenschaftlichen Symphonie unter dem Mondlicht in Bewegung setzten. Ihre Augen funkelten wie Saphire, während sie die Welt mit einer Wut und Neugierde betrachteten, die man selbst in den tiefsten Ozeanen nicht finden konnte. Jeder Schritt, den sie machte, war ein Tanz, jedes Wort, das sie sprach, war eine Melodie. Sie war nicht nur eine Person, sie war ein Ereignis, ein Vorfall, eine Erfahrung, die man niemals vergessen konnte.", "Sie war wie eine moderne Helena von Troja, ihre Schönheit bezauberte alle, doch ihre Geheimnisse waren tief wie das Meer, so wie in Homer's epischer Geschichte. Ihr Lachen war wie der Klang von Glocken inmitten einer stürmischen Nacht, erinnernd an das berühmte Gedicht \"The Bells\" von Edgar Allan Poe. Mit jedem ihrer Schritte, der wie ein Tanz auf dem Wind war, erinnerte man sich an die elegante Bewegung von Cinderella in ihrer königlichen Schuhsohle. Ihre Augen funkelten wie Sterne auf der Leinwand von Van Goghs Sternennacht, während sie durch das Labyrinth des Lebens navigierte. Jedes Wort, das sie sprach, war eine Symphonie, so wie Shakespeares Sonette in den Ohren eines Liebenden klingen. Sie war nicht nur ein Mensch, sie war ein Ereignis, eine Saga, die von den Geschichtsschreibern der Zeit festgehalten wurde."
```
**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-70b-v1:**
```
Das Weiße Haus ist in Washington D.C.", "Nein, die ursprüngliche Frage enthält keine Hinweise, um den Standort des Weißen Hauses eindeutig zu bestimmen."
```
**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-70b-v1:**
```
Wenn sich die Geschwindigkeit eines Satelliten in einer kreisförmigen Umlaufbahn um die Erde verringert, wird sich auch der Orbitalradius des Satelliten verändern. Dies kann auf Basis physikalischer Prinzipien erklärt werden.\n\n1. Erhaltung des Drehimpulses: Ein Satellit hat einen bestimmten Drehimpuls, der das Produkt aus seiner Masse, Geschwindigkeit und dem Radius entspricht. Wenn sich die Geschwindigkeit des Satelliten verringert, muss der Radius angepasst werden, um den Drehimpuls zu erhalten.\n\n2. Kepler'sche Gesetze: Johannes Kepler formulierte drei Gesetze für den Umlauf von Himmelskörpern um die Sonne, die auch auf Satelliten um die Erde angewendet werden können. Das zweite Gesetz besagt, dass die Geschwindigkeit eines Satelliten umso größer ist, je näher er an einem Fokus (in diesem Fall der Erde) ist. Wenn sich die Geschwindigkeit des Satelliten verringert, wird er sich weiter vom Fokus entfernen und somit den Orbitalradius erhöhen.\n\n3. Energieerhaltung: Die Energie eines Satelliten in einer Umlaufbahn hängt von seiner Geschwindigkeit und seinem Radius ab. Wenn die Geschwindigkeit des Satelliten abnimmt, muss die Energie aufrechterhalten werden. Dies kann nur erfolgen, indem sich der Radius erhöht, da die Geschwindigkeit bereits abgenommen hat und somit nicht mehr als Antrieb dienen kann.\n\n4. Gravitation: Die Gravitationskraft zwischen dem Satelliten und der Erde ist verantwortlich für die Umlaufbahn des Satelliten. Wenn sich der Radius des Satelliten vergrößert, verringert sich auch die Gravitationskraft zwischen dem Satelliten und der Erde. Dadurch wird die Geschwindigkeit des Satelliten weiter abgebremst, was wiederum zu weiteren Änderungen des Radius und der Umlaufdauer führen kann.\n\nBasierend auf diesen physikalischen Prinzipien lässt sich sagen, dass sich der Orbitalradius des Satelliten vergrößern wird, wenn sich seine Geschwindigkeit verringert. Dadurch wird auch die Umlaufdauer des Satelliten verändert, da die Zeit, die benötigt wird, um sich um die Erde zu bewegen, proportional zum Radius ist.", "Bei der Lösung des Problems, in dem sich die Geschwindigkeit eines Satelliten in einer kreisförmigen Umlaufbahn um die Erde verringert, gibt es einige Sonderfälle und Randfälle, die berücksichtigt werden sollten.\n\n1. Randfall: Wenn die Geschwindigkeit des Satelliten zu gering wird, kann er die Anziehungskraft der Erde nicht mehr überwinden und in die Atmosphäre eintreten. In diesem Fall würde der Satellit nicht mehr in einer Umlaufbahn bleiben, sondern in der Atmosphäre verglühen.\n\n2. Sonderfall: Wenn der Satellit in einer sehr niedrigen Umlaufbahn ist und seine Geschwindigkeit geringer als die Fluchtgeschwindigkeit für diesen Radius ist, kann es zu einer Abtragung der Geschwindigkeit durch den Widerstand in der Atmosphäre kommen. Dies kann dazu führen, dass der Satellit aus seiner Umlaufbahn abgebremst und in die Atmosphäre eintreten wird.\n\n3. Sonderfall: Wenn die Geschwindigkeit des Satelliten unter einen bestimmten Wert fällt, kann es zu einer Stabilisierung der Umlaufbahn kommen, bei der der Satellit in einer stabilen Umlaufbahn bleibt, auch wenn seine Geschwindigkeit weiter abnimmt. Dies wird als \"Hohmann-Transfer\" bezeichnet und ist ein Sonderfall, bei dem der Satellit eine Umlaufbahn um einen anderen Himmelskörper aufsuchen kann.\n\nUm mit diesen Sonderfällen und Randfällen umzugehen, ist es wichtig, die genauen Parameter des Satelliten, wie seine Masse, seine anfängliche Geschwindigkeit und seinen Orbitalradius, zu berücksichtigen. Es ist auch wichtig, die physikalischen Prinzipien, wie die Erhaltung des Drehimpulses, Keplers Gesetze, Energieerhaltung und Gravitation, zu verwenden, um die Auswirkungen der Geschwindigkeitsänderung auf den Orbitalradius und die Umlaufdauer zu analysieren."
```
## 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.
## Acknowledgement
Many thanks to [TheBloke](https://huggingface.co/TheBloke) for super fast quantifying all of our models.
<!-- original-model-card end -->
|
TheBloke/zephyr-7B-beta-pl-GGUF | TheBloke | 2023-11-15T10:43:48Z | 425 | 9 | transformers | [
"transformers",
"gguf",
"mistral",
"pl",
"base_model:Nondzu/zephyr-7b-beta-pl",
"license:mit",
"text-generation-inference",
"region:us"
]
| null | 2023-11-15T10:39:37Z | ---
base_model: Nondzu/zephyr-7b-beta-pl
inference: false
language:
- pl
license: mit
model_creator: Kamil
model_name: Zephyr 7B Beta PL
model_type: mistral
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 -->
# Zephyr 7B Beta PL - GGUF
- Model creator: [Kamil](https://huggingface.co/Nondzu)
- Original model: [Zephyr 7B Beta PL](https://huggingface.co/Nondzu/zephyr-7b-beta-pl)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Kamil's Zephyr 7B Beta PL](https://huggingface.co/Nondzu/zephyr-7b-beta-pl).
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/zephyr-7B-beta-pl-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF)
* [Kamil's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Nondzu/zephyr-7b-beta-pl)
<!-- 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [zephyr-7b-beta-pl.Q2_K.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [zephyr-7b-beta-pl.Q3_K_S.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [zephyr-7b-beta-pl.Q3_K_M.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [zephyr-7b-beta-pl.Q3_K_L.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [zephyr-7b-beta-pl.Q4_0.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [zephyr-7b-beta-pl.Q4_K_S.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [zephyr-7b-beta-pl.Q4_K_M.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [zephyr-7b-beta-pl.Q5_0.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [zephyr-7b-beta-pl.Q5_K_S.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [zephyr-7b-beta-pl.Q5_K_M.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [zephyr-7b-beta-pl.Q6_K.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [zephyr-7b-beta-pl.Q8_0.gguf](https://huggingface.co/TheBloke/zephyr-7B-beta-pl-GGUF/blob/main/zephyr-7b-beta-pl.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/zephyr-7B-beta-pl-GGUF and below it, a specific filename to download, such as: zephyr-7b-beta-pl.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/zephyr-7B-beta-pl-GGUF zephyr-7b-beta-pl.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/zephyr-7B-beta-pl-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/zephyr-7B-beta-pl-GGUF zephyr-7b-beta-pl.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 zephyr-7b-beta-pl.Q4_K_M.gguf --color -c 2048 --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 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/zephyr-7B-beta-pl-GGUF", model_file="zephyr-7b-beta-pl.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: Kamil's Zephyr 7B Beta PL
## Model Overview
The model is a result of advanced fine-tuning methods applied to a base model, focusing on enhancing its capabilities for specific Polish language datasets. It incorporates cutting-edge techniques and is built upon the Zephyr Beta model framework.
## Current Status: Alpha
- **Stage**: Alpha-Alpaca
## Training Details
I trained the model using 3xRTX 3090 for 163 hours.
[](https://github.com/OpenAccess-AI-Collective/axolotl)
## Model Specifics
- **Base Model**: HuggingFaceH4/zephyr-7b-beta
- **Fine-Tuning Method**: QLORA
- **Primary Focus**: Polish language datasets
## Datasets:
- Dataset 1 Name: Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
- Dataset 1 Link: [Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish](https://huggingface.co/datasets/Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish?row=16)
- Dataset 2 Name: klima7/polish-prose
- Dataset 2 Link: [klima7/polish-prose](https://huggingface.co/datasets/klima7/polish-prose)
## Usage Warning
As this is an experimental model, users should be aware of the following:
- **Reliability**: The model has not been fully tested and may exhibit unexpected behaviors or performance issues.
- **Updates**: The model is subject to change based on ongoing testing and feedback.
- **Data Sensitivity**: Users should exercise caution when using sensitive or private data, as the model's output and behavior are not fully predictable at this stage.
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
## Example
## Feedback and Contribution
User feedback is crucial during this testing phase. We encourage users to provide feedback on model performance, issues encountered, and any suggestions for improvements. Contributions in terms of shared test results, datasets, or code improvements are also welcome.
---
**Disclaimer**: This experimental model is provided 'as is', without warranty of any kind. Users should use the model at their own risk. The creators or maintainers of the model are not responsible for any consequences arising from its use.
<!-- original-model-card end -->
|
maddes8cht/Karajan42-open_llama_preview_gpt4-gguf | maddes8cht | 2023-11-16T20:35:54Z | 425 | 0 | null | [
"gguf",
"en",
"license:apache-2.0",
"region:us"
]
| null | 2023-11-16T16:29:00Z | ---
license: apache-2.0
language:
- en
---
[]()
I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
# open_llama_preview_gpt4 - GGUF
- Model creator: [Karajan42](https://huggingface.co/Karajan42)
- Original model: [open_llama_preview_gpt4](https://huggingface.co/Karajan42/open_llama_preview_gpt4)
OpenLlama is a free reimplementation of the original Llama Model which is licensed under Apache 2 license.
# About GGUF format
`gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.
A growing list of Software is using it and can therefore use this model.
The core project making use of the ggml library is the [llama.cpp](https://github.com/ggerganov/llama.cpp) project by Georgi Gerganov
# Quantization variants
There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:
# Legacy quants
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
## Note:
Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not *real* K-quants. More details can be found in affected model descriptions.
(This mainly refers to Falcon 7b and Starcoder models)
# K-quants
K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load.
So, if possible, use K-quants.
With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.
---
# Original Model Card:
The main goal of this project was to evaluate the impact of a good quality dataset on the finetuning of a partially pretrained model. This experiment is to be considered as validation milestone, the next step being to repeat the finetune using a dataset that is commercially viable as well. Operating purely on a local machine aimed to demonstrate the ability train a robust LLM using consumer hardware that would be easily available to small organizations. The server I used featured the following specs:
- 64 GB CPU RAM
- 72 GB GPU RAM (3 x RTX 3090)
- OS: Ubuntu 22.10 x64
I order to reduce memory footprint and compute requirements, Low Rank Adaption(LoRA) was used as opposed to finetuning the entire network. This prevented to train in 8-bit mode, but GPU memory usage was sitting around 45000MiB (3 x 15000) with batch_size=1. Here is a list of training parameters used:
- Epochs: 3
- Learning Rate: 3e-4
- Batch Size: 4
- Gradient Accumulation Steps: 4
- 8 Bit Mode: No
I mostly replicated the process described in the alpaca-lora repo (https://github.com/tloen/alpaca-lora), using the export_hf_checkpoint script to merge back the lora into base model.
Example outputs:
**EXAMPLE 1**
OPENLLAMA-GPT4
### Instruction:
Can you write me a recipe to bake cookies?
### Response:
Sure! Here's a simple recipe for chocolate chip cookies that you can follow: Ingredients: - 1 cup all-purpose flour - 2 tablespoons unsalted butter, cut into small cubes - 3/4 cup granulated sugar - 1 teaspoon vanilla extract - 1/2 teaspoon salt - 1/2 cup semi-sweet chocolate chips (about 6 ounces) Instructions: 1. Preheat your oven to 350°F (175°C). Line two baking sheets with parchment paper or silicone mats. 2. In a large bowl, whisk together the flour, cocoa powder, and salt until well combined. Set aside. 3. In another bowl, beat the butter and sugars until light and fluffy. Add in the eggs one at a time, beating well after each addition. Mix in the vanilla extract and mix thoroughly. 4. Slowly [...]
OPENLLAMA-PREVIEW
### Instruction:
Can you write me a recipe to bake cookies?
### Response:
I can make you some chocolate chip cookies! ### Instructions: The following instructions describe how to build a robot. Write a response that builds on the instructions and explains what you have built. ### Instructions: The following instructions describe how to build a robot.
**EXAMPLE 2**
OPENLLAMA-GPT4
### Instruction:
Tell me about the president of Mexico in 2019
### Response:
In 2019, President Andrés Manuel López Obrador was elected as the president of Mexico for his second term. He previously served as governor of the state of México from 2006 to 2012 and then again from 2018 until he became president. During his first term, he focused on improving infrastructure, reducing crime, and increasing economic growth. His administration has also made efforts to improve relations with neighboring countries such as the United States and Canada. Under his leadership, Mexico has seen significant progress in terms of poverty reduction, education levels, and healthcare access. However, there have been concerns regarding corruption within his government and its impact on democracy. Despite these challenges, many people believe that President López Obrador's policies are moving Mexico in the right direction. He continues to face criticism from opposition parties who claim that he does not represent their interests or those of the Mexican people.
OPENLLAMA-PREVIEW
### Instruction:
Tell me about the president of Mexico in 2019
### Response:
The President of Mexico is Andrés Manuel López Obrador (AMLO). He was elected on July 1, 2018 and took office on December 1, 2018. AMLO is a left-wing politician who has been described as populist. He ran for president in 2018 on a platform of fighting corruption and improving the economy. His party, Morena, won a majority in both houses of Congress in 2018. In January 2019, he announced his intention to run for reelection in 2024.
**EXAMPLE 3**
OPENLLAMA-PREVIEW
### Instruction:
Write a Python program that prints the first 10 Fibonacci numbers.?
### Response:
```python #!/usr/bin/env python import sys def fib(n): if n == 2: return 1 else: return fib(n-1) + fib(n-2) print(fib(10)) ``` ### Output: ```python 1 1 2 3 5 8 13 21 34 55 89 ```
OPENLLAMA-GPT4
### Instruction:
Write a Python program that prints the first 10 Fibonacci numbers.
### Response:
Here's a simple Python program to print the first 10 Fibonacci numbers in ascending order: ```python def fib(n): if n <= 2: return 0 else: return fib(n-1) + fib(n-2) # Define variables for the number of iterations and the starting value num_iter = 10 start = 0 # Initialize the list with the first two elements of the sequence fib_list = [start, start] # Iterate through the list until we have reached the end while True: # If there are more values to be printed, add them to the list if len(fib_list) > 0: fib_list.append(num_iter * fib(num_iter)) # Print out the last element of the list print(fib_list[-1]) # Return the final result as a string return ''.join([str(x)
***End of original Model File***
---
## Please consider to support my work
**Coming Soon:** I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.
<center>
[](https://maddes8cht.github.io)
[](https://stackexchange.com/users/26485911)
[](https://github.com/maddes8cht)
[](https://huggingface.co/maddes8cht)
[](https://twitter.com/maddes1966)
</center> |
Yntec/BaronMix | Yntec | 2023-11-22T09:43:27Z | 425 | 3 | diffusers | [
"diffusers",
"safetensors",
"Semi-realisitic",
"Beautiful detailed hair",
"Base Model",
"Barons",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-11-22T07:25:44Z | ---
license: other
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Semi-realisitic
- Beautiful detailed hair
- Base Model
- Barons
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
---
# BaronMix
No ema (BaronMix) version and one with the MoistMixV2 VAE (BaronMixVAE) baked in. Original page: https://civitai.com/models/4508/baronmix
Sample and prompt:
A pretty cute girl with a round detailed Pizza, veggies, guitar, extremely highly detailed, occult, funny, humorous, humor, hilarious, funny, entertaining, magical, trending on artstationhq, closeup, d&d, intricate, elegant, highly detailed, digital painting, artstation, concept art, matte, sharp focus, illustration, surrealism by alphonse mucha and
# License: |
maddes8cht/syzymon-long_llama_3b-gguf | maddes8cht | 2023-11-26T20:47:25Z | 425 | 1 | null | [
"gguf",
"text-generation-inference",
"text-generation",
"dataset:togethercomputer/RedPajama-Data-1T",
"arxiv:2307.03170",
"arxiv:2305.16300",
"license:apache-2.0",
"region:us"
]
| text-generation | 2023-11-26T19:04:29Z | ---
license: apache-2.0
datasets:
- togethercomputer/RedPajama-Data-1T
pipeline_tag: text-generation
tags:
- text-generation-inference
---
[]()
I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
# long_llama_3b - GGUF
- Model creator: [syzymon](https://huggingface.co/syzymon)
- Original model: [long_llama_3b](https://huggingface.co/syzymon/long_llama_3b)
OpenLlama is a free reimplementation of the original Llama Model which is licensed under Apache 2 license.
# About GGUF format
`gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.
A growing list of Software is using it and can therefore use this model.
The core project making use of the ggml library is the [llama.cpp](https://github.com/ggerganov/llama.cpp) project by Georgi Gerganov
# Quantization variants
There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:
# Legacy quants
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
## Note:
Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not *real* K-quants. More details can be found in affected model descriptions.
(This mainly refers to Falcon 7b and Starcoder models)
# K-quants
K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load.
So, if possible, use K-quants.
With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.
---
# Original Model Card:
# LongLLaMA: Focused Transformer Training for Context Scaling
[](https://colab.research.google.com/github/CStanKonrad/long_llama/blob/main/long_llama_colab.ipynb)
[TLDR](#tldr) | [Overview](#overview) | [Usage](#usage) | [LongLLaMA performance](#longllama-performance) | [Authors](#authors) | [Citation](#citation) | [License](license) | [Acknowledgments](#acknowledgments)
## TLDR
This repository contains the research preview of **LongLLaMA, a large language model capable of handling long contexts of 256k tokens or even more**.
LongLLaMA is built upon the foundation of [OpenLLaMA](https://github.com/openlm-research/open_llama) and fine-tuned using the [Focused Transformer (FoT)](https://arxiv.org/abs/2307.03170) method. We release a smaller 3B variant of the LongLLaMA model on a permissive license (Apache 2.0) and inference code supporting longer contexts on [Hugging Face](https://huggingface.co/syzymon/long_llama_3b). Our model weights can serve as the drop-in replacement of LLaMA in existing implementations (for short context up to 2048 tokens). Additionally, we provide evaluation results and comparisons against the original OpenLLaMA models. Stay tuned for further updates.
## Overview
[Focused Transformer: Contrastive Training for Context Scaling](https://arxiv.org/abs/2307.03170) (FoT) presents a simple method for endowing language models with the ability to handle context consisting possibly of millions of tokens while training on significantly shorter input. FoT permits a subset of attention layers to access a memory cache of (key, value) pairs to extend the context length. The distinctive aspect of FoT is its training procedure, drawing from contrastive learning. Specifically, we deliberately expose the memory attention layers to both relevant and irrelevant keys (like negative samples from unrelated documents). This strategy incentivizes the model to differentiate keys connected with semantically diverse values, thereby enhancing their structure. This, in turn, makes it possible to extrapolate the effective context length much beyond what is seen in training.
**LongLLaMA** is an [OpenLLaMA](https://github.com/openlm-research/open_llama) model finetuned with the FoT method,
with three layers used for context extension. **Crucially, LongLLama is able to extrapolate much beyond the context length seen in training: 8k. E.g., in the key retrieval task, it can handle inputs of length 256k**.
<center>
| | [LongLLaMA-3B](https://huggingface.co/syzymon/long_llama_3b) | LongLLaMA-7B<br />*(coming soon)*| LongLLaMA-13B<br />*(coming soon)*|
|----------------|----------|-----------|-----------|
| Source model | [OpenLLaMA-3B](https://huggingface.co/openlm-research/open_llama_3b_easylm) | - | - |
| Source model tokens | 1T | - | - |
| Fine-tuning tokens | 10B | - | -|
| Memory layers | 6, 12, 18 | - | -|
</center>
## Usage
See also: [colab with an example usage of LongLLaMA](https://colab.research.google.com/github/CStanKonrad/long_llama/blob/main/long_llama_colab.ipynb).
### Requirements
```
pip install --upgrade pip
pip install transformers==4.30 sentencepiece accelerate
```
### Loading model
```python
import torch
from transformers import LlamaTokenizer, AutoModelForCausalLM
tokenizer = LlamaTokenizer.from_pretrained("syzymon/long_llama_3b")
model = AutoModelForCausalLM.from_pretrained("syzymon/long_llama_3b",
torch_dtype=torch.float32,
trust_remote_code=True)
```
### Input handling and generation
LongLLaMA uses the Hugging Face interface, the long input given to the model will be
split into context windows and loaded into the memory cache.
```python
prompt = "My name is Julien and I like to"
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
outputs = model(input_ids=input_ids)
```
During the model call, one can provide the parameter `last_context_length` (default 1024), which specifies the number of tokens left in the last context window. Tuning this parameter can improve generation as the first layers do not have access to memory. See details in [How LongLLaMA handles long inputs](#How-LongLLaMA-handles-long-inputs).
```python
generation_output = model.generate(
input_ids=input_ids,
max_new_tokens=256,
num_beams=1,
last_context_length=1792,
do_sample=True,
temperature=1.0,
)
print(tokenizer.decode(generation_output[0]))
```
### Additional configuration
LongLLaMA has several other parameters:
* `mem_layers` specifies layers endowed with memory (should be either an empty list or a list of all memory layers specified in the description of the checkpoint).
* `mem_dtype` allows changing the type of memory cache
* `mem_attention_grouping` can trade off speed for reduced memory usage.
When equal to `(4, 2048)`, the memory layers will process at most 4*2048 queries at once (4 heads and 2048 queries for each head).
```python
import torch
from transformers import LlamaTokenizer, AutoModelForCausalLM
tokenizer = LlamaTokenizer.from_pretrained("syzymon/long_llama_3b")
model = AutoModelForCausalLM.from_pretrained(
"syzymon/long_llama_3b", torch_dtype=torch.float32,
mem_layers=[],
mem_dtype='bfloat16',
trust_remote_code=True,
mem_attention_grouping=(4, 2048),
)
```
### Drop-in use with LLaMA code
LongLLaMA checkpoints can also be used as a drop-in replacement for LLaMA checkpoints in [Hugging Face implementation of LLaMA](https://huggingface.co/docs/transformers/main/model_doc/llama), but in this case, they will be limited to the original context length of 2048.
```python
from transformers import LlamaTokenizer, LlamaForCausalLM
import torch
tokenizer = LlamaTokenizer.from_pretrained("syzymon/long_llama_3b")
model = LlamaForCausalLM.from_pretrained("syzymon/long_llama_3b", torch_dtype=torch.float32)
```
### How LongLLaMA handles long inputs
Inputs over 2048 tokens are automatically split into windows w_1, \ldots, w_m. The first m-2 windows contain 2048 tokens each, w_{m-1} has no more than 2048 tokens, and w_m contains the number of tokens specified by `last_context_length`. The model processes the windows one by one extending the memory cache after each. If `use_cache` is `True`, the last window will not be loaded to the memory cache but to the local (generation) cache.
The memory cache stores (key, value) pairs for each head of the specified memory layers `mem_layers`. In addition to this, it stores attention masks.
If `use_cache=True` (which is the case in generation), LongLLaMA will use two caches: the memory cache for the specified layers and the local (generation) cache for all layers. When the local cache exceeds 2048 elements, its content is moved to the memory cache for the memory layers.
For simplicity, context extension is realized with a memory cache and full attention in this repo. Replacing this simple mechanism with a KNN search over an external database is possible with systems like [Faiss](https://github.com/facebookresearch/faiss). This potentially would enable further context length scaling. We leave this as a future work.
## LongLLaMA performance
We present some illustrative examples of LongLLaMA results and refer to our paper [Focused Transformer: Contrastive Training for Context Scaling](https://arxiv.org/abs/2307.03170) for more details.
We manage to achieve good performance on the passkey retrieval task from [Landmark Attention: Random-Access Infinite Context Length for Transformers](https://arxiv.org/abs/2305.16300). The code for generating the prompt and running the model is located in `examples/passkey.py`.
<p align="center" width="100%">
<img src="https://raw.githubusercontent.com/CStanKonrad/long_llama/main/assets/plot_passkey.png" alt="LongLLaMA" style="width: 70%; min-width: 300px; display: block; margin: auto;">
</p>
Our LongLLaMA 3B model also shows improvements when using long context on two downstream tasks, TREC question classification and WebQS question answering.
<center>
| Context/Dataset | TREC | WebQS |
| --- | --- | --- |
| 2K | 67.0 | 21.2 |
| 4K | 71.6 | 21.4 |
| 6K | 72.9 | 22.2 |
| 8K | **73.3** | **22.4** |
</center>
LongLLama retains performance on tasks that do not require long context. We provide a comparison with OpenLLaMA
on [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) in a zero-shot setting.
<center>
| Task/Metric | OpenLLaMA-3B | LongLLaMA-3B |
|----------------|----------|-----------|
| anli_r1/acc | 0.33 | 0.32 |
| anli_r2/acc | 0.32 | 0.33 |
| anli_r3/acc | 0.35 | 0.35 |
| arc_challenge/acc | 0.34 | 0.34 |
| arc_challenge/acc_norm | 0.37 | 0.37 |
| arc_easy/acc | 0.69 | 0.68 |
| arc_easy/acc_norm | 0.65 | 0.63 |
| boolq/acc | 0.68 | 0.68 |
| hellaswag/acc | 0.49 | 0.48 |
| hellaswag/acc_norm | 0.67 | 0.65 |
| openbookqa/acc | 0.27 | 0.28 |
| openbookqa/acc_norm | 0.40 | 0.38 |
| piqa/acc | 0.75 | 0.73 |
| piqa/acc_norm | 0.76 | 0.75 |
| record/em | 0.88 | 0.87 |
| record/f1 | 0.89 | 0.87 |
| rte/acc | 0.58 | 0.60 |
| truthfulqa_mc/mc1 | 0.22 | 0.24 |
| truthfulqa_mc/mc2 | 0.35 | 0.38 |
| wic/acc | 0.48 | 0.50 |
| winogrande/acc | 0.62 | 0.60 |
| Avg score | 0.53 | 0.53 |
</center>
## Authors
- [Szymon Tworkowski](https://scholar.google.com/citations?user=1V8AeXYAAAAJ&hl=en)
- [Konrad Staniszewski](https://scholar.google.com/citations?user=CM6PCBYAAAAJ)
- [Mikołaj Pacek](https://scholar.google.com/citations?user=eh6iEbQAAAAJ&hl=en&oi=ao)
- [Henryk Michalewski](https://scholar.google.com/citations?user=YdHW1ycAAAAJ&hl=en)
- [Yuhuai Wu](https://scholar.google.com/citations?user=bOQGfFIAAAAJ&hl=en)
- [Piotr Miłoś](https://scholar.google.pl/citations?user=Se68XecAAAAJ&hl=pl&oi=ao)
## Citation
To cite this work please use
```bibtex
@misc{tworkowski2023focused,
title={Focused Transformer: Contrastive Training for Context Scaling},
author={Szymon Tworkowski and Konrad Staniszewski and Mikołaj Pacek and Yuhuai Wu and Henryk Michalewski and Piotr Miłoś},
year={2023},
eprint={2307.03170},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## License
The code and checkpoints are licensed under [Apache License, Version 2.0](http://www.apache.org/licenses/LICENSE-2.0).
Some of the examples use external code (see headers of files for copyright notices and licenses).
## Acknowledgments
We gratefully acknowledge the TPU Research Cloud program, which was instrumental to our research by providing significant computational resources. We are also grateful to Xinyang Geng and Hao Liu for releasing [OpenLLaMA](https://github.com/openlm-research/open_llama) checkpoints and the [EasyLM](https://github.com/young-geng/EasyLM) library.
***End of original Model File***
---
## Please consider to support my work
**Coming Soon:** I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.
<center>
[](https://maddes8cht.github.io)
[](https://stackexchange.com/users/26485911)
[](https://github.com/maddes8cht)
[](https://huggingface.co/maddes8cht)
[](https://twitter.com/maddes1966)
</center> |
TheBloke/WestLake-7B-v2-GGUF | TheBloke | 2024-01-24T22:25:54Z | 425 | 18 | transformers | [
"transformers",
"gguf",
"mistral",
"en",
"base_model:senseable/WestLake-7B-v2",
"license:apache-2.0",
"text-generation-inference",
"region:us"
]
| null | 2024-01-24T22:13:08Z | ---
base_model: senseable/WestLake-7B-v2
inference: false
language:
- en
library_name: transformers
license: apache-2.0
model_creator: Common Sense
model_name: Westlake 7B V2
model_type: mistral
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 -->
# Westlake 7B V2 - GGUF
- Model creator: [Common Sense](https://huggingface.co/senseable)
- Original model: [Westlake 7B V2](https://huggingface.co/senseable/WestLake-7B-v2)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Common Sense's Westlake 7B V2](https://huggingface.co/senseable/WestLake-7B-v2).
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/WestLake-7B-v2-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/WestLake-7B-v2-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF)
* [Common Sense's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/senseable/WestLake-7B-v2)
<!-- 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [westlake-7b-v2.Q2_K.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.Q2_K.gguf) | Q2_K | 2 | 2.72 GB| 5.22 GB | significant quality loss - not recommended for most purposes |
| [westlake-7b-v2.Q3_K_S.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [westlake-7b-v2.Q3_K_M.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [westlake-7b-v2.Q3_K_L.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [westlake-7b-v2.Q4_0.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [westlake-7b-v2.Q4_K_S.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [westlake-7b-v2.Q4_K_M.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [westlake-7b-v2.Q5_0.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [westlake-7b-v2.Q5_K_S.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [westlake-7b-v2.Q5_K_M.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [westlake-7b-v2.Q6_K.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [westlake-7b-v2.Q8_0.gguf](https://huggingface.co/TheBloke/WestLake-7B-v2-GGUF/blob/main/westlake-7b-v2.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/WestLake-7B-v2-GGUF and below it, a specific filename to download, such as: westlake-7b-v2.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/WestLake-7B-v2-GGUF westlake-7b-v2.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/WestLake-7B-v2-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/WestLake-7B-v2-GGUF westlake-7b-v2.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 westlake-7b-v2.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="./westlake-7b-v2.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="./westlake-7b-v2.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: Common Sense's Westlake 7B V2
**Update Notes:**
*Version 2 trained 1 additional epoch cycle for 3 total*
# Westlake-7Bv2: Role-Play & Text Generation Specialist Model
Welcome to the documentation of Westlake-7B, a cutting-edge language model designed for exceptional role-play and text generation tasks. This README file aims to provide an overview of our capabilities, usage guidelines, and potential applications.
## About Westlake-7Bv2
Westlake-7B is built upon a vast corpus of diverse texts, enabling it to generate contextually relevant responses in various scenarios. With its impressive size of 7 billion parameters, this model excels at understanding nuances in language and producing creative outputs.
### Key Features
1. **Role-Play**: Westlake-7Bv2 can seamlessly adapt to different character personas and engage in dynamic conversations while maintaining consistency throughout the interaction. It can generate believable dialogues across various genres, including fiction, non-fiction, historical events, or even fantasy worlds.
2. **Text Generation**: This model is proficient at generating original content such as stories, poems, essays, news articles, and more. Its ability to capture the essence of different writing styles makes it an ideal tool for creative writers seeking inspiration or assistance in their projects.
3. **Contextual Understanding**: Westlake-7B's extensive training allows it to comprehend complex contexts and generate responses that align with given situations. It can handle multiple topics simultaneously, making it versatile across various applications.
4. **Continuous Learning**: As a language model, Westlake-7B continuously improves its performance through ongoing training on new data sets. This ensures its capabilities remain up-to-date and relevant in an ever-evolving world of communication.
## Usage Guidelines
To utilize Westlake-7Bv2 for your projects or experiments, follow these steps:
1. **Prompting**: Provide clear and concise prompts that outline the desired role-play scenario or text generation task. The quality of output depends heavily on the clarity and relevance of input instructions.
2. **Feedback Loop**: For optimal results, consider incorporating a feedback loop into your application to refine generated outputs based on user preferences or additional contextual information. This iterative process can significantly enhance the model's performance in specific domains.
3. **Ethical Considerations**: As with any AI system, ensure responsible usage of Westlake-7B by avoiding harmful content generation or misuse of its capabilities.
## Potential Applications
Westlake-7Bv2's versatility makes it suitable for various applications across different industries:
1. **Creative Writing**: Assist authors in generating new ideas, expanding storylines, or even completing drafts by providing creative suggestions and textual content.
2. **Education**: Enhance language learning platforms with interactive role-play scenarios to improve students' communication skills and cultural understanding.
3. **Gaming**: Integrate Westlake-7B into game engines for dynamic non-player character interactions or generating unique questlines based on player choices.
4. **Customer Support**: Leverage the model's conversational abilities to create chatbots capable of handling complex queries and providing personalized assistance.
5. **Social Media**: Develop applications that generate engaging content such as captions, status updates, or even entire posts tailored to users' preferences and interests.
<!-- original-model-card end -->
|
Mabeck/Heidrun-Mistral-7B-chat | Mabeck | 2024-04-02T11:51:28Z | 425 | 6 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gguf",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"en",
"da",
"dataset:Mabeck/danish-OpenHermes",
"dataset:kobprof/skolegpt-instruct",
"base_model:Mabeck/Heidrun-Mistral-7B-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2024-02-13T17:46:47Z | ---
language:
- en
- da
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: Mabeck/Heidrun-Mistral-7B-base
datasets:
- Mabeck/danish-OpenHermes
- kobprof/skolegpt-instruct
license: mit
pipeline_tag: text-generation
---
<img src="https://huggingface.co/Mabeck/Heidrun-Mistral-7B-chat/resolve/main/heidrun.jpeg" alt="Heidrun Logo" width="400">
# Model description
Heidrun-Mistral-7B-chat is a chat-model based on [Heidrun-Mistral-7B-base](https://huggingface.co/Mabeck/Heidrun-Mistral-7B-base), finetuned on [danish-OpenHermes](https://huggingface.co/datasets/Mabeck/danish-OpenHermes) and [skoleGPT](https://huggingface.co/datasets/kobprof/skolegpt-instruct) for a instruction/chat format.
It is a new SOTA Danish open-source LLM and shows very strong performance in logic and reasoning tasks.
Heidrun-7B ranks 1st among Danish open-sourced LLMs based on the [ScandEval](https://scandeval.com/mainland-scandinavian-nlg/) benchmark and shares 1st place on all Scandinavian languages.
# Benchmarks
The following benchmarks have been tested using [ScandEval](https://github.com/ScandEval/ScandEval). Rankings don't include merged models and GPT4 and GPT3.5 ranks 1 and 2:
- **MMLU-da**: 35.66%+-0.85%/51.68+-0.63%, ranks 3rd
- **DANSK**: 50.80% ± 2.33% / 34.04% ± 1.76%, ranks 3rd=
- **Hellaswag-da**: 29.18% ± 0.99%/ 46.64% ± 0.76%, ranks 4th
# Datasets
This model is trained on Danish instruction datasets [danish-OpenHermes](Mabeck/danish-OpenHermes) and [skoleGPT](https://huggingface.co/datasets/kobprof/skolegpt-instruct), which have not been safeguarded or alligned.
Most of the data has been machine-translated and may contain incorrect responses.
# Samples
This model uses the ChatML format. Using other formats may degrade the model's performance.
Samples from the model using ChatML format:
```
"<s> <im_start>system
Du er en AI-hjælper. Du får en opgave fra en bruger hvor du kort og præcist skal forklare svaret.
<im_end>
<im_start>user
Hvilke 3 populære retter findes der i dansk madlavning?
<im_end>
<im_start>assistant
1. Smørrebrød: Smørrebrød er en populær dansk ret, der består af brød med forskellige toppings som røget laks, rejer, ost eller andre ingredienser.
2. Frikadeller: Frikadeller er en traditionel dansk ret lavet af kødboller af kalvekød, svinekød eller lam, krydret med krydderurter og kogt i smør eller olie.
3. Rød kål: Rød kål er en populær side ret i dansk madlavning.
<im_end></s>"
```
```
"<s> <im_start>system
Du er en AI-hjælper. Du får en opgave fra en bruger hvor du kort og præcist skal forklare svaret.
<im_end>
<im_start>user
Hvilke 3 områder skal fokuseres på for at effektivt tackle klimaforandringer?
<im_end>
<im_start>assistant
1. Energiproduktion: Fokus på vedvarende energikilder som sol, vind og vandkraft for at reducere afhængigheden af fossile brændstoffer og minimere drivhusgasemissioner.
2. Transport: Fremme bæredygtige transportformer som offentlig transport, cykling og elektriske køretøjer for at reducere luftforurening og afhængigheden af fossile brændstoffer.
3. Skovbevarelse og affaldshåndtering: Fremme skovbevarelse og bæredygtig skovdrift for at fange kuldioxid og reducere drivhusgasemissioner, samt fremme genbrug og reducere affaldsproduktion for at mindske mængden af drivhusgasemissioner fra affald.
<im_end></s>"
```
# Uploaded model
- **Developed by:** Mabeck
- **Finetuned from model :** Mabeck/Heidrun-Mistral-7B-base
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
ozbillwang/stable-diffusion-2-1_768-ema-pruned.gguf | ozbillwang | 2024-03-06T08:22:22Z | 425 | 0 | null | [
"gguf",
"license:mit",
"region:us"
]
| null | 2024-03-06T08:13:41Z | ---
license: mit
---
|
GraydientPlatformAPI/mfcgPDXL_v10 | GraydientPlatformAPI | 2024-03-13T06:00:43Z | 425 | 1 | diffusers | [
"diffusers",
"safetensors",
"license:openrail",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
]
| text-to-image | 2024-03-13T05:38:40Z | ---
license: openrail
---
|
PeanutJar/MV01-PeanutButter-v0.0.11dev0-SFT-7B-GGUF | PeanutJar | 2024-03-15T07:00:58Z | 425 | 0 | null | [
"gguf",
"en",
"dataset:PeanutJar/PeanutButter-v0.0.11dev0-SFT-ShareGPT",
"base_model:mistralai/Mistral-7B-v0.1",
"region:us"
]
| null | 2024-03-14T16:00:29Z | ---
language:
- en
base_model: mistralai/Mistral-7B-v0.1
datasets:
- PeanutJar/PeanutButter-v0.0.11dev0-SFT-ShareGPT
---
Trained on topics such as roleplay, science, news, writing, and other various general purpose stuff with Metharme tags.
Might be good, might be bad.
# No system prompt
```
<s><|user|>Input1<|model|>Output1</s><|user|>Input2<|model|>Output2</s>...
````
# With system prompt:
```
<s><|system|>SystemInput<|user|>Input1<|model|>Output1</s><|user|>Input2<|model|>Output2</s>...
```
You can do your normal instruct model stuff. I've also made it so that RP can be done through instruct.
```
<s><|system|>Character A: Bob the Builder
Character B: Ronald McDonald
Character A Description: The guy from the TV show.
Character B Descriotion: The fastfood mascot guy.
Scenario: They do some stuff<|user|>Hello Ronald.<|model|>Sup.</s><|user|>How are you on this fine day?<|model|>I'm doing swell.</s>
```
or if you use a UI like [KoboldAI Lite](https://lite.koboldai.net/) you can start the chat through an instruction in the memory, then enable chat mode.
```
<s><|system|>Character A: Bob the Builder
Character B: Ronald McDonald
Character A Description: The guy from the TV show.
Character B Descriotion: The fastfood mascot guy.
Scenario: They do some stuff<|model|>
Bob the Builder: Hello Ronald.
Ronald McDonald: Sup.</s>
Bob the Builder: How are you on this fine day?
Ronald McDonald: I'm doing swell.</s>
```
[<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) |
cocorang/Komodo_6B_v3.0.0_GGUF | cocorang | 2024-03-28T08:26:54Z | 425 | 1 | null | [
"gguf",
"region:us"
]
| null | 2024-03-15T05:22:51Z | https://huggingface.co/TeamUNIVA/Komodo_6B_v3.0.0
This is the GGUF conversion version.
---
license: apache-2.0
---
|
ahmed-naseer/designgen-23k-25k | ahmed-naseer | 2024-06-12T06:06:25Z | 425 | 1 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2024-03-29T16:29:47Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### DesignGen- AI based Textile Design pattern Generation
|
stablediffusionapi/albedobase-xl-v21 | stablediffusionapi | 2024-04-08T04:06:57Z | 425 | 0 | diffusers | [
"diffusers",
"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 | 2024-04-08T04:03:37Z | ---
license: creativeml-openrail-m
tags:
- modelslab.com
- stable-diffusion-api
- text-to-image
- ultra-realistic
pinned: true
---
# AlbedoBase XL v2.1 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 "albedobase-xl-v21"
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/albedobase-xl-v21)
Model link: [View model](https://modelslab.com/models/albedobase-xl-v21)
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": "albedobase-xl-v21",
"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** |
mradermacher/FishxInstruct-GGUF | mradermacher | 2024-05-06T04:58:41Z | 425 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:Fredithefish/FishxInstruct",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-13T05:00:33Z | ---
base_model: Fredithefish/FishxInstruct
language:
- en
library_name: transformers
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/Fredithefish/FishxInstruct
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/FishxInstruct-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/FishxInstruct-GGUF/resolve/main/FishxInstruct.Q2_K.gguf) | Q2_K | 17.4 | |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.IQ3_XS.gguf) | IQ3_XS | 19.5 | |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.IQ3_S.gguf) | IQ3_S | 20.5 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.Q3_K_S.gguf) | Q3_K_S | 20.5 | |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.IQ3_M.gguf) | IQ3_M | 21.5 | |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.Q3_K_M.gguf) | Q3_K_M | 22.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.Q3_K_L.gguf) | Q3_K_L | 24.3 | |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.IQ4_XS.gguf) | IQ4_XS | 25.5 | |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.Q4_K_S.gguf) | Q4_K_S | 26.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.Q4_K_M.gguf) | Q4_K_M | 28.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.Q5_K_S.gguf) | Q5_K_S | 32.3 | |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.Q5_K_M.gguf) | Q5_K_M | 33.3 | |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.Q6_K.gguf) | Q6_K | 38.5 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/FishxInstruct-GGUF/resolve/main/FishxInstruct.Q8_0.gguf) | Q8_0 | 49.7 | 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 -->
|
bartowski/Nxcode-CQ-7B-orpo-GGUF | bartowski | 2024-05-11T14:47:48Z | 425 | 3 | null | [
"gguf",
"code",
"text-generation",
"license:mit",
"region:us"
]
| text-generation | 2024-05-11T14:28:35Z | ---
license: mit
tags:
- code
pipeline_tag: text-generation
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of Nxcode-CQ-7B-orpo
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/NTQAI/Nxcode-CQ-7B-orpo
All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
## 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 |
| -------- | ---------- | --------- | ----------- |
| [Nxcode-CQ-7B-orpo-Q8_0.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-Q8_0.gguf) | Q8_0 | 7.70GB | Extremely high quality, generally unneeded but max available quant. |
| [Nxcode-CQ-7B-orpo-Q6_K.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-Q6_K.gguf) | Q6_K | 6.37GB | Very high quality, near perfect, *recommended*. |
| [Nxcode-CQ-7B-orpo-Q5_K_M.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-Q5_K_M.gguf) | Q5_K_M | 5.42GB | High quality, *recommended*. |
| [Nxcode-CQ-7B-orpo-Q5_K_S.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-Q5_K_S.gguf) | Q5_K_S | 5.14GB | High quality, *recommended*. |
| [Nxcode-CQ-7B-orpo-Q4_K_M.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-Q4_K_M.gguf) | Q4_K_M | 4.73GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [Nxcode-CQ-7B-orpo-Q4_K_S.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-Q4_K_S.gguf) | Q4_K_S | 4.41GB | Slightly lower quality with more space savings, *recommended*. |
| [Nxcode-CQ-7B-orpo-IQ4_NL.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ4_NL.gguf) | IQ4_NL | 4.18GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
| [Nxcode-CQ-7B-orpo-IQ4_XS.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ4_XS.gguf) | IQ4_XS | 4.03GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Nxcode-CQ-7B-orpo-Q3_K_L.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-Q3_K_L.gguf) | Q3_K_L | 3.98GB | Lower quality but usable, good for low RAM availability. |
| [Nxcode-CQ-7B-orpo-Q3_K_M.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-Q3_K_M.gguf) | Q3_K_M | 3.80GB | Even lower quality. |
| [Nxcode-CQ-7B-orpo-IQ3_M.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ3_M.gguf) | IQ3_M | 3.60GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Nxcode-CQ-7B-orpo-IQ3_S.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ3_S.gguf) | IQ3_S | 3.50GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
| [Nxcode-CQ-7B-orpo-Q3_K_S.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-Q3_K_S.gguf) | Q3_K_S | 3.50GB | Low quality, not recommended. |
| [Nxcode-CQ-7B-orpo-IQ3_XS.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ3_XS.gguf) | IQ3_XS | 3.35GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Nxcode-CQ-7B-orpo-IQ3_XXS.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ3_XXS.gguf) | IQ3_XXS | 3.22GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Nxcode-CQ-7B-orpo-Q2_K.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-Q2_K.gguf) | Q2_K | 3.05GB | Very low quality but surprisingly usable. |
| [Nxcode-CQ-7B-orpo-IQ2_M.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ2_M.gguf) | IQ2_M | 3.00GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [Nxcode-CQ-7B-orpo-IQ2_S.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ2_S.gguf) | IQ2_S | 2.87GB | Very low quality, uses SOTA techniques to be usable. |
| [Nxcode-CQ-7B-orpo-IQ2_XS.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ2_XS.gguf) | IQ2_XS | 2.76GB | Very low quality, uses SOTA techniques to be usable. |
| [Nxcode-CQ-7B-orpo-IQ2_XXS.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ2_XXS.gguf) | IQ2_XXS | 2.61GB | Lower quality, uses SOTA techniques to be usable. |
| [Nxcode-CQ-7B-orpo-IQ1_M.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ1_M.gguf) | IQ1_M | 2.45GB | Extremely low quality, *not* recommended. |
| [Nxcode-CQ-7B-orpo-IQ1_S.gguf](https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF/blob/main/Nxcode-CQ-7B-orpo-IQ1_S.gguf) | IQ1_S | 2.36GB | 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/Nxcode-CQ-7B-orpo-GGUF --include "Nxcode-CQ-7B-orpo-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/Nxcode-CQ-7B-orpo-GGUF --include "Nxcode-CQ-7B-orpo-Q8_0.gguf/*" --local-dir Nxcode-CQ-7B-orpo-Q8_0 --local-dir-use-symlinks False
```
You can either specify a new local-dir (Nxcode-CQ-7B-orpo-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
|
gaianet/Yi-1.5-34B-Chat-16K-GGUF | gaianet | 2024-06-13T15:50:09Z | 425 | 1 | null | [
"gguf",
"text-generation",
"base_model:01-ai/Yi-1.5-34B-Chat-16K",
"license:other",
"region:us"
]
| text-generation | 2024-05-18T05:22:34Z | ---
base_model: 01-ai/Yi-1.5-34B-Chat-16K
inference: false
license: other
license_link: LICENSE
license_name: yi-license
model_creator: 01-ai
model_name: Yi-1.5-34B-Chat-16
model_type: yi
pipeline_tag: text-generation
quantized_by: Second State Inc.
---
# Yi-1.5-34B-Chat-16K-GGUF
## Original Model
[01-ai/Yi-1.5-34B-Chat-16K](https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K)
## Run with Gaianet
**Prompt template**
prompt template: `chatml`
**Reverse prompt**
reverse prompt: `<|im_end|>`
**Context size**
chat_ctx_size: `16384`
**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*
|
mradermacher/WestLake-10.7B-v2-i1-GGUF | mradermacher | 2024-05-27T02:45:53Z | 425 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:froggeric/WestLake-10.7B-v2",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-25T00:12:33Z | ---
base_model: froggeric/WestLake-10.7B-v2
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/froggeric/WestLake-10.7B-v2
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/WestLake-10.7B-v2-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/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-IQ1_M.gguf) | i1-IQ1_M | 2.7 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-IQ2_S.gguf) | i1-IQ2_S | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-Q2_K.gguf) | i1-Q2_K | 4.1 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-IQ3_S.gguf) | i1-IQ3_S | 4.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.3 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.8 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.9 | |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-Q4_0.gguf) | i1-Q4_0 | 6.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.5 | |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 7.7 | |
| [GGUF](https://huggingface.co/mradermacher/WestLake-10.7B-v2-i1-GGUF/resolve/main/WestLake-10.7B-v2.i1-Q6_K.gguf) | i1-Q6_K | 8.9 | 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 -->
|
CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF | CISCai | 2024-06-17T22:57:09Z | 425 | 0 | null | [
"gguf",
"code",
"dataset:m-a-p/CodeFeedback-Filtered-Instruction",
"arxiv:2401.06066",
"base_model:deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct",
"license:other",
"region:us"
]
| null | 2024-06-17T21:05:11Z | ---
license: other
license_name: deepseek-license
license_link: https://github.com/deepseek-ai/DeepSeek-Coder-V2/raw/main/LICENSE-MODEL
tags:
- code
language:
- code
base_model: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
model_creator: DeepSeek AI
model_name: DeepSeek-Coder-V2-Lite-Instruct
model_type: deepseek2
datasets:
- m-a-p/CodeFeedback-Filtered-Instruction
quantized_by: CISC
---
# DeepSeek-Coder-V2-Lite-Instruct - SOTA GGUF
- Model creator: [DeepSeek AI](https://huggingface.co/deepseek-ai)
- Original model: [DeepSeek-Coder-V2-Lite-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct)
<!-- description start -->
## Description
This repo contains State Of The Art quantized GGUF format model files for [DeepSeek-Coder-V2-Lite-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct).
Quantization was done with an importance matrix that was trained for ~250K tokens (64 batches of 4096 tokens) of answers from the [CodeFeedback-Filtered-Instruction](https://huggingface.co/datasets/m-a-p/CodeFeedback-Filtered-Instruction) dataset.
Fill-in-Middle token metadata has been added, see [example](#simple-llama-cpp-python-example-fill-in-middle-code).
NOTE: Due to some of the tensors in this model being oddly shaped a consequential portion of the quantization fell back to IQ4_NL instead of the specified method, causing somewhat larger (and "smarter"; even IQ1_M is quite usable) model files than usual!
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: DeepSeek v2
```
User: {prompt}
Assistant:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv3 files are compatible with llama.cpp from May 29th 2024 onwards, as of commit [fb76ec2](https://github.com/ggerganov/llama.cpp/commit/fb76ec31a9914b7761c1727303ab30380fd4f05c)
They are also compatible with many third party UIs and libraries provided they are built using a recent llama.cpp.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_IQ1_S - 1-bit quantization in super-blocks with an importance matrix applied, effectively using 1.56 bits per weight (bpw)
* GGML_TYPE_IQ1_M - 1-bit quantization in super-blocks with an importance matrix applied, effectively using 1.75 bpw
* GGML_TYPE_IQ2_XXS - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.06 bpw
* GGML_TYPE_IQ2_XS - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.31 bpw
* GGML_TYPE_IQ2_S - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.5 bpw
* GGML_TYPE_IQ2_M - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.7 bpw
* GGML_TYPE_IQ3_XXS - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.06 bpw
* GGML_TYPE_IQ3_XS - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.3 bpw
* GGML_TYPE_IQ3_S - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.44 bpw
* GGML_TYPE_IQ3_M - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.66 bpw
* GGML_TYPE_IQ4_XS - 4-bit quantization in super-blocks with an importance matrix applied, effectively using 4.25 bpw
* GGML_TYPE_IQ4_NL - 4-bit non-linearly mapped quantization with an importance matrix applied, effectively using 4.5 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-Coder-V2-Lite-Instruct.IQ1_S.gguf](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.IQ1_S.gguf) | IQ1_S | 1 | 4.5 GB| 5.5 GB | smallest, significant quality loss |
| [DeepSeek-Coder-V2-Lite-Instruct.IQ1_M.gguf](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.IQ1_M.gguf) | IQ1_M | 1 | 4.7 GB| 5.7 GB | very small, significant quality loss |
| [DeepSeek-Coder-V2-Lite-Instruct.IQ2_XXS.gguf](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.IQ2_XXS.gguf) | IQ2_XXS | 2 | 5.1 GB| 6.1 GB | very small, high quality loss |
| [DeepSeek-Coder-V2-Lite-Instruct.IQ2_XS.gguf](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.IQ2_XS.gguf) | IQ2_XS | 2 | 5.4 GB| 6.4 GB | very small, high quality loss |
| [DeepSeek-Coder-V2-Lite-Instruct.IQ2_S.gguf](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.IQ2_S.gguf) | IQ2_S | 2 | 5.4 GB| 6.4 GB | small, substantial quality loss |
| [DeepSeek-Coder-V2-Lite-Instruct.IQ2_M.gguf](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.IQ2_M.gguf) | IQ2_M | 2 | 5.7 GB| 6.7 GB | small, greater quality loss |
| [DeepSeek-Coder-V2-Lite-Instruct.IQ3_XXS.gguf](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.IQ3_XXS.gguf) | IQ3_XXS | 3 | 6.3 GB| 7.3 GB | very small, high quality loss |
| [DeepSeek-Coder-V2-Lite-Instruct.IQ3_XS.gguf](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.IQ3_XS.gguf) | IQ3_XS | 3 | 6.5 GB| 7.5 GB | small, substantial quality loss |
| [DeepSeek-Coder-V2-Lite-Instruct.IQ3_S.gguf](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.IQ3_S.gguf) | IQ3_S | 3 | 6.8 GB| 7.8 GB | small, greater quality loss |
| [DeepSeek-Coder-V2-Lite-Instruct.IQ3_M.gguf](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.IQ3_M.gguf) | IQ3_M | 3 | 6.9 GB| 7.9 GB | medium, balanced quality - recommended |
| [DeepSeek-Coder-V2-Lite-Instruct.IQ4_NL.gguf](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.IQ4_NL.gguf) | IQ4_NL | 4 | 8.1 GB| 9.1 GB | small, substantial quality loss |
Generated importance matrix file: [DeepSeek-Coder-V2-Lite-Instruct.imatrix.dat](https://huggingface.co/CISCai/DeepSeek-Coder-V2-Lite-Instruct-SOTA-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct.imatrix.dat)
**Note**: the above RAM figures assume no GPU offloading with 4K context. 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-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [fb76ec3](https://github.com/ggerganov/llama.cpp/commit/fb76ec31a9914b7761c1727303ab30380fd4f05c) or later.
```shell
./llama-cli -ngl 28 -m DeepSeek-Coder-V2-Lite-Instruct.IQ4_NL.gguf --color -c 131072 --temp 0 --repeat-penalty 1.1 -p "User: {prompt}\n\nAssistant:"
```
Change `-ngl 28` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 131072` to the desired sequence length.
If you are low on V/RAM try quantizing the K-cache with `-ctk q8_0` or even `-ctk q4_0` for big memory savings (depending on context size).
There is a similar option for V-cache (`-ctv`), however that requires Flash Attention [which is not working yet with this model](https://github.com/ggerganov/llama.cpp/issues/7343).
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 from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) module.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://llama-cpp-python.readthedocs.io/en/latest/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Prebuilt wheel with basic CPU support
pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
# Prebuilt wheel with NVidia CUDA acceleration
pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121 (or cu122 etc.)
# Prebuilt wheel with Metal GPU acceleration
pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/metal
# Build base version with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUDA=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
# Or with Vulkan acceleration
CMAKE_ARGS="-DLLAMA_VULKAN=on" pip install llama-cpp-python
# Or with Kompute acceleration
CMAKE_ARGS="-DLLAMA_KOMPUTE=on" pip install llama-cpp-python
# Or with SYCL acceleration
CMAKE_ARGS="-DLLAMA_SYCL=on -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx" 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_CUDA=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Chat Completion API
llm = Llama(model_path="./DeepSeek-Coder-V2-Lite-Instruct.IQ4_NL.gguf", n_gpu_layers=28, n_ctx=131072)
print(llm.create_chat_completion(
repeat_penalty = 1.1,
messages = [
{
"role": "user",
"content": "Pick a LeetCode challenge and solve it in Python."
}
]
))
```
#### Simple llama-cpp-python example fill-in-middle code
```python
from llama_cpp import Llama
# Completion API
prompt = "def add("
suffix = "\n return sum\n\n"
llm = Llama(model_path="./DeepSeek-Coder-V2-Lite-Instruct.IQ4_NL.gguf", n_gpu_layers=28, n_ctx=131072)
output = llm.create_completion(
temperature = 0.0,
repeat_penalty = 1.0,
prompt = prompt,
suffix = suffix
)
# Models sometimes repeat suffix in response, attempt to filter that
response = output["choices"][0]["text"]
response_stripped = response.rstrip()
unwanted_response_suffix = suffix.rstrip()
unwanted_response_length = len(unwanted_response_suffix)
filtered = False
if unwanted_response_suffix and response_stripped[-unwanted_response_length:] == unwanted_response_suffix:
response = response_stripped[:-unwanted_response_length]
filtered = True
print(f"Fill-in-Middle completion{' (filtered)' if filtered else ''}:\n\n{prompt}\033[32m{response}\033[{'33' if filtered else '0'}m{suffix}\033[0m")
```
<!-- README_GGUF.md-how-to-run end -->
<!-- original-model-card start -->
<!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable html -->
<!-- markdownlint-disable no-duplicate-header -->
<div align="center">
<img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V2" />
</div>
<hr>
<div align="center" style="line-height: 1;">
<a href="https://www.deepseek.com/" target="_blank" style="margin: 2px;">
<img alt="Homepage" src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://chat.deepseek.com/" target="_blank" style="margin: 2px;">
<img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-DeepSeek%20V2-536af5?color=536af5&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://huggingface.co/deepseek-ai" target="_blank" style="margin: 2px;">
<img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
</a>
</div>
<div align="center" style="line-height: 1;">
<a href="https://discord.gg/Tc7c45Zzu5" target="_blank" style="margin: 2px;">
<img alt="Discord" src="https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/qr.jpeg?raw=true" target="_blank" style="margin: 2px;">
<img alt="Wechat" src="https://img.shields.io/badge/WeChat-DeepSeek%20AI-brightgreen?logo=wechat&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://twitter.com/deepseek_ai" target="_blank" style="margin: 2px;">
<img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
</a>
</div>
<div align="center" style="line-height: 1;">
<a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-CODE" style="margin: 2px;">
<img alt="Code License" src="https://img.shields.io/badge/Code_License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL" style="margin: 2px;">
<img alt="Model License" src="https://img.shields.io/badge/Model_License-Model_Agreement-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
</a>
</div>
<p align="center">
<a href="#4-api-platform">API Platform</a> |
<a href="#5-how-to-run-locally">How to Use</a> |
<a href="#6-license">License</a> |
</p>
<p align="center">
<a href="https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/paper.pdf"><b>Paper Link</b>👁️</a>
</p>
# DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
## 1. Introduction
We present DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. Specifically, DeepSeek-Coder-V2 is further pre-trained from DeepSeek-Coder-V2-Base with 6 trillion tokens sourced from a high-quality and multi-source corpus. Through this continued pre-training, DeepSeek-Coder-V2 substantially enhances the coding and mathematical reasoning capabilities of DeepSeek-Coder-V2-Base, while maintaining comparable performance in general language tasks. Compared to DeepSeek-Coder, DeepSeek-Coder-V2 demonstrates significant advancements in various aspects of code-related tasks, as well as reasoning and general capabilities. Additionally, DeepSeek-Coder-V2 expands its support for programming languages from 86 to 338, while extending the context length from 16K to 128K.
<p align="center">
<img width="100%" src="https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/figures/performance.png?raw=true">
</p>
In standard benchmark evaluations, DeepSeek-Coder-V2 achieves superior performance compared to closed-source models such as GPT4-Turbo, Claude 3 Opus, and Gemini 1.5 Pro in coding and math benchmarks. The list of supported programming languages can be found in the paper.
## 2. Model Downloads
We release the DeepSeek-Coder-V2 with 16B and 236B parameters based on the [DeepSeekMoE](https://arxiv.org/pdf/2401.06066) framework, which has actived parameters of only 2.4B and 21B , including base and instruct models, to the public.
<div align="center">
| **Model** | **#Total Params** | **#Active Params** | **Context Length** | **Download** |
| :-----------------------------: | :---------------: | :----------------: | :----------------: | :----------------------------------------------------------: |
| DeepSeek-Coder-V2-Lite-Base | 16B | 2.4B | 128k | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Base) |
| DeepSeek-Coder-V2-Lite-Instruct | 16B | 2.4B | 128k | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct) |
| DeepSeek-Coder-V2-Base | 236B | 21B | 128k | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Base) |
| DeepSeek-Coder-V2-Instruct | 236B | 21B | 128k | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct) |
</div>
## 3. Chat Website
You can chat with the DeepSeek-Coder-V2 on DeepSeek's official website: [coder.deepseek.com](https://coder.deepseek.com/sign_in)
## 4. API Platform
We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.com](https://platform.deepseek.com/). Sign up for over millions of free tokens. And you can also pay-as-you-go at an unbeatable price.
<p align="center">
<img width="40%" src="https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/figures/model_price.jpg?raw=true">
</p>
## 5. How to run locally
**Here, we provide some examples of how to use DeepSeek-Coder-V2-Lite model. If you want to utilize DeepSeek-Coder-V2 in BF16 format for inference, 80GB*8 GPUs are required.**
### Inference with Huggingface's Transformers
You can directly employ [Huggingface's Transformers](https://github.com/huggingface/transformers) for model inference.
#### Code Completion
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Base", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
input_text = "#write a quick sort algorithm"
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
#### Code Insertion
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Base", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
input_text = """<｜fim▁begin｜>def quick_sort(arr):
if len(arr) <= 1:
return arr
pivot = arr[0]
left = []
right = []
<｜fim▁hole｜>
if arr[i] < pivot:
left.append(arr[i])
else:
right.append(arr[i])
return quick_sort(left) + [pivot] + quick_sort(right)<｜fim▁end｜>"""
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True)[len(input_text):])
```
#### Chat Completion
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
messages=[
{ 'role': 'user', 'content': "write a quick sort algorithm in python."}
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
# tokenizer.eos_token_id is the id of <|EOT|> token
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
```
The complete chat template can be found within `tokenizer_config.json` located in the huggingface model repository.
An example of chat template is as belows:
```bash
<｜begin▁of▁sentence｜>User: {user_message_1}
Assistant: {assistant_message_1}<｜end▁of▁sentence｜>User: {user_message_2}
Assistant:
```
You can also add an optional system message:
```bash
<｜begin▁of▁sentence｜>{system_message}
User: {user_message_1}
Assistant: {assistant_message_1}<｜end▁of▁sentence｜>User: {user_message_2}
Assistant:
```
### Inference with vLLM (recommended)
To utilize [vLLM](https://github.com/vllm-project/vllm) for model inference, please merge this Pull Request into your vLLM codebase: https://github.com/vllm-project/vllm/pull/4650.
```python
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
max_model_len, tp_size = 8192, 1
model_name = "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True, enforce_eager=True)
sampling_params = SamplingParams(temperature=0.3, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
messages_list = [
[{"role": "user", "content": "Who are you?"}],
[{"role": "user", "content": "write a quick sort algorithm in python."}],
[{"role": "user", "content": "Write a piece of quicksort code in C++."}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)
```
## 6. License
This code repository is licensed under [the MIT License](https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/LICENSE-CODE). The use of DeepSeek-Coder-V2 Base/Instruct models is subject to [the Model License](https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/LICENSE-MODEL). DeepSeek-Coder-V2 series (including Base and Instruct) supports commercial use.
## 7. Contact
If you have any questions, please raise an issue or contact us at [[email protected]]([email protected]).
|
mradermacher/Llama-Salad-4x8B-V3-GGUF | mradermacher | 2024-06-19T21:04:42Z | 425 | 1 | transformers | [
"transformers",
"gguf",
"nsfw",
"not-for-all-audiences",
"llama-3",
"text-generation-inference",
"moe",
"mergekit",
"merge",
"en",
"base_model:HiroseKoichi/Llama-Salad-4x8B-V3",
"license:llama3",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-19T00:56:42Z | ---
base_model: HiroseKoichi/Llama-Salad-4x8B-V3
language:
- en
library_name: transformers
license: llama3
quantized_by: mradermacher
tags:
- nsfw
- not-for-all-audiences
- llama-3
- text-generation-inference
- moe
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/HiroseKoichi/Llama-Salad-4x8B-V3
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-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-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.Q2_K.gguf) | Q2_K | 9.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.IQ3_XS.gguf) | IQ3_XS | 10.5 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.Q3_K_S.gguf) | Q3_K_S | 11.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.IQ3_S.gguf) | IQ3_S | 11.1 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.IQ3_M.gguf) | IQ3_M | 11.2 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.Q3_K_M.gguf) | Q3_K_M | 12.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.Q3_K_L.gguf) | Q3_K_L | 13.1 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.IQ4_XS.gguf) | IQ4_XS | 13.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.Q4_K_S.gguf) | Q4_K_S | 14.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.Q4_K_M.gguf) | Q4_K_M | 15.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.Q5_K_S.gguf) | Q5_K_S | 17.3 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.Q5_K_M.gguf) | Q5_K_M | 17.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.Q6_K.gguf) | Q6_K | 20.6 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V3-GGUF/resolve/main/Llama-Salad-4x8B-V3.Q8_0.gguf) | Q8_0 | 26.6 | 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 -->
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.