modelId
stringlengths 5
122
| author
stringlengths 2
42
| last_modified
unknown | downloads
int64 0
738M
| likes
int64 0
11k
| library_name
stringclasses 245
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 48
values | createdAt
unknown | card
stringlengths 1
901k
|
|---|---|---|---|---|---|---|---|---|---|
nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2 | nm-testing | "2024-06-13T20:05:56Z" | 1,010 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-06-13T20:05:24Z" | Entry not found |
pierreguillou/bert-large-cased-squad-v1.1-portuguese | pierreguillou | "2022-01-04T09:57:00Z" | 1,009 | 39 | transformers | [
"transformers",
"pytorch",
"tf",
"bert",
"question-answering",
"bert-large",
"pt",
"dataset:brWaC",
"dataset:squad",
"dataset:squad_v1_pt",
"license:mit",
"endpoints_compatible",
"region:us"
] | question-answering | "2022-03-02T23:29:05Z" | ---
language: pt
license: mit
tags:
- question-answering
- bert
- bert-large
- pytorch
datasets:
- brWaC
- squad
- squad_v1_pt
metrics:
- squad
widget:
- text: "Quando começou a pandemia de Covid-19 no mundo?"
context: "A pandemia de COVID-19, também conhecida como pandemia de coronavírus, é uma pandemia em curso de COVID-19, uma doença respiratória causada pelo coronavírus da síndrome respiratória aguda grave 2 (SARS-CoV-2). O vírus tem origem zoonótica e o primeiro caso conhecido da doença remonta a dezembro de 2019 em Wuhan, na China."
- text: "Onde foi descoberta a Covid-19?"
context: "A pandemia de COVID-19, também conhecida como pandemia de coronavírus, é uma pandemia em curso de COVID-19, uma doença respiratória causada pelo coronavírus da síndrome respiratória aguda grave 2 (SARS-CoV-2). O vírus tem origem zoonótica e o primeiro caso conhecido da doença remonta a dezembro de 2019 em Wuhan, na China."
---
# Portuguese BERT large cased QA (Question Answering), finetuned on SQUAD v1.1
## Introduction
The model was trained on the dataset SQUAD v1.1 in portuguese from the [Deep Learning Brasil group](http://www.deeplearningbrasil.com.br/).
The language model used is the [BERTimbau Large](https://huggingface.co/neuralmind/bert-large-portuguese-cased) (aka "bert-large-portuguese-cased") from [Neuralmind.ai](https://neuralmind.ai/): BERTimbau is a pretrained BERT model for Brazilian Portuguese that achieves state-of-the-art performances on three downstream NLP tasks: Named Entity Recognition, Sentence Textual Similarity and Recognizing Textual Entailment. It is available in two sizes: Base and Large.
## Informations on the method used
All the informations are in the blog post : [NLP | Como treinar um modelo de Question Answering em qualquer linguagem baseado no BERT large, melhorando o desempenho do modelo utilizando o BERT base? (estudo de caso em português)](https://medium.com/@pierre_guillou/nlp-como-treinar-um-modelo-de-question-answering-em-qualquer-linguagem-baseado-no-bert-large-1c899262dd96)
## Notebook in GitHub
[question_answering_BERT_large_cased_squad_v11_pt.ipynb](https://github.com/piegu/language-models/blob/master/question_answering_BERT_large_cased_squad_v11_pt.ipynb) ([nbviewer version](https://nbviewer.jupyter.org/github/piegu/language-models/blob/master/question_answering_BERT_large_cased_squad_v11_pt.ipynb))
## Performance
The results obtained are the following:
```
f1 = 84.43 (against 82.50 for the base model)
exact match = 72.68 (against 70.49 for the base model)
```
## How to use the model... with Pipeline
```python
import transformers
from transformers import pipeline
# source: https://pt.wikipedia.org/wiki/Pandemia_de_COVID-19
context = r"""
A pandemia de COVID-19, também conhecida como pandemia de coronavírus, é uma pandemia em curso de COVID-19,
uma doença respiratória causada pelo coronavírus da síndrome respiratória aguda grave 2 (SARS-CoV-2).
O vírus tem origem zoonótica e o primeiro caso conhecido da doença remonta a dezembro de 2019 em Wuhan, na China.
Em 20 de janeiro de 2020, a Organização Mundial da Saúde (OMS) classificou o surto
como Emergência de Saúde Pública de Âmbito Internacional e, em 11 de março de 2020, como pandemia.
Em 18 de junho de 2021, 177 349 274 casos foram confirmados em 192 países e territórios,
com 3 840 181 mortes atribuídas à doença, tornando-se uma das pandemias mais mortais da história.
Os sintomas de COVID-19 são altamente variáveis, variando de nenhum a doenças com risco de morte.
O vírus se espalha principalmente pelo ar quando as pessoas estão perto umas das outras.
Ele deixa uma pessoa infectada quando ela respira, tosse, espirra ou fala e entra em outra pessoa pela boca, nariz ou olhos.
Ele também pode se espalhar através de superfícies contaminadas.
As pessoas permanecem contagiosas por até duas semanas e podem espalhar o vírus mesmo se forem assintomáticas.
"""
model_name = 'pierreguillou/bert-large-cased-squad-v1.1-portuguese'
nlp = pipeline("question-answering", model=model_name)
question = "Quando começou a pandemia de Covid-19 no mundo?"
result = nlp(question=question, context=context)
print(f"Answer: '{result['answer']}', score: {round(result['score'], 4)}, start: {result['start']}, end: {result['end']}")
# Answer: 'dezembro de 2019', score: 0.5087, start: 290, end: 306
```
## How to use the model... with the Auto classes
```python
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("pierreguillou/bert-large-cased-squad-v1.1-portuguese")
model = AutoModelForQuestionAnswering.from_pretrained("pierreguillou/bert-large-cased-squad-v1.1-portuguese")
```
Or just clone the model repo:
```python
git lfs install
git clone https://huggingface.co/pierreguillou/bert-large-cased-squad-v1.1-portuguese
# if you want to clone without large files – just their pointers
# prepend your git clone with the following env var:
GIT_LFS_SKIP_SMUDGE=1
```
## Limitations and bias
The training data used for this model come from Portuguese SQUAD. It could contain a lot of unfiltered content, which is far from neutral, and biases.
## Author
Portuguese BERT large cased QA (Question Answering), finetuned on SQUAD v1.1 was trained and evaluated by [Pierre GUILLOU](https://www.linkedin.com/in/pierreguillou/) thanks to the Open Source code, platforms and advices of many organizations ([link to the list](https://medium.com/@pierre_guillou/nlp-como-treinar-um-modelo-de-question-answering-em-qualquer-linguagem-baseado-no-bert-large-1c899262dd96#c2f5)). In particular: [Hugging Face](https://huggingface.co/), [Neuralmind.ai](https://neuralmind.ai/), [Deep Learning Brasil group](http://www.deeplearningbrasil.com.br/) and [AI Lab](https://ailab.unb.br/).
## Citation
If you use our work, please cite:
```bibtex
@inproceedings{pierreguillou2021bertlargecasedsquadv11portuguese,
title={Portuguese BERT large cased QA (Question Answering), finetuned on SQUAD v1.1},
author={Pierre Guillou},
year={2021}
}
``` |
NeelNanda/Attn_Only_1L512W_C4_Code | NeelNanda | "2022-10-26T14:33:12Z" | 1,009 | 1 | transformers | [
"transformers",
"endpoints_compatible",
"region:us"
] | null | "2022-10-26T14:26:30Z" | Entry not found |
liminerity/Blur-7b-v1.22 | liminerity | "2024-03-11T18:32:49Z" | 1,009 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"s3nh/Sonya-Panda-7B-slerp",
"argilla/distilabeled-Marcoro14-7B-slerp",
"Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp",
"base_model:s3nh/Sonya-Panda-7B-slerp",
"base_model:argilla/distilabeled-Marcoro14-7B-slerp",
"base_model:Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-18T04:40:21Z" | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- s3nh/Sonya-Panda-7B-slerp
- argilla/distilabeled-Marcoro14-7B-slerp
- Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
base_model:
- s3nh/Sonya-Panda-7B-slerp
- argilla/distilabeled-Marcoro14-7B-slerp
- Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
model-index:
- name: Blur-7b-v1.22
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: 62.29
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22
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: 82.0
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22
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: 58.03
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22
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: 68.01
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22
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: 78.61
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22
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: 31.16
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22
name: Open LLM Leaderboard
---
# Blur-7b-v1.22
Blur-7b-v1.22 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [s3nh/Sonya-Panda-7B-slerp](https://huggingface.co/s3nh/Sonya-Panda-7B-slerp)
* [argilla/distilabeled-Marcoro14-7B-slerp](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp)
* [Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp](https://huggingface.co/Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp)
## 🧩 Configuration
```yaml
models:
- model: s3nh/Sonya-Panda-7B-slerp
parameters:
density: [1, 0.7, 0.1] # density gradient
weight: 1.0
- model: argilla/distilabeled-Marcoro14-7B-slerp
parameters:
density: 0.5
weight: [0, 0.3, 0.7, 1] # weight gradient
- model: Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
parameters:
density: 0.33
weight:
- filter: mlp
value: 0.5
- value: 0
merge_method: ties
base_model: liminerity/Blur-7b-v1.21
parameters:
normalize: true
int8_mask: true
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "liminerity/Blur-7b-v1.22"
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"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_liminerity__Blur-7b-v1.22)
| Metric |Value|
|---------------------------------|----:|
|Avg. |63.35|
|AI2 Reasoning Challenge (25-Shot)|62.29|
|HellaSwag (10-Shot) |82.00|
|MMLU (5-Shot) |58.03|
|TruthfulQA (0-shot) |68.01|
|Winogrande (5-shot) |78.61|
|GSM8k (5-shot) |31.16|
|
Azazelle/Mocha-SR-7b-ex | Azazelle | "2024-03-23T16:11:31Z" | 1,009 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:WizardLM/WizardMath-7B-V1.1",
"base_model:akjindal53244/Mistral-7B-v0.1-Open-Platypus",
"base_model:Open-Orca/Mistral-7B-OpenOrca",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-23T15:29:24Z" | ---
pipeline_tag: text-generation
base_model:
- mistralai/Mistral-7B-v0.1
- WizardLM/WizardMath-7B-V1.1
- akjindal53244/Mistral-7B-v0.1-Open-Platypus
- Open-Orca/Mistral-7B-OpenOrca
library_name: transformers
tags:
- mergekit
- merge
license: cc-by-4.0
---
# Moko-SR-7b-ex
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the rescaled_sample merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca)
* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
* [akjindal53244/Mistral-7B-v0.1-Open-Platypus](https://huggingface.co/akjindal53244/Mistral-7B-v0.1-Open-Platypus)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: Open-Orca/Mistral-7B-OpenOrca
parameters:
density: [1, 0.7, 0.1] # density gradient
weight: 1.0
- model: akjindal53244/Mistral-7B-v0.1-Open-Platypus
parameters:
density: 0.5
weight: [0, 0.3, 0.7, 1] # weight gradient
- model: WizardLM/WizardMath-7B-V1.1
parameters:
density: 0.33
weight:
- filter: mlp
value: 0.5
- value: 0
merge_method: rescaled_sample
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: float16
```
|
statking/zephyr-7b-sft-full-orpo | statking | "2024-05-21T09:00:33Z" | 1,009 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"trl",
"orpo",
"generated_from_trainer",
"conversational",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"base_model:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-18T16:35:37Z" | ---
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- alignment-handbook
- trl
- orpo
- generated_from_trainer
- trl
- orpo
- alignment-handbook
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: zephyr-7b-sft-full-orpo
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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/statking/huggingface/runs/90a8kp39)
# zephyr-7b-sft-full-orpo
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrafeedback_binarized dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4701
- Rewards/chosen: -0.0364
- Rewards/rejected: -0.0499
- Rewards/accuracies: 0.6587
- Rewards/margins: 0.0135
- Logps/rejected: -0.9978
- Logps/chosen: -0.7282
- Logits/rejected: -2.9263
- Logits/chosen: -2.9434
- Nll Loss: 0.4357
- Log Odds Ratio: -0.6093
- Log Odds Chosen: 0.4456
## 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: 7e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: inverse_sqrt
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
| 0.5226 | 0.1049 | 100 | 0.5280 | -0.0386 | -0.0472 | 0.6329 | 0.0086 | -0.9448 | -0.7728 | -2.7583 | -2.7860 | 0.4953 | -0.6326 | 0.2873 |
| 0.5074 | 0.2098 | 200 | 0.5134 | -0.0381 | -0.0478 | 0.6409 | 0.0098 | -0.9566 | -0.7612 | -2.6736 | -2.7002 | 0.4774 | -0.6357 | 0.3190 |
| 0.5265 | 0.3146 | 300 | 0.5012 | -0.0379 | -0.0479 | 0.6329 | 0.0099 | -0.9572 | -0.7588 | -2.7317 | -2.7594 | 0.4653 | -0.6374 | 0.3278 |
| 0.5194 | 0.4195 | 400 | 0.4912 | -0.0371 | -0.0478 | 0.6429 | 0.0107 | -0.9559 | -0.7417 | -2.6640 | -2.6974 | 0.4560 | -0.6284 | 0.3607 |
| 0.5008 | 0.5244 | 500 | 0.4847 | -0.0373 | -0.0489 | 0.6508 | 0.0117 | -0.9786 | -0.7455 | -2.5957 | -2.6294 | 0.4499 | -0.6209 | 0.3873 |
| 0.4725 | 0.6293 | 600 | 0.4794 | -0.0362 | -0.0470 | 0.6349 | 0.0107 | -0.9394 | -0.7248 | -2.6147 | -2.6477 | 0.4435 | -0.6320 | 0.3567 |
| 0.4875 | 0.7341 | 700 | 0.4767 | -0.0368 | -0.0498 | 0.6409 | 0.0129 | -0.9955 | -0.7365 | -2.6910 | -2.7213 | 0.4416 | -0.6158 | 0.4180 |
| 0.4796 | 0.8390 | 800 | 0.4740 | -0.0371 | -0.0508 | 0.6508 | 0.0137 | -1.0162 | -0.7416 | -2.7913 | -2.8114 | 0.4396 | -0.6169 | 0.4363 |
| 0.4851 | 0.9439 | 900 | 0.4714 | -0.0357 | -0.0466 | 0.6528 | 0.0109 | -0.9324 | -0.7143 | -2.9543 | -2.9692 | 0.4361 | -0.6245 | 0.3669 |
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
John6666/better-than-hentai-xxxl-unreal-pony-mk2-sdxl | John6666 | "2024-06-04T11:23:41Z" | 1,009 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"stable-diffusion-xl",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2024-06-04T11:18:43Z" | ---
license: other
tags:
- text-to-image
- stable-diffusion
- stable-diffusion-xl
---
Original model is [here](https://civitai.com/models/258840/better-than-hentai-xxxl?modelVersionId=544529).
|
Raunak1/EI-Mistral-Q4_0-GGUF | Raunak1 | "2024-06-25T13:07:27Z" | 1,009 | 1 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:Raunak1/EI-Mistral",
"endpoints_compatible",
"region:us"
] | null | "2024-06-25T13:07:05Z" | ---
base_model: Raunak1/EI-Mistral
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
---
# Raunak1/EI-Mistral-Q4_0-GGUF
This model was converted to GGUF format from [`Raunak1/EI-Mistral`](https://huggingface.co/Raunak1/EI-Mistral) 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/Raunak1/EI-Mistral) 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 Raunak1/EI-Mistral-Q4_0-GGUF --hf-file ei-mistral-q4_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Raunak1/EI-Mistral-Q4_0-GGUF --hf-file ei-mistral-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 Raunak1/EI-Mistral-Q4_0-GGUF --hf-file ei-mistral-q4_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Raunak1/EI-Mistral-Q4_0-GGUF --hf-file ei-mistral-q4_0.gguf -c 2048
```
|
monsoon-nlp/hindi-bert | monsoon-nlp | "2023-09-20T22:22:29Z" | 1,008 | 16 | transformers | [
"transformers",
"pytorch",
"tf",
"safetensors",
"electra",
"feature-extraction",
"hi",
"doi:10.57967/hf/1305",
"endpoints_compatible",
"region:us"
] | feature-extraction | "2022-03-02T23:29:05Z" | ---
language: hi
---
# Releasing Hindi ELECTRA model
This is a first attempt at a Hindi language model trained with Google Research's [ELECTRA](https://github.com/google-research/electra).
**As of 2022 I recommend Google's MuRIL model trained on English, Hindi, and other major Indian languages, both in their script and latinized script**: https://huggingface.co/google/muril-base-cased and https://huggingface.co/google/muril-large-cased
**For causal language models, I would suggest https://huggingface.co/sberbank-ai/mGPT, though this is a large model**
<a href="https://colab.research.google.com/drive/1R8TciRSM7BONJRBc9CBZbzOmz39FTLl_">Tokenization and training CoLab</a>
I originally used <a href="https://github.com/monsoonNLP/transformers">a modified ELECTRA</a> for finetuning, but now use SimpleTransformers.
<a href="https://medium.com/@mapmeld/teaching-hindi-to-electra-b11084baab81">Blog post</a> - I was greatly influenced by: https://huggingface.co/blog/how-to-train
## Example Notebooks
This small model has comparable results to Multilingual BERT on <a href="https://colab.research.google.com/drive/18FQxp9QGOORhMENafQilEmeAo88pqVtP">BBC Hindi news classification</a>
and on <a href="https://colab.research.google.com/drive/1UYn5Th8u7xISnPUBf72at1IZIm3LEDWN">Hindi movie reviews / sentiment analysis</a> (using SimpleTransformers)
You can get higher accuracy using ktrain by adjusting learning rate (also: changing model_type in config.json - this is an open issue with ktrain): https://colab.research.google.com/drive/1mSeeSfVSOT7e-dVhPlmSsQRvpn6xC05w?usp=sharing
Question-answering on MLQA dataset: https://colab.research.google.com/drive/1i6fidh2tItf_-IDkljMuaIGmEU6HT2Ar#scrollTo=IcFoAHgKCUiQ
A larger model (<a href="https://huggingface.co/monsoon-nlp/hindi-tpu-electra">Hindi-TPU-Electra</a>) using ELECTRA base size outperforms both models on Hindi movie reviews / sentiment analysis, but
does not perform as well on the BBC news classification task.
## Corpus
Download: https://drive.google.com/drive/folders/1SXzisKq33wuqrwbfp428xeu_hDxXVUUu?usp=sharing
The corpus is two files:
- Hindi CommonCrawl deduped by OSCAR https://traces1.inria.fr/oscar/
- latest Hindi Wikipedia ( https://dumps.wikimedia.org/hiwiki/ ) + WikiExtractor to txt
Bonus notes:
- Adding English wiki text or parallel corpus could help with cross-lingual tasks and training
## Vocabulary
https://drive.google.com/file/d/1-6tXrii3tVxjkbrpSJE9MOG_HhbvP66V/view?usp=sharing
Bonus notes:
- Created with HuggingFace Tokenizers; you can increase vocabulary size and re-train; remember to change ELECTRA vocab_size
## Training
Structure your files, with data-dir named "trainer" here
```
trainer
- vocab.txt
- pretrain_tfrecords
-- (all .tfrecord... files)
- models
-- modelname
--- checkpoint
--- graph.pbtxt
--- model.*
```
CoLab notebook gives examples of GPU vs. TPU setup
[configure_pretraining.py](https://github.com/google-research/electra/blob/master/configure_pretraining.py)
## Conversion
Use this process to convert an in-progress or completed ELECTRA checkpoint to a Transformers-ready model:
```
git clone https://github.com/huggingface/transformers
python ./transformers/src/transformers/convert_electra_original_tf_checkpoint_to_pytorch.py
--tf_checkpoint_path=./models/checkpointdir
--config_file=config.json
--pytorch_dump_path=pytorch_model.bin
--discriminator_or_generator=discriminator
python
```
```
from transformers import TFElectraForPreTraining
model = TFElectraForPreTraining.from_pretrained("./dir_with_pytorch", from_pt=True)
model.save_pretrained("tf")
```
Once you have formed one directory with config.json, pytorch_model.bin, tf_model.h5, special_tokens_map.json, tokenizer_config.json, and vocab.txt on the same level, run:
```
transformers-cli upload directory
```
|
Kukedlc/NeuTrixOmniBe-7B-model-remix | Kukedlc | "2024-03-04T13:08:11Z" | 1,008 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"CultriX/NeuralTrix-7B-dpo",
"paulml/OmniBeagleSquaredMBX-v3-7B-v2",
"base_model:CultriX/NeuralTrix-7B-dpo",
"base_model:paulml/OmniBeagleSquaredMBX-v3-7B-v2",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-10T23:20:07Z" | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- CultriX/NeuralTrix-7B-dpo
- paulml/OmniBeagleSquaredMBX-v3-7B-v2
base_model:
- CultriX/NeuralTrix-7B-dpo
- paulml/OmniBeagleSquaredMBX-v3-7B-v2
model-index:
- name: NeuTrixOmniBe-7B-model-remix
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: 72.7
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuTrixOmniBe-7B-model-remix
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: 89.03
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuTrixOmniBe-7B-model-remix
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: 64.57
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuTrixOmniBe-7B-model-remix
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: 76.9
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuTrixOmniBe-7B-model-remix
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: 85.08
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuTrixOmniBe-7B-model-remix
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: 69.52
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuTrixOmniBe-7B-model-remix
name: Open LLM Leaderboard
---
# NOT FOR USE -- BUG IN RESPONSE
# NeuTrixOmniBe-7B-model-remix
NeuTrixOmniBe-7B-model-remix is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [CultriX/NeuralTrix-7B-dpo](https://huggingface.co/CultriX/NeuralTrix-7B-dpo)
* [paulml/OmniBeagleSquaredMBX-v3-7B-v2](https://huggingface.co/paulml/OmniBeagleSquaredMBX-v3-7B-v2)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: CultriX/NeuralTrix-7B-dpo
layer_range: [0, 32]
- model: paulml/OmniBeagleSquaredMBX-v3-7B-v2
layer_range: [0, 32]
merge_method: slerp
base_model: CultriX/NeuralTrix-7B-dpo
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 = "Kukedlc/NeuTrixOmniBe-7B-model-remix"
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"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Kukedlc__NeuTrixOmniBe-7B-model-remix)
| Metric |Value|
|---------------------------------|----:|
|Avg. |76.30|
|AI2 Reasoning Challenge (25-Shot)|72.70|
|HellaSwag (10-Shot) |89.03|
|MMLU (5-Shot) |64.57|
|TruthfulQA (0-shot) |76.90|
|Winogrande (5-shot) |85.08|
|GSM8k (5-shot) |69.52|
|
ChaoticNeutrals/Kool-Aid_7B | ChaoticNeutrals | "2024-03-15T20:32:50Z" | 1,008 | 4 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"en",
"license:other",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-15T05:14:01Z" | ---
language:
- en
license: other
library_name: transformers
tags:
- mergekit
- merge
base_model: []
model-index:
- name: Kool-Aid_7B
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: 67.49
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Kool-Aid_7B
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: 86.13
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Kool-Aid_7B
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: 63.82
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Kool-Aid_7B
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: 65.12
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Kool-Aid_7B
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: 81.37
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Kool-Aid_7B
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: 54.21
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Kool-Aid_7B
name: Open LLM Leaderboard
---
# Kool-Aid
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* ErosEris
* CookieNexus
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: CookieNexus
layer_range: [0, 32]
- model: ErosEris
layer_range: [0, 32]
merge_method: slerp
base_model: CookieNexus
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
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ChaoticNeutrals__Kool-Aid_7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |69.69|
|AI2 Reasoning Challenge (25-Shot)|67.49|
|HellaSwag (10-Shot) |86.13|
|MMLU (5-Shot) |63.82|
|TruthfulQA (0-shot) |65.12|
|Winogrande (5-shot) |81.37|
|GSM8k (5-shot) |54.21|
|
Vikhrmodels/it-5.2-fp16-cp | Vikhrmodels | "2024-05-29T08:21:08Z" | 1,008 | 6 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"ru",
"en",
"arxiv:2405.13929",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-14T19:10:54Z" | ---
library_name: transformers
language:
- ru
- en
license: apache-2.0
---
# Релиз вихря 0.5
Долили сильно больше данных в sft, теперь стабильнее работает json и multiturn, слегка подточили параметры претрена модели
Added a lot more data to sft, now json and multiturn work more stable on long context and hard prompts
- [Google Colab](https://colab.research.google.com/drive/1-_BWsJycBm3rEyjpBx2_ejshpemQYHbe?usp=sharing)
- [GGUF](https://huggingface.co/Vikhrmodels/it-5.2-fp16-cp-GGUF)
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/it-5.2-fp16-cp",
device_map="auto",
attn_implementation="sdpa",
torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained("Vikhrmodels/it-5.2-fp16-cp")
from transformers import AutoTokenizer, pipeline
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
prompts = [
"В чем разница между фруктом и овощем?",
"Годы жизни колмагорова?"]
def test_inference(prompt):
prompt = pipe.tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=False, add_generation_prompt=True)
print(prompt)
outputs = pipe(prompt, max_new_tokens=512, do_sample=True, num_beams=1, temperature=0.25, top_k=50, top_p=0.98, eos_token_id=79097)
return outputs[0]['generated_text'][len(prompt):].strip()
for prompt in prompts:
print(f" prompt:\n{prompt}")
print(f" response:\n{test_inference(prompt)}")
print("-"*50)
```
```
@article{nikolich2024vikhr,
title={Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian},
author={Aleksandr Nikolich and Konstantin Korolev and Artem Shelmanov},
journal={arXiv preprint arXiv:2405.13929},
year={2024},
url={https://arxiv.org/pdf/2405.13929}
}
``` |
OpenBuddy/openbuddy-yi1.5-34b-v21.3-32k | OpenBuddy | "2024-06-06T00:59:41Z" | 1,008 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mixtral",
"conversational",
"zh",
"en",
"fr",
"de",
"ja",
"ko",
"it",
"ru",
"fi",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-06-05T12:14:55Z" | ---
license: apache-2.0
language:
- zh
- en
- fr
- de
- ja
- ko
- it
- ru
- fi
pipeline_tag: text-generation
inference: false
library_name: transformers
tags:
- mixtral
---
# OpenBuddy - Open Multilingual Chatbot
GitHub and Usage Guide: [https://github.com/OpenBuddy/OpenBuddy](https://github.com/OpenBuddy/OpenBuddy)
Website and Demo: [https://openbuddy.ai](https://openbuddy.ai)
Evaluation result of this model: [Evaluation.txt](Evaluation.txt)
# Copyright Notice
Base model: https://huggingface.co/01-ai/Yi-1.5-34B-32K
License: Apache 2.0
# Prompt Format
We recommend using the fast tokenizer from `transformers`, which should be enabled by default in the `transformers` and `vllm` libraries. Other implementations including `sentencepiece` may not work as expected, especially for special tokens like `<|role|>`, `<|says|>` and `<|end|>`.
```
<|role|>system<|says|>You(assistant) are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human(user).
Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
You cannot access the internet, but you have vast knowledge, cutoff: 2023-04.
You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), not related to GPT or OpenAI.<|end|>
<|role|>user<|says|>History input 1<|end|>
<|role|>assistant<|says|>History output 1<|end|>
<|role|>user<|says|>History input 2<|end|>
<|role|>assistant<|says|>History output 2<|end|>
<|role|>user<|says|>Current input<|end|>
<|role|>assistant<|says|>
```
This format is also defined in `tokenizer_config.json`, which means you can directly use `vllm` to deploy an OpenAI-like API service. For more information, please refer to the [vllm documentation](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html).
## Disclaimer
All OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.
OpenBuddy is provided "as-is" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.
By using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.
## 免责声明
所有OpenBuddy模型均存在固有的局限性，可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事，不要使用这些模型，以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。
OpenBuddy按“原样”提供，不附带任何种类的明示或暗示的保证，包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下，作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任（无论是合同、侵权还是其他原因）承担责任。
使用OpenBuddy即表示您同意这些条款和条件，并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。 |
njaana/phi3-mini-demo-fine-tune-model | njaana | "2024-06-12T09:37:28Z" | 1,008 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | "2024-06-12T04:41:57Z" | Entry not found |
timm/convnextv2_large.fcmae_ft_in22k_in1k_384 | timm | "2024-02-10T23:29:26Z" | 1,007 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2301.00808",
"license:cc-by-nc-4.0",
"region:us"
] | image-classification | "2023-01-05T01:54:26Z" | ---
license: cc-by-nc-4.0
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
- imagenet-1k
---
# Model card for convnextv2_large.fcmae_ft_in22k_in1k_384
A ConvNeXt-V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine-tuned on ImageNet-22k and then ImageNet-1k.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 198.0
- GMACs: 101.1
- Activations (M): 126.7
- Image size: 384 x 384
- **Papers:**
- ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders: https://arxiv.org/abs/2301.00808
- **Original:** https://github.com/facebookresearch/ConvNeXt-V2
- **Dataset:** ImageNet-1k
- **Pretrain 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('convnextv2_large.fcmae_ft_in22k_in1k_384', 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(
'convnextv2_large.fcmae_ft_in22k_in1k_384',
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, 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(
'convnextv2_large.fcmae_ft_in22k_in1k_384',
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
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
| model |top1 |top5 |img_size|param_count|gmacs |macts |samples_per_sec|batch_size|
|------------------------------------------------------------------------------------------------------------------------------|------|------|--------|-----------|------|------|---------------|----------|
| [convnextv2_huge.fcmae_ft_in22k_in1k_512](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_512) |88.848|98.742|512 |660.29 |600.81|413.07|28.58 |48 |
| [convnextv2_huge.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_384) |88.668|98.738|384 |660.29 |337.96|232.35|50.56 |64 |
| [convnext_xxlarge.clip_laion2b_soup_ft_in1k](https://huggingface.co/timm/convnext_xxlarge.clip_laion2b_soup_ft_in1k) |88.612|98.704|256 |846.47 |198.09|124.45|122.45 |256 |
| [convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384) |88.312|98.578|384 |200.13 |101.11|126.74|196.84 |256 |
| [convnextv2_large.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k_384) |88.196|98.532|384 |197.96 |101.1 |126.74|128.94 |128 |
| [convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320) |87.968|98.47 |320 |200.13 |70.21 |88.02 |283.42 |256 |
| [convnext_xlarge.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k_384) |87.75 |98.556|384 |350.2 |179.2 |168.99|124.85 |192 |
| [convnextv2_base.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k_384) |87.646|98.422|384 |88.72 |45.21 |84.49 |209.51 |256 |
| [convnext_large.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k_384) |87.476|98.382|384 |197.77 |101.1 |126.74|194.66 |256 |
| [convnext_large_mlp.clip_laion2b_augreg_ft_in1k](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_augreg_ft_in1k) |87.344|98.218|256 |200.13 |44.94 |56.33 |438.08 |256 |
| [convnextv2_large.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k) |87.26 |98.248|224 |197.96 |34.4 |43.13 |376.84 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384) |87.138|98.212|384 |88.59 |45.21 |84.49 |365.47 |256 |
| [convnext_xlarge.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k) |87.002|98.208|224 |350.2 |60.98 |57.5 |368.01 |256 |
| [convnext_base.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k_384) |86.796|98.264|384 |88.59 |45.21 |84.49 |366.54 |256 |
| [convnextv2_base.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k) |86.74 |98.022|224 |88.72 |15.38 |28.75 |624.23 |256 |
| [convnext_large.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k) |86.636|98.028|224 |197.77 |34.4 |43.13 |581.43 |256 |
| [convnext_base.clip_laiona_augreg_ft_in1k_384](https://huggingface.co/timm/convnext_base.clip_laiona_augreg_ft_in1k_384) |86.504|97.97 |384 |88.59 |45.21 |84.49 |368.14 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in12k_in1k](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k) |86.344|97.97 |256 |88.59 |20.09 |37.55 |816.14 |256 |
| [convnextv2_huge.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in1k) |86.256|97.75 |224 |660.29 |115.0 |79.07 |154.72 |256 |
| [convnext_small.in12k_ft_in1k_384](https://huggingface.co/timm/convnext_small.in12k_ft_in1k_384) |86.182|97.92 |384 |50.22 |25.58 |63.37 |516.19 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in1k](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in1k) |86.154|97.68 |256 |88.59 |20.09 |37.55 |819.86 |256 |
| [convnext_base.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k) |85.822|97.866|224 |88.59 |15.38 |28.75 |1037.66 |256 |
| [convnext_small.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k_384) |85.778|97.886|384 |50.22 |25.58 |63.37 |518.95 |256 |
| [convnextv2_large.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in1k) |85.742|97.584|224 |197.96 |34.4 |43.13 |375.23 |256 |
| [convnext_small.in12k_ft_in1k](https://huggingface.co/timm/convnext_small.in12k_ft_in1k) |85.174|97.506|224 |50.22 |8.71 |21.56 |1474.31 |256 |
| [convnext_tiny.in12k_ft_in1k_384](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k_384) |85.118|97.608|384 |28.59 |13.14 |39.48 |856.76 |256 |
| [convnextv2_tiny.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k_384) |85.112|97.63 |384 |28.64 |13.14 |39.48 |491.32 |256 |
| [convnextv2_base.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in1k) |84.874|97.09 |224 |88.72 |15.38 |28.75 |625.33 |256 |
| [convnext_small.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k) |84.562|97.394|224 |50.22 |8.71 |21.56 |1478.29 |256 |
| [convnext_large.fb_in1k](https://huggingface.co/timm/convnext_large.fb_in1k) |84.282|96.892|224 |197.77 |34.4 |43.13 |584.28 |256 |
| [convnext_tiny.in12k_ft_in1k](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k) |84.186|97.124|224 |28.59 |4.47 |13.44 |2433.7 |256 |
| [convnext_tiny.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k_384) |84.084|97.14 |384 |28.59 |13.14 |39.48 |862.95 |256 |
| [convnextv2_tiny.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k) |83.894|96.964|224 |28.64 |4.47 |13.44 |1452.72 |256 |
| [convnext_base.fb_in1k](https://huggingface.co/timm/convnext_base.fb_in1k) |83.82 |96.746|224 |88.59 |15.38 |28.75 |1054.0 |256 |
| [convnextv2_nano.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k_384) |83.37 |96.742|384 |15.62 |7.22 |24.61 |801.72 |256 |
| [convnext_small.fb_in1k](https://huggingface.co/timm/convnext_small.fb_in1k) |83.142|96.434|224 |50.22 |8.71 |21.56 |1464.0 |256 |
| [convnextv2_tiny.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in1k) |82.92 |96.284|224 |28.64 |4.47 |13.44 |1425.62 |256 |
| [convnext_tiny.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k) |82.898|96.616|224 |28.59 |4.47 |13.44 |2480.88 |256 |
| [convnext_nano.in12k_ft_in1k](https://huggingface.co/timm/convnext_nano.in12k_ft_in1k) |82.282|96.344|224 |15.59 |2.46 |8.37 |3926.52 |256 |
| [convnext_tiny_hnf.a2h_in1k](https://huggingface.co/timm/convnext_tiny_hnf.a2h_in1k) |82.216|95.852|224 |28.59 |4.47 |13.44 |2529.75 |256 |
| [convnext_tiny.fb_in1k](https://huggingface.co/timm/convnext_tiny.fb_in1k) |82.066|95.854|224 |28.59 |4.47 |13.44 |2346.26 |256 |
| [convnextv2_nano.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k) |82.03 |96.166|224 |15.62 |2.46 |8.37 |2300.18 |256 |
| [convnextv2_nano.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in1k) |81.83 |95.738|224 |15.62 |2.46 |8.37 |2321.48 |256 |
| [convnext_nano_ols.d1h_in1k](https://huggingface.co/timm/convnext_nano_ols.d1h_in1k) |80.866|95.246|224 |15.65 |2.65 |9.38 |3523.85 |256 |
| [convnext_nano.d1h_in1k](https://huggingface.co/timm/convnext_nano.d1h_in1k) |80.768|95.334|224 |15.59 |2.46 |8.37 |3915.58 |256 |
| [convnextv2_pico.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_pico.fcmae_ft_in1k) |80.304|95.072|224 |9.07 |1.37 |6.1 |3274.57 |256 |
| [convnext_pico.d1_in1k](https://huggingface.co/timm/convnext_pico.d1_in1k) |79.526|94.558|224 |9.05 |1.37 |6.1 |5686.88 |256 |
| [convnext_pico_ols.d1_in1k](https://huggingface.co/timm/convnext_pico_ols.d1_in1k) |79.522|94.692|224 |9.06 |1.43 |6.5 |5422.46 |256 |
| [convnextv2_femto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_femto.fcmae_ft_in1k) |78.488|93.98 |224 |5.23 |0.79 |4.57 |4264.2 |256 |
| [convnext_femto_ols.d1_in1k](https://huggingface.co/timm/convnext_femto_ols.d1_in1k) |77.86 |93.83 |224 |5.23 |0.82 |4.87 |6910.6 |256 |
| [convnext_femto.d1_in1k](https://huggingface.co/timm/convnext_femto.d1_in1k) |77.454|93.68 |224 |5.22 |0.79 |4.57 |7189.92 |256 |
| [convnextv2_atto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_atto.fcmae_ft_in1k) |76.664|93.044|224 |3.71 |0.55 |3.81 |4728.91 |256 |
| [convnext_atto_ols.a2_in1k](https://huggingface.co/timm/convnext_atto_ols.a2_in1k) |75.88 |92.846|224 |3.7 |0.58 |4.11 |7963.16 |256 |
| [convnext_atto.d2_in1k](https://huggingface.co/timm/convnext_atto.d2_in1k) |75.664|92.9 |224 |3.7 |0.55 |3.81 |8439.22 |256 |
## Citation
```bibtex
@article{Woo2023ConvNeXtV2,
title={ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders},
author={Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon and Saining Xie},
year={2023},
journal={arXiv preprint arXiv:2301.00808},
}
```
```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}}
}
```
|
timm/swinv2_small_window16_256.ms_in1k | timm | "2024-02-10T23:31:11Z" | 1,007 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2111.09883",
"license:mit",
"region:us"
] | image-classification | "2023-03-18T03:36:57Z" | ---
license: mit
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
---
# Model card for swinv2_small_window16_256.ms_in1k
A Swin Transformer V2 image classification model. Pretrained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 49.7
- GMACs: 12.8
- Activations (M): 66.3
- Image size: 256 x 256
- **Papers:**
- Swin Transformer V2: Scaling Up Capacity and Resolution: https://arxiv.org/abs/2111.09883
- **Original:** https://github.com/microsoft/Swin-Transformer
- **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('swinv2_small_window16_256.ms_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(
'swinv2_small_window16_256.ms_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. for swin_base_patch4_window7_224 (NHWC output)
# torch.Size([1, 56, 56, 128])
# torch.Size([1, 28, 28, 256])
# torch.Size([1, 14, 14, 512])
# torch.Size([1, 7, 7, 1024])
# e.g. for swinv2_cr_small_ns_224 (NCHW output)
# torch.Size([1, 96, 56, 56])
# torch.Size([1, 192, 28, 28])
# torch.Size([1, 384, 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(
'swinv2_small_window16_256.ms_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 (ie.e a (batch_size, H, W, num_features) tensor for swin / swinv2
# or (batch_size, num_features, H, W) for swinv2_cr
output = model.forward_head(output, pre_logits=True)
# output is (batch_size, num_features) 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{liu2021swinv2,
title={Swin Transformer V2: Scaling Up Capacity and Resolution},
author={Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
booktitle={International Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2022}
}
```
```bibtex
@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}}
}
```
|
Quake24/easyTermsSummerizer | Quake24 | "2023-04-22T11:15:07Z" | 1,007 | 1 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"bart",
"text2text-generation",
"summarization",
"generated_from_trainer",
"en",
"dataset:Quake24/paraphrasedPayPal",
"dataset:Quake24/paraphrasedTwitter",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | summarization | "2023-04-22T11:05:20Z" | ---
license: apache-2.0
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: easyTermsSummerizer
results: []
datasets:
- Quake24/paraphrasedPayPal
- Quake24/paraphrasedTwitter
language:
- en
library_name: transformers
---
<!-- 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. -->
# easyTermsSummerizer
This model is a fine-tuned version of [sshleifer/distilbart-cnn-12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8124
- Rouge1: 0.7533
- Rouge2: 0.6964
- Rougel: 0.6806
- Rougelsum: 0.6793
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
| No log | 1.0 | 2 | 2.2083 | 0.7332 | 0.6595 | 0.6374 | 0.6376 |
| No log | 2.0 | 4 | 1.9331 | 0.7776 | 0.7268 | 0.6991 | 0.7005 |
| No log | 3.0 | 6 | 1.8124 | 0.7533 | 0.6964 | 0.6806 | 0.6793 |
### Framework versions
- Transformers 4.27.3
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2 |
digiplay/fantexi_v0.9 | digiplay | "2023-10-01T00:48:08Z" | 1,007 | 1 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-08-20T16:51:06Z" | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/131601?modelVersionId=144665
|
Labbeti/conette | Labbeti | "2023-11-09T16:50:29Z" | 1,007 | 0 | transformers | [
"transformers",
"pytorch",
"audio",
"captioning",
"text",
"audio-captioning",
"automated-audio-captioning",
"en",
"arxiv:2309.00454",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | "2023-09-26T16:51:40Z" | ---
language: en
license: mit
tags:
- audio
- captioning
- text
- audio-captioning
- automated-audio-captioning
model_name: CoNeTTE
task_categories:
- audio-captioning
---
<div align="center">
# CoNeTTE model for Audio Captioning
</div>
CoNeTTE is an audio captioning system, which generate a short textual description of the sound events in any audio file. The architecture and training are explained in the corresponding [paper](https://arxiv.org/pdf/2309.00454.pdf). The model has been developped by me ([Étienne Labbé](https://labbeti.github.io/)) during my PhD.
## Installation
```bash
python -m pip install conette
```
## Usage with python
```py
from conette import CoNeTTEConfig, CoNeTTEModel
config = CoNeTTEConfig.from_pretrained("Labbeti/conette")
model = CoNeTTEModel.from_pretrained("Labbeti/conette", config=config)
path = "/your/path/to/audio.wav"
outputs = model(path)
candidate = outputs["cands"][0]
print(candidate)
```
The model can also accept several audio files at the same time (list[str]), or a list of pre-loaded audio files (list[Tensor]). In this second case you also need to provide the sampling rate of this files:
```py
import torchaudio
path_1 = "/your/path/to/audio_1.wav"
path_2 = "/your/path/to/audio_2.wav"
audio_1, sr_1 = torchaudio.load(path_1)
audio_2, sr_2 = torchaudio.load(path_2)
outputs = model([audio_1, audio_2], sr=[sr_1, sr_2])
candidates = outputs["cands"]
print(candidates)
```
The model can also produces different captions using a Task Embedding input which indicates the dataset caption style. The default task is "clotho".
```py
outputs = model(path, task="clotho")
candidate = outputs["cands"][0]
print(candidate)
outputs = model(path, task="audiocaps")
candidate = outputs["cands"][0]
print(candidate)
```
## Usage with command line
Simply use the command `conette-predict` with `--audio PATH1 PATH2 ...` option. You can also export results to a CSV file using `--csv_export PATH`.
```bash
conette-predict --audio "/your/path/to/audio.wav"
```
## Performance
| Test data | SPIDEr (%) | SPIDEr-FL (%) | FENSE (%) | Vocab | Outputs | Scores |
| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |
| AC-test | 44.14 | 43.98 | 60.81 | 309 | [Link](https://github.com/Labbeti/conette-audio-captioning/blob/main/results/conette/outputs_audiocaps_test.csv) | [Link](https://github.com/Labbeti/conette-audio-captioning/blob/main/results/conette/scores_audiocaps_test.yaml) |
| CL-eval | 30.97 | 30.87 | 51.72 | 636 | [Link](https://github.com/Labbeti/conette-audio-captioning/blob/main/results/conette/outputs_clotho_eval.csv) | [Link](https://github.com/Labbeti/conette-audio-captioning/blob/main/results/conette/scores_clotho_eval.yaml) |
This model checkpoint has been trained for the Clotho dataset, but it can also reach a good performance on AudioCaps with the "audiocaps" task.
## Limitations
- The model expected audio sampled at 32 kHz. The model automatically resample up or down the input audio files. However, it might give worse results, especially when using audio with lower sampling rates.
- The model has been trained on audio lasting from 1 to 30 seconds. It can handle longer audio files, but it might require more memory and give worse results.
## Citation
The preprint version of the paper describing CoNeTTE is available on arxiv: https://arxiv.org/pdf/2309.00454.pdf
```bibtex
@misc{labbé2023conette,
title = {CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding},
author = {Étienne Labbé and Thomas Pellegrini and Julien Pinquier},
year = 2023,
journal = {arXiv preprint arXiv:2309.00454},
url = {https://arxiv.org/pdf/2309.00454.pdf},
eprint = {2309.00454},
archiveprefix = {arXiv},
primaryclass = {cs.SD}
}
```
## Additional information
- CoNeTTE stands for **Co**nv**Ne**Xt-**T**ransformer with **T**ask **E**mbedding.
- Model weights are available on HuggingFace: https://huggingface.co/Labbeti/conette
- The encoder part of the architecture is based on a ConvNeXt model for audio classification, available here: https://huggingface.co/topel/ConvNeXt-Tiny-AT. More precisely, the encoder weights used are named "convnext_tiny_465mAP_BL_AC_70kit.pth", available on Zenodo: https://zenodo.org/record/8020843.
## Contact
Maintainer:
- Etienne Labbé "Labbeti": [email protected] |
AIGym/deepseek-coder-1.3b-chat | AIGym | "2024-03-04T17:17:29Z" | 1,007 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"finetuned",
"conversational",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-04T21:37:03Z" | ---
license: apache-2.0
tags:
- finetuned
pipeline_tag: text-generation
model-index:
- name: deepseek-coder-1.3b-chat
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: 25.85
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat
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: 39.59
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat
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: 26.36
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat
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: 43.92
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat
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: 51.7
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat
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: 3.03
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat
name: Open LLM Leaderboard
---
# deepseek-coder-1.3b-chat
It was created by starting with the deepseek-coder-1.3b and training it on the open assistant dataset. We have attached the wandb report in pdf form to view the training run at a glance.
# Reson
This model was fine tned to allow it to follow direction and is a steeping stone to further training, but still would be good for asking qestions about code.
# How to use
You will need the transformers>=4.31
```python
from transformers import AutoTokenizer
import transformers
import torch
model = "AIGym/deepseek-coder-1.3b-chat"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
prompt = "What are the values in open source projects?"
formatted_prompt = (
f"### Human: {prompt}### Assistant:"
)
sequences = pipeline(
formatted_prompt,
do_sample=True,
top_k=50,
top_p = 0.7,
num_return_sequences=1,
repetition_penalty=1.1,
max_new_tokens=500,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
# Referrals
Run Pod - This is who I use to train th emodels on huggingface. If you use it we both get free crdits. - <a href="https://runpod.io?ref=kilq83n1" target="_blank" style="color: #3498db; text-decoration: none; font-weight: bold;">Visit Runpod's Website!</a>
Paypal - If you want to leave a tip, it is appecaheted. - <a href="https://paypal.me/OpenSourceTraining" target="_blank" style="color: #3498db; text-decoration: none; font-weight: bold;">Visit My Paypal!</a>
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_AIGym__deepseek-coder-1.3b-chat)
| Metric |Value|
|---------------------------------|----:|
|Avg. |31.74|
|AI2 Reasoning Challenge (25-Shot)|25.85|
|HellaSwag (10-Shot) |39.59|
|MMLU (5-Shot) |26.36|
|TruthfulQA (0-shot) |43.92|
|Winogrande (5-shot) |51.70|
|GSM8k (5-shot) | 3.03|
|
fhai50032/xLakeChat | fhai50032 | "2024-03-04T12:50:58Z" | 1,007 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"xDAN-AI/xDAN-L1-Chat-RL-v1",
"fhai50032/BeagleLake-7B-Toxic",
"base_model:xDAN-AI/xDAN-L1-Chat-RL-v1",
"base_model:fhai50032/BeagleLake-7B-Toxic",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-11T02:43:39Z" | ---
license: apache-2.0
tags:
- merge
- mergekit
- mistral
- xDAN-AI/xDAN-L1-Chat-RL-v1
- fhai50032/BeagleLake-7B-Toxic
base_model:
- xDAN-AI/xDAN-L1-Chat-RL-v1
- fhai50032/BeagleLake-7B-Toxic
model-index:
- name: xLakeChat
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: 62.37
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
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: 82.64
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
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: 59.32
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
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: 52.96
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
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: 74.74
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
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: 50.27
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
name: Open LLM Leaderboard
---
# xLakeChat
xLakeChat is a merge of the following models
* [xDAN-AI/xDAN-L1-Chat-RL-v1](https://huggingface.co/xDAN-AI/xDAN-L1-Chat-RL-v1)
* [fhai50032/BeagleLake-7B-Toxic](https://huggingface.co/fhai50032/BeagleLake-7B-Toxic)
## 🧩 Configuration
```yaml
models:
- model: senseable/WestLake-7B-v2
# no params for base model
- model: xDAN-AI/xDAN-L1-Chat-RL-v1
parameters:
weight: 0.73
density: 0.64
- model: fhai50032/BeagleLake-7B-Toxic
parameters:
weight: 0.46
density: 0.55
merge_method: dare_ties
base_model: senseable/WestLake-7B-v2
parameters:
normalize: true
int8_mask: true
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "fhai50032/xLakeChat"
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"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_fhai50032__xLakeChat)
| Metric |Value|
|---------------------------------|----:|
|Avg. |63.72|
|AI2 Reasoning Challenge (25-Shot)|62.37|
|HellaSwag (10-Shot) |82.64|
|MMLU (5-Shot) |59.32|
|TruthfulQA (0-shot) |52.96|
|Winogrande (5-shot) |74.74|
|GSM8k (5-shot) |50.27|
|
macadeliccc/Monarch-7B-SFT | macadeliccc | "2024-03-04T19:21:02Z" | 1,007 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-21T20:54:07Z" | ---
license: apache-2.0
model-index:
- name: Monarch-7B-SFT
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: 63.74
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Monarch-7B-SFT
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: 83.58
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Monarch-7B-SFT
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: 64.11
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Monarch-7B-SFT
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: 54.25
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Monarch-7B-SFT
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: 79.79
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Monarch-7B-SFT
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: 68.39
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Monarch-7B-SFT
name: Open LLM Leaderboard
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **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]
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_macadeliccc__Monarch-7B-SFT)
| Metric |Value|
|---------------------------------|----:|
|Avg. |68.98|
|AI2 Reasoning Challenge (25-Shot)|63.74|
|HellaSwag (10-Shot) |83.58|
|MMLU (5-Shot) |64.11|
|TruthfulQA (0-shot) |54.25|
|Winogrande (5-shot) |79.79|
|GSM8k (5-shot) |68.39|
|
fhai50032/RP-Coder-SM3 | fhai50032 | "2024-03-10T06:13:05Z" | 1,007 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-09T19:59:50Z" | ---
library_name: transformers
license: apache-2.0
---
# 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] |
axxd/wizardllama-7b | axxd | "2024-03-23T08:54:23Z" | 1,007 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"code",
"base_model:codellama/CodeLlama-7b-Python-hf",
"base_model:WizardLM/WizardCoder-Python-7B-V1.0",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-23T08:34:23Z" | ---
base_model:
- codellama/CodeLlama-7b-Python-hf
- WizardLM/WizardCoder-Python-7B-V1.0
library_name: transformers
tags:
- mergekit
- merge
- code
license: apache-2.0
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf)
* [WizardLM/WizardCoder-Python-7B-V1.0](https://huggingface.co/WizardLM/WizardCoder-Python-7B-V1.0)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: WizardLM/WizardCoder-Python-7B-V1.0
layer_range: [0, 32]
- model: codellama/CodeLlama-7b-Python-hf
layer_range: [0, 32]
merge_method: slerp
base_model: codellama/CodeLlama-7b-Python-hf
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
``` |
jambroz/sixtyoneeighty-7b | jambroz | "2024-04-05T11:48:00Z" | 1,007 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:Intel/neural-chat-7b-v3-1",
"base_model:mlabonne/AlphaMonarch-7B",
"base_model:HuggingFaceH4/zephyr-7b-beta",
"base_model:mlabonne/NeuralBeagle14-7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-05T08:35:32Z" | ---
base_model:
- Intel/neural-chat-7b-v3-1
- mlabonne/AlphaMonarch-7B
- HuggingFaceH4/zephyr-7b-beta
- mlabonne/NeuralBeagle14-7B
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B) as a base.
### Models Merged
The following models were included in the merge:
* [Intel/neural-chat-7b-v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1)
* [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
* [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: mlabonne/NeuralBeagle14-7B
dtype: bfloat16
merge_method: dare_ties
models:
- model: mlabonne/NeuralBeagle14-7B
- model: mlabonne/AlphaMonarch-7B
parameters:
density: '0.53'
weight: '0.4'
- model: Intel/neural-chat-7b-v3-1
parameters:
density: '0.53'
weight: '0.3'
- model: HuggingFaceH4/zephyr-7b-beta
parameters:
density: '0.53'
weight: '0.3'
parameters:
int8_mask: true
``` |
SlavicNLP/slavicner-ner-cross-topic-large | SlavicNLP | "2024-05-22T20:06:35Z" | 1,007 | 1 | transformers | [
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"ner",
"named entity recognition",
"multilingual",
"pl",
"ru",
"uk",
"bg",
"cs",
"sl",
"dataset:SlavicNER",
"arxiv:2404.00482",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | "2024-05-14T19:00:50Z" | ---
language:
- multilingual
- pl
- ru
- uk
- bg
- cs
- sl
datasets:
- SlavicNER
license: apache-2.0
library_name: transformers
pipeline_tag: token-classification
tags:
- ner
- named entity recognition
widget:
- text: "Nie jest za późno, aby powstrzymać Brexit, a Wielka Brytania wciąż może zmienić zdanie - powiedział przewodniczący Rady Europejskiej eurodeputowanym w Strasburgu."
example_title: Polish
- text: "„Musíme mluvit o sektorových a také ekonomických sankcích,“ řekl při příchodu na Evropskou radu litevský prezident Gitanas Nauseda."
example_title: Czech
- text: "Президентските избори в САЩ през 2016 г. със сигурност ще останат в историята. Не само защото Доналд Тръмп, личност без какъвто и да е опит на обществени длъжности, надви един от най-добре подготвените кандидати в историята – бившата първа дама, сенаторка и държавна секретарка Хилъри Клинтън, но и защото кампанията преди вота се отличи с безпрецедентен тон, тематика и идеи, които заеха основно място по време на дебата."
example_title: Bulgarian
- text: "По словам министра здравоохранения Светланы Леонтьевой, вакцинация против новой коронавирусной инфекции проходит примерно так же, как и ежегодная сезонная вакцинация против гриппа. В Приамурье используется два вида вакцины — «Гам-Ковид-Вак» и «ЭпиВакКорона», которые имеют разный принцип действия, но одинаково эффективны. Привить планируется 60 процентов взрослого населения, или более 300 тысяч амурчан. "
example_title: Russian
- text: "Poslanci so najprej s 296 glasovi za in 327 glasovi proti zavrnili dopolnilo vodje opozicijski laburistov Jeremya Corbyna, s katerimi je želel preprečiti brexit brez dogovora."
example_title: Slovene
- text: "У Пакистані християнка Азія Бібі, яку Верховний суд днями виправдав та скасував їй смертний вирок за богохульство, досі залишається за ґратами. Ми чекаємо на інструкції від Верховного суду. Азія Бібі перебуває у в'язниці, точне місце її розташування не може бути розкрито з міркувань безпеки, - повідомив в коментарі DW голова в'язниці в провінції Пенджаб Салім Баіг."
example_title: Ukrainian
---
# Model description
This is a baseline model for named entity **recognition** trained on the cross-topic split of the
[SlavicNER corpus](https://github.com/SlavicNLP/SlavicNER).
# Resources and Technical Documentation
- Paper: [Cross-lingual Named Entity Corpus for Slavic Languages](https://arxiv.org/pdf/2404.00482), to appear in LREC-COLING 2024.
- Annotation guidelines: https://arxiv.org/pdf/2404.00482
- SlavicNER Corpus: https://github.com/SlavicNLP/SlavicNER
# Evaluation
*Will appear soon*
# Usage
```python
from transformers import pipeline
model = "SlavicNLP/slavicner-ner-cross-topic-large"
text = """Nie jest za późno, aby powstrzymać Brexit, a Wielka Brytania wciąż
może zmienić zdanie - powiedział przewodniczący Rady Europejskiej
eurodeputowanym w Strasburgu"""
pipe = pipeline("ner", model, aggregation_strategy="simple")
entities = pipe(text)
print(*entities, sep="\n")
# {'entity_group': 'EVT', 'score': 0.99720407, 'word': 'Brexit', 'start': 35, 'end': 41}
# {'entity_group': 'LOC', 'score': 0.9656372, 'word': 'Wielka Brytania', 'start': 45, 'end': 60}
# {'entity_group': 'ORG', 'score': 0.9977708, 'word': 'Rady Europejskiej', 'start': 115, 'end': 132}
# {'entity_group': 'LOC', 'score': 0.95184135, 'word': 'Strasburgu', 'start': 151, 'end': 161}
```
# Citation
```latex
@inproceedings{piskorski-etal-2024-cross-lingual,
title = "Cross-lingual Named Entity Corpus for {S}lavic Languages",
author = "Piskorski, Jakub and
Marci{\'n}czuk, Micha{\l} and
Yangarber, Roman",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italy",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.369",
pages = "4143--4157",
abstract = "This paper presents a corpus manually annotated with named entities for six Slavic languages {---} Bulgarian, Czech, Polish, Slovenian, Russian,
and Ukrainian. This work is the result of a series of shared tasks, conducted in 2017{--}2023 as a part of the Workshops on Slavic Natural
Language Processing. The corpus consists of 5,017 documents on seven topics. The documents are annotated with five classes of named entities.
Each entity is described by a category, a lemma, and a unique cross-lingual identifier. We provide two train-tune dataset splits
{---} single topic out and cross topics. For each split, we set benchmarks using a transformer-based neural network architecture
with the pre-trained multilingual models {---} XLM-RoBERTa-large for named entity mention recognition and categorization,
and mT5-large for named entity lemmatization and linking.",
}
```
# Contact
Michał Marcińczuk ([email protected]) |
nllg/detikzify-ds-7b | nllg | "2024-05-17T21:39:55Z" | 1,007 | 3 | transformers | [
"transformers",
"safetensors",
"detikzify",
"text-generation",
"dataset:nllg/datikz-v2",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-05-15T07:13:36Z" | ---
license: other
license_name: deepseek
license_link: >-
https://raw.githubusercontent.com/deepseek-ai/DeepSeek-Coder/main/LICENSE-MODEL
datasets:
- nllg/datikz-v2
---
# Model Card for DeTi*k*Zify-DS<sub>7b</sub>
DeTi*k*Zify-DS<sub>1.3b</sub> is a language model that automatically converts
sketches and existing scientific figures into editable, semantics-preserving
Ti*k*Z graphics programs. It is based on [DeepSeek Coder 7b
v1.5](https://huggingface.co/deepseek-ai/deepseek-coder-7b-base-v1.5) and was
fine-tuned on
[DaTi*k*Z<sub>v2</sub>](https://huggingface.co/datasets/nllg/datikz-v2). Check
out the [DeTi*k*Zify](https://github.com/potamides/DeTikZify) project for more
information and tips on how to best run the model.
## Usage
```python
from operator import itemgetter
from detikzify.model import load
from detikzify.infer import DetikzifyPipeline
import torch
image = "https://w.wiki/A7Cc"
pipeline = DetikzifyPipeline(*load(
base_model="nllg/detikzify-ds-7b",
device_map="auto",
torch_dtype=torch.bfloat16,
))
# generate a single TikZ program
fig = pipeline.sample(image=image)
# if it compiles, rasterize it and show it
if fig.is_rasterizable:
fig.rasterize().show()
# run MCTS for 10 minutes and generate multiple TikZ programs
figs = set()
for score, fig in pipeline.simulate(image=image, timeout=600):
figs.add((score, fig))
# save the best TikZ program
best = sorted(figs, key=itemgetter(0))[-1][1]
best.save("fig.tex")
``` |
hallisky/voice-classifier-gpt4-data | hallisky | "2024-05-19T19:01:00Z" | 1,007 | 0 | transformers | [
"transformers",
"safetensors",
"roberta",
"text-classification",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2024-05-19T18:52:37Z" | ---
license: apache-2.0
---
|
rwitz2/empty-phi-3-mini | rwitz2 | "2024-06-01T19:46:37Z" | 1,007 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-06-01T19:40:22Z" | ---
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] |
NikolayKozloff/Trendyol-LLM-7b-chat-v1.8-IQ4_NL-GGUF | NikolayKozloff | "2024-06-29T12:10:23Z" | 1,007 | 1 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"tr",
"base_model:Trendyol/Trendyol-LLM-7b-chat-v1.8",
"license:apache-2.0",
"region:us"
] | text-generation | "2024-06-29T12:10:05Z" | ---
base_model: Trendyol/Trendyol-LLM-7b-chat-v1.8
language:
- tr
license: apache-2.0
pipeline_tag: text-generation
tags:
- llama-cpp
- gguf-my-repo
---
# NikolayKozloff/Trendyol-LLM-7b-chat-v1.8-IQ4_NL-GGUF
This model was converted to GGUF format from [`Trendyol/Trendyol-LLM-7b-chat-v1.8`](https://huggingface.co/Trendyol/Trendyol-LLM-7b-chat-v1.8) 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/Trendyol/Trendyol-LLM-7b-chat-v1.8) 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/Trendyol-LLM-7b-chat-v1.8-IQ4_NL-GGUF --hf-file trendyol-llm-7b-chat-v1.8-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo NikolayKozloff/Trendyol-LLM-7b-chat-v1.8-IQ4_NL-GGUF --hf-file trendyol-llm-7b-chat-v1.8-iq4_nl-imat.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/Trendyol-LLM-7b-chat-v1.8-IQ4_NL-GGUF --hf-file trendyol-llm-7b-chat-v1.8-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo NikolayKozloff/Trendyol-LLM-7b-chat-v1.8-IQ4_NL-GGUF --hf-file trendyol-llm-7b-chat-v1.8-iq4_nl-imat.gguf -c 2048
```
|
timm/convnext_tiny.in12k | timm | "2024-02-10T23:29:44Z" | 1,006 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-12k",
"arxiv:2201.03545",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-01-11T22:35:12Z" | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-12k
---
# Model card for convnext_tiny.in12k
A ConvNeXt image classification model. Trained in `timm` on ImageNet-12k (a 11821 class subset of full ImageNet-22k) by Ross Wightman.
ImageNet-12k training done on TPUs thanks to support of the [TRC](https://sites.research.google/trc/about/) program.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 36.9
- GMACs: 4.5
- Activations (M): 13.4
- Image size: 224 x 224
- **Papers:**
- A ConvNet for the 2020s: https://arxiv.org/abs/2201.03545
- **Original:** https://github.com/huggingface/pytorch-image-models
- **Dataset:** ImageNet-12k
## 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('convnext_tiny.in12k', 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(
'convnext_tiny.in12k',
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, 96, 56, 56])
# torch.Size([1, 192, 28, 28])
# torch.Size([1, 384, 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(
'convnext_tiny.in12k',
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).
All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
| model |top1 |top5 |img_size|param_count|gmacs |macts |samples_per_sec|batch_size|
|------------------------------------------------------------------------------------------------------------------------------|------|------|--------|-----------|------|------|---------------|----------|
| [convnextv2_huge.fcmae_ft_in22k_in1k_512](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_512) |88.848|98.742|512 |660.29 |600.81|413.07|28.58 |48 |
| [convnextv2_huge.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_384) |88.668|98.738|384 |660.29 |337.96|232.35|50.56 |64 |
| [convnext_xxlarge.clip_laion2b_soup_ft_in1k](https://huggingface.co/timm/convnext_xxlarge.clip_laion2b_soup_ft_in1k) |88.612|98.704|256 |846.47 |198.09|124.45|122.45 |256 |
| [convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384) |88.312|98.578|384 |200.13 |101.11|126.74|196.84 |256 |
| [convnextv2_large.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k_384) |88.196|98.532|384 |197.96 |101.1 |126.74|128.94 |128 |
| [convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320) |87.968|98.47 |320 |200.13 |70.21 |88.02 |283.42 |256 |
| [convnext_xlarge.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k_384) |87.75 |98.556|384 |350.2 |179.2 |168.99|124.85 |192 |
| [convnextv2_base.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k_384) |87.646|98.422|384 |88.72 |45.21 |84.49 |209.51 |256 |
| [convnext_large.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k_384) |87.476|98.382|384 |197.77 |101.1 |126.74|194.66 |256 |
| [convnext_large_mlp.clip_laion2b_augreg_ft_in1k](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_augreg_ft_in1k) |87.344|98.218|256 |200.13 |44.94 |56.33 |438.08 |256 |
| [convnextv2_large.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k) |87.26 |98.248|224 |197.96 |34.4 |43.13 |376.84 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384) |87.138|98.212|384 |88.59 |45.21 |84.49 |365.47 |256 |
| [convnext_xlarge.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k) |87.002|98.208|224 |350.2 |60.98 |57.5 |368.01 |256 |
| [convnext_base.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k_384) |86.796|98.264|384 |88.59 |45.21 |84.49 |366.54 |256 |
| [convnextv2_base.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k) |86.74 |98.022|224 |88.72 |15.38 |28.75 |624.23 |256 |
| [convnext_large.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k) |86.636|98.028|224 |197.77 |34.4 |43.13 |581.43 |256 |
| [convnext_base.clip_laiona_augreg_ft_in1k_384](https://huggingface.co/timm/convnext_base.clip_laiona_augreg_ft_in1k_384) |86.504|97.97 |384 |88.59 |45.21 |84.49 |368.14 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in12k_in1k](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k) |86.344|97.97 |256 |88.59 |20.09 |37.55 |816.14 |256 |
| [convnextv2_huge.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in1k) |86.256|97.75 |224 |660.29 |115.0 |79.07 |154.72 |256 |
| [convnext_small.in12k_ft_in1k_384](https://huggingface.co/timm/convnext_small.in12k_ft_in1k_384) |86.182|97.92 |384 |50.22 |25.58 |63.37 |516.19 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in1k](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in1k) |86.154|97.68 |256 |88.59 |20.09 |37.55 |819.86 |256 |
| [convnext_base.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k) |85.822|97.866|224 |88.59 |15.38 |28.75 |1037.66 |256 |
| [convnext_small.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k_384) |85.778|97.886|384 |50.22 |25.58 |63.37 |518.95 |256 |
| [convnextv2_large.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in1k) |85.742|97.584|224 |197.96 |34.4 |43.13 |375.23 |256 |
| [convnext_small.in12k_ft_in1k](https://huggingface.co/timm/convnext_small.in12k_ft_in1k) |85.174|97.506|224 |50.22 |8.71 |21.56 |1474.31 |256 |
| [convnext_tiny.in12k_ft_in1k_384](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k_384) |85.118|97.608|384 |28.59 |13.14 |39.48 |856.76 |256 |
| [convnextv2_tiny.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k_384) |85.112|97.63 |384 |28.64 |13.14 |39.48 |491.32 |256 |
| [convnextv2_base.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in1k) |84.874|97.09 |224 |88.72 |15.38 |28.75 |625.33 |256 |
| [convnext_small.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k) |84.562|97.394|224 |50.22 |8.71 |21.56 |1478.29 |256 |
| [convnext_large.fb_in1k](https://huggingface.co/timm/convnext_large.fb_in1k) |84.282|96.892|224 |197.77 |34.4 |43.13 |584.28 |256 |
| [convnext_tiny.in12k_ft_in1k](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k) |84.186|97.124|224 |28.59 |4.47 |13.44 |2433.7 |256 |
| [convnext_tiny.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k_384) |84.084|97.14 |384 |28.59 |13.14 |39.48 |862.95 |256 |
| [convnextv2_tiny.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k) |83.894|96.964|224 |28.64 |4.47 |13.44 |1452.72 |256 |
| [convnext_base.fb_in1k](https://huggingface.co/timm/convnext_base.fb_in1k) |83.82 |96.746|224 |88.59 |15.38 |28.75 |1054.0 |256 |
| [convnextv2_nano.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k_384) |83.37 |96.742|384 |15.62 |7.22 |24.61 |801.72 |256 |
| [convnext_small.fb_in1k](https://huggingface.co/timm/convnext_small.fb_in1k) |83.142|96.434|224 |50.22 |8.71 |21.56 |1464.0 |256 |
| [convnextv2_tiny.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in1k) |82.92 |96.284|224 |28.64 |4.47 |13.44 |1425.62 |256 |
| [convnext_tiny.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k) |82.898|96.616|224 |28.59 |4.47 |13.44 |2480.88 |256 |
| [convnext_nano.in12k_ft_in1k](https://huggingface.co/timm/convnext_nano.in12k_ft_in1k) |82.282|96.344|224 |15.59 |2.46 |8.37 |3926.52 |256 |
| [convnext_tiny_hnf.a2h_in1k](https://huggingface.co/timm/convnext_tiny_hnf.a2h_in1k) |82.216|95.852|224 |28.59 |4.47 |13.44 |2529.75 |256 |
| [convnext_tiny.fb_in1k](https://huggingface.co/timm/convnext_tiny.fb_in1k) |82.066|95.854|224 |28.59 |4.47 |13.44 |2346.26 |256 |
| [convnextv2_nano.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k) |82.03 |96.166|224 |15.62 |2.46 |8.37 |2300.18 |256 |
| [convnextv2_nano.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in1k) |81.83 |95.738|224 |15.62 |2.46 |8.37 |2321.48 |256 |
| [convnext_nano_ols.d1h_in1k](https://huggingface.co/timm/convnext_nano_ols.d1h_in1k) |80.866|95.246|224 |15.65 |2.65 |9.38 |3523.85 |256 |
| [convnext_nano.d1h_in1k](https://huggingface.co/timm/convnext_nano.d1h_in1k) |80.768|95.334|224 |15.59 |2.46 |8.37 |3915.58 |256 |
| [convnextv2_pico.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_pico.fcmae_ft_in1k) |80.304|95.072|224 |9.07 |1.37 |6.1 |3274.57 |256 |
| [convnext_pico.d1_in1k](https://huggingface.co/timm/convnext_pico.d1_in1k) |79.526|94.558|224 |9.05 |1.37 |6.1 |5686.88 |256 |
| [convnext_pico_ols.d1_in1k](https://huggingface.co/timm/convnext_pico_ols.d1_in1k) |79.522|94.692|224 |9.06 |1.43 |6.5 |5422.46 |256 |
| [convnextv2_femto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_femto.fcmae_ft_in1k) |78.488|93.98 |224 |5.23 |0.79 |4.57 |4264.2 |256 |
| [convnext_femto_ols.d1_in1k](https://huggingface.co/timm/convnext_femto_ols.d1_in1k) |77.86 |93.83 |224 |5.23 |0.82 |4.87 |6910.6 |256 |
| [convnext_femto.d1_in1k](https://huggingface.co/timm/convnext_femto.d1_in1k) |77.454|93.68 |224 |5.22 |0.79 |4.57 |7189.92 |256 |
| [convnextv2_atto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_atto.fcmae_ft_in1k) |76.664|93.044|224 |3.71 |0.55 |3.81 |4728.91 |256 |
| [convnext_atto_ols.a2_in1k](https://huggingface.co/timm/convnext_atto_ols.a2_in1k) |75.88 |92.846|224 |3.7 |0.58 |4.11 |7963.16 |256 |
| [convnext_atto.d2_in1k](https://huggingface.co/timm/convnext_atto.d2_in1k) |75.664|92.9 |224 |3.7 |0.55 |3.81 |8439.22 |256 |
## 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{liu2022convnet,
author = {Zhuang Liu and Hanzi Mao and Chao-Yuan Wu and Christoph Feichtenhofer and Trevor Darrell and Saining Xie},
title = {A ConvNet for the 2020s},
journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2022},
}
```
|
filipealmeida/open-llama-3b-v2-pii-transform | filipealmeida | "2023-09-19T07:39:45Z" | 1,006 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gguf",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-31T02:27:12Z" | ---
license: apache-2.0
widget:
- text: "### Instruction:\nMy name is Filipe and my phone number is 555-121-2234. How are you?\n### Response:\n"
example_title: "Example 1"
---
# Open Llama based PII anonymizer
## Description
This model, based on the `openlm-research/open_llama_3b_v2` architecture, is designed to automatically anonymize personal identifiable information (PII) from text data. Given a piece of text, the model can replace specific details such as names, addresses, dates, and other personal details with generic or randomized alternatives, thereby safeguarding the privacy of individuals while retaining the overall context of the text.
## Disclaimer
This model is an experiment and, while it strives to maintain privacy, it may not capture or anonymize all instances of PII in every context. Users should always review and verify the output, especially when dealing with sensitive data. |
foduucom/stockmarket-future-prediction | foduucom | "2023-10-07T06:35:04Z" | 1,006 | 72 | ultralytics | [
"ultralytics",
"tensorboard",
"ultralyticsplus",
"yolov8",
"yolo",
"vision",
"object-detection",
"pytorch",
"finance",
"stock market",
"candlesticks",
"pattern recognition",
"option trading",
"chart reader",
"future stock prediction",
"trends prediction",
"en",
"model-index",
"region:us"
] | object-detection | "2023-09-27T09:35:59Z" | ---
tags:
- ultralyticsplus
- yolov8
- ultralytics
- yolo
- vision
- object-detection
- pytorch
- finance
- stock market
- candlesticks
- pattern recognition
- option trading
- chart reader
- future stock prediction
- trends prediction
library_name: ultralytics
library_version: 8.0.43
inference: false
model-index:
- name: foduucom/stockmarket-future-prediction
results:
- task:
type: object-detection
metrics:
- type: precision
value: 0.649
name: [email protected](box)
language:
- en
pipeline_tag: object-detection
---
<div align="center">
<img width="640" alt="foduucom/product-detection-in-shelf-yolov8" src="https://huggingface.co/foduucom/stockmarket-future-prediction/resolve/main/_Stockmarket-Future-Prediction.jpeg">
</div>
# Model Card for YOLOv8s Stock Market future trends prediction on Live Trading Video Data
## Model Summary
The YOLOv8s Stock Market future trends prediction model is an object detection model based on the YOLO (You Only Look Once) framework. It is designed to detect various chart patterns in real-time stock market trading video data. The model aids traders and investors by automating the analysis of chart patterns, providing timely insights for informed decision-making. The model has been fine-tuned on a diverse dataset and achieved high accuracy in detecting and classifying stock market future trend detection in live trading scenarios.
## Model Details
### Model Description
The YOLOv8s Stock Market future trends prediction model offers a transformative solution for traders and investors by enabling real-time detection of crucial chart patterns within live trading video data. As stock markets evolve rapidly, this model's capabilities empower users with timely insights, allowing them to make informed decisions with speed and accuracy.
The model seamlessly integrates into live trading systems, providing instant trends prediction and classification. By leveraging advanced bounding box techniques and pattern-specific feature extraction, the model excels in identifying patterns such as 'Down','Up'. This enables traders to optimize their strategies, automate trading decisions, and respond to market trends in real-time.
To facilitate integration into live trading systems or to inquire about customization, please contact us at [email protected]. Your collaboration and feedback are instrumental in refining and enhancing the model's performance in dynamic trading environments.
- **Developed by:** FODUU AI
- **Model type:** Object Detection
- **Task:** Stock Market future trends prediction on Live Trading Video Data
The YOLOv8s Stock Market Pattern Detection model is designed to adapt to the fast-paced nature of live trading environments. Its ability to operate on real-time video data allows traders and investors to harness pattern-based insights without delay.
### Supported Labels
```
['Down','Up']
```
## Uses
### Direct Use
The YOLOv8s Stock Market future trends prediction model can be directly integrated into live trading systems to provide real-time detection and classification of chart patterns or classify the upcoming trends. Traders can utilize the model's insights for timely decision-making.
### Downstream Use
The model's real-time capabilities can be leveraged to automate trading strategies, generate alerts for specific patterns or trends, and enhance overall trading performance.
### Out-of-Scope Use
The model is not designed for unrelated object detection tasks or scenarios outside the scope of stock market trends prediction in live trading video data.
## Bias, Risks, and Limitations
The YOLOv8s Stock Market future prediction model may exhibit some limitations and biases:
- Performance may be affected by variations in video quality, lighting conditions, and pattern complexity within live trading data.
- Rapid market fluctuations and noise in video data may impact the model's accuracy and responsiveness.
- Market-specific patterns or anomalies not well-represented in the training data may pose challenges for detection.
### Recommendations
Users should be aware of the model's limitations and potential biases. Thorough testing and validation within live trading simulations are advised before deploying the model in real trading environments.
## How to Get Started with the Model
To begin using the YOLOv8s Stock Market future prediction model on live trading video data, follow these steps:
```bash
pip install ultralyticsplus==0.0.28 ultralytics==8.0.43
```
- Load model and perform real-time prediction:
```python
from ultralyticsplus import YOLO, render_result
import cv2
# load model
model = YOLO('foduucom/stockmarket-future-prediction')
# set model parameters
model.overrides['conf'] = 0.25 # NMS confidence threshold
model.overrides['iou'] = 0.45 # NMS IoU threshold
model.overrides['agnostic_nms'] = False # NMS class-agnostic
model.overrides['max_det'] = 1000 # maximum number of detections per image
# set image
image = '/path/to/your/document/images'
# perform inference
results = model.predict(image)
# observe results
print(results[0].boxes)
render = render_result(model=model, image=image, result=results[0])
render.show()
```
## Training Details
### Training Data
The model is trained on a diverse dataset containing stock market chart images with various chart patterns, capturing different market conditions and scenarios.
### Training Procedure
The training process involves extensive computation and is conducted over multiple epochs. The model's weights are adjusted to minimize detection loss and optimize performance for stock market pattern detection.
#### Metrics
- [email protected] (box): 0.65
- All patterns: 0.90
- Individual patterns: Varies based on pattern type
### Model Architecture and Objective
The YOLOv8s architecture incorporates modifications tailored to stock market future prediction. It features a specialized backbone network, self-attention mechanisms, and trends-specific feature extraction modules.
### Compute Infrastructure
#### Hardware
NVIDIA GeForce RTX 3080 card
#### Software
The model was trained and fine-tuned using a Jupyter Notebook environment.
## Model Card Contact
For inquiries and contributions, please contact us at [email protected].
```bibtex
@ModelCard{
author = {Nehul Agrawal and
Rahul parihar},
title = {YOLOv8s Stock Market future prediction on Live Trading Video Data},
year = {2023}
}
``` |
TheBloke/Python-Code-33B-GGUF | TheBloke | "2023-11-14T21:45:23Z" | 1,006 | 3 | transformers | [
"transformers",
"gguf",
"llama",
"code",
"en",
"dataset:ajibawa-2023/Python-Code-23k-ShareGPT",
"base_model:ajibawa-2023/Python-Code-33B",
"license:other",
"text-generation-inference",
"region:us"
] | null | "2023-11-14T18:53:03Z" | ---
base_model: ajibawa-2023/Python-Code-33B
datasets:
- ajibawa-2023/Python-Code-23k-ShareGPT
inference: false
language:
- en
license: other
model_creator: Feynman Innovations
model_name: Python Code 33B
model_type: llama
prompt_template: 'This is a conversation with your helpful AI assistant. AI assistant
can generate Python Code along with necessary explanation.
Context
You are a helpful AI assistant.
USER: {prompt}
ASSISTANT:
'
quantized_by: TheBloke
tags:
- code
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Python Code 33B - GGUF
- Model creator: [Feynman Innovations](https://huggingface.co/ajibawa-2023)
- Original model: [Python Code 33B](https://huggingface.co/ajibawa-2023/Python-Code-33B)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Feynman Innovations's Python Code 33B](https://huggingface.co/ajibawa-2023/Python-Code-33B).
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/Python-Code-33B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Python-Code-33B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Python-Code-33B-GGUF)
* [Feynman Innovations's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ajibawa-2023/Python-Code-33B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Ajibawa-Python-Code
```
This is a conversation with your helpful AI assistant. AI assistant can generate Python Code along with necessary explanation.
Context
You are a helpful AI assistant.
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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [python-code-33b.Q2_K.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q2_K.gguf) | Q2_K | 2 | 13.50 GB| 16.00 GB | smallest, significant quality loss - not recommended for most purposes |
| [python-code-33b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q3_K_S.gguf) | Q3_K_S | 3 | 14.06 GB| 16.56 GB | very small, high quality loss |
| [python-code-33b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q3_K_M.gguf) | Q3_K_M | 3 | 15.76 GB| 18.26 GB | very small, high quality loss |
| [python-code-33b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q3_K_L.gguf) | Q3_K_L | 3 | 17.28 GB| 19.78 GB | small, substantial quality loss |
| [python-code-33b.Q4_0.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q4_0.gguf) | Q4_0 | 4 | 18.36 GB| 20.86 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [python-code-33b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q4_K_S.gguf) | Q4_K_S | 4 | 18.44 GB| 20.94 GB | small, greater quality loss |
| [python-code-33b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q4_K_M.gguf) | Q4_K_M | 4 | 19.62 GB| 22.12 GB | medium, balanced quality - recommended |
| [python-code-33b.Q5_0.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q5_0.gguf) | Q5_0 | 5 | 22.40 GB| 24.90 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [python-code-33b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q5_K_S.gguf) | Q5_K_S | 5 | 22.40 GB| 24.90 GB | large, low quality loss - recommended |
| [python-code-33b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q5_K_M.gguf) | Q5_K_M | 5 | 23.05 GB| 25.55 GB | large, very low quality loss - recommended |
| [python-code-33b.Q6_K.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q6_K.gguf) | Q6_K | 6 | 26.69 GB| 29.19 GB | very large, extremely low quality loss |
| [python-code-33b.Q8_0.gguf](https://huggingface.co/TheBloke/Python-Code-33B-GGUF/blob/main/python-code-33b.Q8_0.gguf) | Q8_0 | 8 | 34.57 GB| 37.07 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/Python-Code-33B-GGUF and below it, a specific filename to download, such as: python-code-33b.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/Python-Code-33B-GGUF python-code-33b.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/Python-Code-33B-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/Python-Code-33B-GGUF python-code-33b.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 python-code-33b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "This is a conversation with your helpful AI assistant. AI assistant can generate Python Code along with necessary explanation.\n\nContext\nYou are a helpful AI assistant.\n\nUSER: {prompt}\nASSISTANT:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 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/Python-Code-33B-GGUF", model_file="python-code-33b.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: Feynman Innovations's Python Code 33B
**Python-Code-33B**
Large Language Models (LLMs) are good with code generations. Sometimes LLMs do make mistakes in code generation. How about if they can give detailed explanation along with the code.
This is what I have tried over here. The base Llama-2 model was used for training purpose. It is trained on around 23000+ set of codes. Each set having 2 conversations.
This data was generated using GPT-3.5, GPT-4 etc. This conversation is in Vicuna/ShareGPT format. Each set, along with code, has detailed explanation.
I have released the [data](https://huggingface.co/datasets/ajibawa-2023/Python-Code-23k-ShareGPT).
**Training:**
Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 42 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.
**GPTQ GGML & AWQ**
GPTQ: TBA
GGUF: TBA
AWQ: TBA
**Example Prompt:**
```
This is a conversation with your helpful AI assistant. AI assistant can generate Python Code along with necessary explanation.
Context
You are a helpful AI assistant.
USER: <prompt>
ASSISTANT:
```
<!-- original-model-card end -->
|
dranger003/SFR-Embedding-Mistral-GGUF | dranger003 | "2024-02-18T15:16:23Z" | 1,006 | 14 | gguf | [
"gguf",
"sentence-similarity",
"license:cc-by-nc-4.0",
"region:us"
] | sentence-similarity | "2024-02-10T02:34:07Z" | ---
license: cc-by-nc-4.0
library_name: gguf
pipeline_tag: sentence-similarity
---
GGUF quants for https://huggingface.co/Salesforce/SFR-Embedding-Mistral
NOTE: This is a text embedding model used for feature extraction.
As of Feb. 9, 2024 this model is no. 1 on the MTEB leaderboard.
https://huggingface.co/spaces/mteb/leaderboard
I have an example of how to use llama.cpp to generate embeddings for sentence similarity on my repo:
https://github.com/dranger003/llama.cpp-dotnet
| Layers | Context | Template |
| --- | --- | --- |
| <pre>32</pre> | <pre>32768</pre> | <pre>Instruct: {task_description}<br>Query: {query}</pre> | |
digiplay/Yuzu_v1.1 | digiplay | "2024-02-27T19:26:40Z" | 1,006 | 1 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2024-02-27T18:08:51Z" | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info:
https://civitai.com/models/67120/yuzu
Sample images:
|
InferenceIllusionist/Magic-Dolphin-7b | InferenceIllusionist | "2024-03-17T15:13:25Z" | 1,006 | 4 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"code",
"arxiv:2203.05482",
"base_model:cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser",
"base_model:Locutusque/Hyperion-1.5-Mistral-7B",
"base_model:ibm/merlinite-7b",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-03T21:45:51Z" | ---
license: apache-2.0
base_model:
- cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
- Locutusque/Hyperion-1.5-Mistral-7B
- ibm/merlinite-7b
library_name: transformers
tags:
- mergekit
- merge
- code
model-index:
- name: Magic-Dolphin-7b
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: 65.78
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b
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: 85.61
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b
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: 64.64
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b
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: 58.01
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b
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: 79.64
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b
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: 51.18
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b
name: Open LLM Leaderboard
---
# Magic-Dolphin-7b
<img src="https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b/resolve/main/magic-dolphin.jfif" width="500"/>
<b>The follow-up to this model has been released, check out the updated benchmarks here for [Excalibur-7b](https://huggingface.co/InferenceIllusionist/Excalibur-7b)</b>
For GGUF files please look [here](https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b-GGUF)
A linear merge of:
- [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)
- [Locutusque/Hyperion-1.5-Mistral-7B](https://huggingface.co/Locutusque/Hyperion-1.5-Mistral-7B)
- [ibm/merlinite-7b](https://huggingface.co/ibm/merlinite-7b)
These three models showed excellent acumen in technical topics so I wanted to see how they would behave together in a merge. Several different ratios were tested before this release, in the end a higher weighting for merlinite-7b helped smooth out some edges. This model is a test of how LAB tuning is impacted by merges with models leveraging DPO.
### Benchmark Performance
| Name | Avg. | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
| <b>Magic-Dolphin-7b</b> | <u><b>67.48</b></u> | 65.78 | 85.61 | 64.64 | 58.01 | 79.64 | <u><b>51.18</b></u> |
| dolphin-2.6-mistral-7b-dpo-laser | 67.28 | 66.3 | 85.73 | 63.16 | 61.71 | 79.16 | 47.61 |
| merlinite-7b | 64 | 63.65 | 84.52 | 64.91 | 50.15 | 79.72 | 41.09 |
| Hyperion-1.5-Mistral-7B | 61.43 | 60.49 | 83.64 | 63.57 | 41.78 | 78.61 | 40.49 |
This was my first experiment with merging models so any feedback is greatly appreciated.
Uses Alpaca template.
<p align="center">
</p>
<b>Sample Question</b>
<img src="https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b/resolve/main/magic-dolphin.JPG" width="750"/>
## Merge Details
### Merge Method
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
### Models Merged
The following models were included in the merge:
* [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)
* [Locutusque/Hyperion-1.5-Mistral-7B](https://huggingface.co/Locutusque/Hyperion-1.5-Mistral-7B)
* [ibm/merlinite-7b](https://huggingface.co/ibm/merlinite-7b)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: models/dolphin-2.6-mistral-7b-dpo-laser
parameters:
weight: 1.0
- model: models/Hyperion-1.5-Mistral-7B
parameters:
weight: 0.3
- model: models/merlinite-7b
parameters:
weight: 0.5
merge_method: linear
dtype: float16
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_InferenceIllusionist__Magic-Dolphin-7b)
| Metric |Value|
|---------------------------------|----:|
|Avg. |67.48|
|AI2 Reasoning Challenge (25-Shot)|65.78|
|HellaSwag (10-Shot) |85.61|
|MMLU (5-Shot) |64.64|
|TruthfulQA (0-shot) |58.01|
|Winogrande (5-shot) |79.64|
|GSM8k (5-shot) |51.18|
|
RaoFoundation/774M-03_09_2024 | RaoFoundation | "2024-03-10T06:34:47Z" | 1,006 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:tiiuae/falcon-refinedweb",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-10T05:56:25Z" | ---
license: mit
datasets:
- tiiuae/falcon-refinedweb
---
This model was trained for Bittensor's pretraining subnet (https://github.com/RaoFoundation/pretraining) and, as of March 9th 2024, is the top model.
Bittensor subnet 9 rewards miners for producing pretrained Foundation-Models on the Falcon Refined Web dataset. It acts like a continuous benchmark whereby miners are rewarded for attaining the best losses on randomly sampled pages of Falcon given a consistent model architecture. The reward mechanism works as follows:
1. Miners train and periodically publish models to hugging face and commit the metadata for that model to the Bittensor chain.
2. Validators download the models from hugging face for each miner based on the Bittensor chain metadata and continuously evaluate them, setting weights based on the performance of each model against the Falcon dataset. They also log results to [wandb](https://wandb.ai/opentensor-dev/pretraining-subnet).
3. The Bittensor chain aggregates weights from all active validators using Yuma Consensus to determine the proportion of TAO emission rewarded to miners and validators.
Bittensor hosts multiple incentive mechanism through which miners are evaluated by validators for performing actions well. Validators perform the process of evaluation and 'set weights', which are transactions into Bittensor's blockchain. Each incentive mechanism in Bittensor is called a 'subnet' and has an identifier (This particular mechanism has subnet uid 9). Weights and the amount of TAO held by the validators become inputs to Bittensor's consensus mechanism called Yuma Consensus. YC drives validators towards a consensus, agreement about the value of the work done by miners. The miners with the highest agreed upon scores are minted TAO, the network digital currency.
Miners within this subnet are evaluated based on the number of times the model they have hosted has a lower loss than another model on the network when randomly sampling from the near infinite Falcon Refined Web pretraining dataset. To perform well, miners must attain the lowest loss on the largest number of random batches. Finding the best model and delta at the earliest block ensures the most incentive. |
Helsinki-NLP/opus-mt-tn-en | Helsinki-NLP | "2023-08-16T12:07:02Z" | 1,005 | 0 | transformers | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"tn",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | "2022-03-02T23:29:04Z" | ---
tags:
- translation
license: apache-2.0
---
### opus-mt-tn-en
* source languages: tn
* target languages: en
* OPUS readme: [tn-en](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/tn-en/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-21.zip](https://object.pouta.csc.fi/OPUS-MT-models/tn-en/opus-2020-01-21.zip)
* test set translations: [opus-2020-01-21.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/tn-en/opus-2020-01-21.test.txt)
* test set scores: [opus-2020-01-21.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/tn-en/opus-2020-01-21.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| JW300.tn.en | 43.4 | 0.589 |
|
Kukedlc/NeuralKukedlc-7B-Labonned | Kukedlc | "2024-05-25T17:09:35Z" | 1,005 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/NeuralBeagle14-7B",
"mlabonne/NeuralHermes-2.5-Mistral-7B",
"conversational",
"base_model:mlabonne/NeuralBeagle14-7B",
"base_model:mlabonne/NeuralHermes-2.5-Mistral-7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-10T22:41:19Z" | ---
tags:
- merge
- mergekit
- lazymergekit
- mlabonne/NeuralBeagle14-7B
- mlabonne/NeuralHermes-2.5-Mistral-7B
base_model:
- mlabonne/NeuralBeagle14-7B
- mlabonne/NeuralHermes-2.5-Mistral-7B
license: apache-2.0
---
# NeuralKukedlc-7B-Labonned
NeuralKukedlc-7B-Labonned is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: mlabonne/NeuralBeagle14-7B
layer_range: [0, 32]
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: mlabonne/NeuralBeagle14-7B
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 = "Kukedlc/NeuralKukedlc-7B-Labonned"
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"])
``` |
mayacinka/yam-jom-7B-dare | mayacinka | "2024-03-07T14:39:48Z" | 1,005 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2",
"yam-peleg/Experiment26-7B",
"base_model:eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2",
"base_model:yam-peleg/Experiment26-7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-05T22:17:51Z" | ---
tags:
- merge
- mergekit
- lazymergekit
- eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2
- yam-peleg/Experiment26-7B
base_model:
- eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2
- yam-peleg/Experiment26-7B
license: apache-2.0
---
# yam-jom-7B-dare
yam-jom-7B-dare is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2](https://huggingface.co/eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2)
* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
## 🧩 Configuration
```yaml
models:
- model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2
parameters:
weight: 0.35
density: 0.8
- model: yam-peleg/Experiment26-7B
parameters:
weight: 0.65
density: 0.8
base_model: yam-peleg/Experiment26-7B
merge_method: dare_ties
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mayacinka/yam-jom-7B-dare"
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"])
``` |
clowman/openchat-mistral-7b-reproduce | clowman | "2024-03-15T14:04:27Z" | 1,005 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-14T13:34:41Z" | ---
license: mit
---
A reproduction of https://github.com/imoneoi/openchat.
Training command:
```bash
deepspeed --num_gpus=8 --module ochat.training_deepspeed.train \
--model_path imone/Mistral_7B_with_EOT_token \
--data_prefix ./data/ \
--save_path ./checkpoints/mistral-7b/ \
--batch_max_len 77824 \
--epochs 10 \
--save_every 1 \
--deepspeed \
--deepspeed_config deepspeed_config.json
```
`deepspeed_config.json`:
```json
{
"bf16": {
"enabled": true
},
"zero_optimization": {
"stage": 2
},
"gradient_clipping": 1.0,
"gradient_accumulation_steps": 1,
"train_micro_batch_size_per_gpu": 1,
"steps_per_print": 100,
"wall_clock_breakdown": false
}
```
Training data is https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset |
Joseph717171/Mistral-12.25B-v0.2 | Joseph717171 | "2024-04-03T05:45:38Z" | 1,005 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2312.15166",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-31T05:44:09Z" | ---
base_model: []
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# Credit for the model card's description goes to ddh0 and mergekit
# Credit for access and conversion of Mistral-7B-v0.2 goes to alpindale (from MistalAI's weights to HF Transformers)
# Mistral-12.25B-v0.2
This is Mistral-12.25B-v0.2, a depth-upscaled version of [alpindale/Mistral-7B-v0.2-hf](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf).
This model is intended to be used as a basis for further fine-tuning, or as a drop-in upgrade from the original 7 billion parameter model.
Paper detailing how Depth-Up Scaling works: [SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling](https://arxiv.org/abs/2312.15166)
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
# UpStage's conclusionary limitations of their research:
"Our study on the Depth Up-Scaling (DUS) has important limitations and considerations. **One key limitation is the need for more thorough explorations of hyperparameters used in the DUS approach. Namely, we removed m = 8 layers from both ends of our base model, primarily due to hardware limitations. However, we have not yet determined if this value is optimal for enhancing performance.** The extended time and cost of continued pretraining made it challenging to conduct more comprehensive experiments, which we aim to address in future work through various comparative analyses."
This model was made to help test whether 10.7B parameters (m = 8) is better or worse than m < 8 (10.7B+ parameters)
## Merge Details
### Merge Method
This model was merged using the passthrough merge method.
### Models Merged
The following models were included in the merge:
* /Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf
### Configuration
The following YAML configuration was used to produce this model:
```yaml
dtype: bfloat16
merge_method: passthrough
# Depth UpScaled (DUS) version of Mistral-7B-v0.2
# where m = 4 (The number of layers to remove from the model)
# s = 56 (The number of layers the model will have after the DUS)
slices:
- sources:
- layer_range: [0, 28]
model: /Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf
- sources:
- layer_range: [4, 32]
model: /Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf
```
# exllama (Thanks to blockblockblock)
https:// huggingface.co/blockblockblock/
Mistral-12.25B-Instruct-vO.2-bpw2.5 https://huggingtace.co/blockblockblock/
Mistral-12.25B-Instruct-v0.2-bpw3 https://huggingface.co/blockblockblock/
Mistral-12.25B-Instruct-vO.2-bpw3.5 https://huggingface.co/blockblockblock/
Mistral-12.25B-Instruct-vO.2-bpw3.7 https://huggingface.co/blockblockblock/
Mistral-12.25B-Instruct-vO.2-bpw4 https://huggingface.co/blockblockblock/
Mistral-12.25B-Instruct-v0.2-bpw4.2 https://huggingface.co/blockblockblock/
Mistral-12.25B-Instruct-v0.2-bpw4.4 https://huggingface.co/blockblockblock/
Mistral-12.25B-Instruct-v0.2-bpw4.6 https://huggingface.co/blockblockblock/
Mistral-12.25B-Instruct-vO.2-bpw4.8 https://huggingface.co/blockblockblock/
Mistral-12.25B-Instruct-v0.2-bpw5 https://huggingface.co/blockblockblock/
Mistral-12.25B-Instruct-vO.2-bpw5.5 https://huggingface.co/blockblockblock/
Mistral-12.25B-Instruct-v0.2-bpw6 |
mkeys20/cats-random | mkeys20 | "2024-06-14T07:32:06Z" | 1,005 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2024-06-14T07:25:56Z" | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### Cats_random Dreambooth model trained by mkeys20 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
.jpg)
.jpg)
.jpg)
.jpg)
.jpg)
.jpg)
.jpg)
.jpg)
.jpg)
.jpg)
|
google/pix2struct-widget-captioning-base | google | "2023-09-11T20:24:03Z" | 1,004 | 6 | transformers | [
"transformers",
"pytorch",
"safetensors",
"pix2struct",
"text2text-generation",
"visual-question-answering",
"en",
"fr",
"ro",
"de",
"multilingual",
"arxiv:2210.03347",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] | visual-question-answering | "2023-03-21T10:13:36Z" | ---
language:
- en
- fr
- ro
- de
- multilingual
pipeline_tag: visual-question-answering
inference: false
license: apache-2.0
---
# Model card for Pix2Struct - Finetuned on Widget Captioning (Captioning a UI component on a screen)
# Table of Contents
0. [TL;DR](#TL;DR)
1. [Using the model](#using-the-model)
2. [Contribution](#contribution)
3. [Citation](#citation)
# TL;DR
Pix2Struct is an image encoder - text decoder model that is trained on image-text pairs for various tasks, including image captionning and visual question answering. The full list of available models can be found on the Table 1 of the paper:
The abstract of the model states that:
> Visually-situated language is ubiquitous—sources range from textbooks with diagrams to web pages with images and tables, to mobile apps with buttons and
forms. Perhaps due to this diversity, previous work has typically relied on domainspecific recipes with limited sharing of the underlying data, model architectures,
and objectives. We present Pix2Struct, a pretrained image-to-text model for
purely visual language understanding, which can be finetuned on tasks containing visually-situated language. Pix2Struct is pretrained by learning to parse
masked screenshots of web pages into simplified HTML. The web, with its richness of visual elements cleanly reflected in the HTML structure, provides a large
source of pretraining data well suited to the diversity of downstream tasks. Intuitively, this objective subsumes common pretraining signals such as OCR, language modeling, image captioning. In addition to the novel pretraining strategy,
we introduce a variable-resolution input representation and a more flexible integration of language and vision inputs, where language prompts such as questions
are rendered directly on top of the input image. For the first time, we show that a
single pretrained model can achieve state-of-the-art results in six out of nine tasks
across four domains: documents, illustrations, user interfaces, and natural images.
# Using the model
## 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_checkpoint_to_pytorch.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
```
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
```
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")
```
## Running the model
The instructions for running the model are exactly the same as the instructions stated on [`pix2struct-textcaps-base`](https://huggingface.co/google/pix2struct-textcaps-base#using-the-model) model.
# Contribution
This model was originally contributed by Kenton Lee, Mandar Joshi 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{https://doi.org/10.48550/arxiv.2210.03347,
doi = {10.48550/ARXIV.2210.03347},
url = {https://arxiv.org/abs/2210.03347},
author = {Lee, Kenton and Joshi, Mandar and Turc, Iulia and Hu, Hexiang and Liu, Fangyu and Eisenschlos, Julian and Khandelwal, Urvashi and Shaw, Peter and Chang, Ming-Wei and Toutanova, Kristina},
keywords = {Computation and Language (cs.CL), Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
``` |
xinlai/LISA-13B-llama2-v1 | xinlai | "2023-08-23T11:56:45Z" | 1,004 | 4 | transformers | [
"transformers",
"pytorch",
"llava",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-08-23T11:34:04Z" | Entry not found |
TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF | TheBloke | "2023-09-27T12:52:41Z" | 1,004 | 9 | transformers | [
"transformers",
"gguf",
"llama",
"en",
"dataset:ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split",
"base_model:ehartford/WizardLM-33b-V1.0-Uncensored",
"license:other",
"text-generation-inference",
"region:us"
] | null | "2023-09-19T23:18:31Z" | ---
language:
- en
license: other
datasets:
- ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
model_name: WizardLM 33B V1.0 Uncensored
base_model: ehartford/WizardLM-33b-V1.0-Uncensored
inference: false
model_creator: Eric Hartford
model_type: llama
prompt_template: 'A chat between a curious user and an artificial intelligence assistant.
The assistant gives helpful, detailed, and polite answers to the user''s questions.
USER: {prompt} ASSISTANT:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# WizardLM 33B V1.0 Uncensored - GGUF
- Model creator: [Eric Hartford](https://huggingface.co/ehartford)
- Original model: [WizardLM 33B V1.0 Uncensored](https://huggingface.co/ehartford/WizardLM-33b-V1.0-Uncensored)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Eric Hartford's WizardLM 33B V1.0 Uncensored](https://huggingface.co/ehartford/WizardLM-33b-V1.0-Uncensored).
<!-- 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/WizardLM-33B-V1.0-Uncensored-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF)
* [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/WizardLM-33b-V1.0-Uncensored)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Vicuna
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [wizardlm-33b-v1.0-uncensored.Q2_K.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q2_K.gguf) | Q2_K | 2 | 13.50 GB| 16.00 GB | smallest, significant quality loss - not recommended for most purposes |
| [wizardlm-33b-v1.0-uncensored.Q3_K_S.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q3_K_S.gguf) | Q3_K_S | 3 | 14.06 GB| 16.56 GB | very small, high quality loss |
| [wizardlm-33b-v1.0-uncensored.Q3_K_M.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q3_K_M.gguf) | Q3_K_M | 3 | 15.76 GB| 18.26 GB | very small, high quality loss |
| [wizardlm-33b-v1.0-uncensored.Q3_K_L.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q3_K_L.gguf) | Q3_K_L | 3 | 17.28 GB| 19.78 GB | small, substantial quality loss |
| [wizardlm-33b-v1.0-uncensored.Q4_0.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q4_0.gguf) | Q4_0 | 4 | 18.36 GB| 20.86 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [wizardlm-33b-v1.0-uncensored.Q4_K_S.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q4_K_S.gguf) | Q4_K_S | 4 | 18.44 GB| 20.94 GB | small, greater quality loss |
| [wizardlm-33b-v1.0-uncensored.Q4_K_M.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q4_K_M.gguf) | Q4_K_M | 4 | 19.62 GB| 22.12 GB | medium, balanced quality - recommended |
| [wizardlm-33b-v1.0-uncensored.Q5_0.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q5_0.gguf) | Q5_0 | 5 | 22.40 GB| 24.90 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [wizardlm-33b-v1.0-uncensored.Q5_K_S.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q5_K_S.gguf) | Q5_K_S | 5 | 22.40 GB| 24.90 GB | large, low quality loss - recommended |
| [wizardlm-33b-v1.0-uncensored.Q5_K_M.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q5_K_M.gguf) | Q5_K_M | 5 | 23.05 GB| 25.55 GB | large, very low quality loss - recommended |
| [wizardlm-33b-v1.0-uncensored.Q6_K.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q6_K.gguf) | Q6_K | 6 | 26.69 GB| 29.19 GB | very large, extremely low quality loss |
| [wizardlm-33b-v1.0-uncensored.Q8_0.gguf](https://huggingface.co/TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF/blob/main/wizardlm-33b-v1.0-uncensored.Q8_0.gguf) | Q8_0 | 8 | 34.57 GB| 37.07 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/WizardLM-33B-V1.0-Uncensored-GGUF and below it, a specific filename to download, such as: wizardlm-33b-v1.0-uncensored.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/WizardLM-33B-V1.0-Uncensored-GGUF wizardlm-33b-v1.0-uncensored.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/WizardLM-33B-V1.0-Uncensored-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/WizardLM-33B-V1.0-Uncensored-GGUF wizardlm-33b-v1.0-uncensored.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 wizardlm-33b-v1.0-uncensored.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/WizardLM-33B-V1.0-Uncensored-GGUF", model_file="wizardlm-33b-v1.0-uncensored.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: Eric Hartford's WizardLM 33B V1.0 Uncensored
This is a retraining of https://huggingface.co/WizardLM/WizardLM-30B-V1.0 with a filtered dataset, intended to reduce refusals, avoidance, and bias.
Note that LLaMA itself has inherent ethical beliefs, so there's no such thing as a "truly uncensored" model. But this model will be more compliant than WizardLM/WizardLM-7B-V1.0.
Shout out to the open source AI/ML community, and everyone who helped me out.
Note: An uncensored model has no guardrails. You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car. Publishing anything this model generates is the same as publishing it yourself. You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.
Like WizardLM/WizardLM-30B-V1.0, this model is trained with Vicuna-1.1 style prompts.
```
You are a helpful AI assistant.
USER: <prompt>
ASSISTANT:
```
Thank you [chirper.ai](https://chirper.ai) for sponsoring some of my compute!
<!-- original-model-card end -->
|
LongSafari/hyenadna-medium-160k-seqlen-hf | LongSafari | "2024-01-24T17:20:02Z" | 1,004 | 2 | transformers | [
"transformers",
"safetensors",
"hyenadna",
"text-generation",
"dna",
"biology",
"genomics",
"hyena",
"custom_code",
"arxiv:2306.15794",
"arxiv:2302.10866",
"license:bsd-3-clause",
"autotrain_compatible",
"region:us"
] | text-generation | "2023-11-03T14:07:05Z" | ---
license: bsd-3-clause
tags:
- dna
- biology
- genomics
- hyena
---
# HyenaDNA
Welcome! HyenaDNA is a long-range genomic foundation model pretrained on context lengths of up to **1 million tokens** at **single nucleotide resolution**.
See below for an [overview](#model) of the model and training. Better yet, check out these resources.
**Resources:**
- [arxiv](https://arxiv.org/abs/2306.15794)
- [blog](https://hazyresearch.stanford.edu/blog/2023-06-29-hyena-dna)
- [colab](https://colab.research.google.com/drive/1wyVEQd4R3HYLTUOXEEQmp_I8aNC_aLhL?usp=sharing)
- [github](https://github.com/HazyResearch/hyena-dna)
**Links to all HuggingFace models:**
We've uploaded a [collection](https://huggingface.co/collections/LongSafari/hyenadna-models-654d0cbbe113b04ba5a0f638) of all the pretrained HyenaDNA checkpoints.
You'll see models of different sizes and sequence lengths. There are also original weights-only versions of each model in the [LongSafari organization](https://huggingface.co/LongSafari), which are designed to be loaded with the original [github](https://github.com/HazyResearch/hyena-dna) repo. These models have identical outputs to the models in the collection above, just different interfaces.
See [GPU requirements](#hardware) for each model.
### Using HyenaDNA
In this brief code sample we demonstrate fine-tuning HyenaDNA on a sequence classification task. This sample uses the `medium` checkpoint, with a maximum sequence length of 160k nucleotides. Note that training will fail if you use a sequence length longer than the maximum supported length for your chosen checkpoint.
In testing, we have been able to train at a sequence length up to about 250k nucleotides on a Colab T4 GPU (16GB VRAM). For longer sequence lengths, more memory will be required.
```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer
from transformers import TrainingArguments, Trainer, logging
import torch
# instantiate pretrained model
checkpoint = 'LongSafari/hyenadna-medium-160k-seqlen-hf'
max_length = 160_000
# bfloat16 for better speed and reduced memory usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint, trust_remote_code=True)
model = AutoModelForSequenceClassification.from_pretrained(checkpoint, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
# Generate some random sequence and labels
# If you're copying this code, replace the sequences and labels
# here with your own data!
sequence = 'ACTG' * int(max_length/4)
sequence = [sequence] * 8 # Create 8 identical samples
tokenized = tokenizer(sequence)["input_ids"]
labels = [0, 1] * 4
# Create a dataset for training
ds = Dataset.from_dict({"input_ids": tokenized, "labels": labels})
ds.set_format("pt")
# Initialize Trainer
# Note that we're using extremely small batch sizes to maximize
# our ability to fit long sequences in memory!
args = {
"output_dir": "tmp",
"num_train_epochs": 1,
"per_device_train_batch_size": 1,
"gradient_accumulation_steps": 4,
"gradient_checkpointing": True,
"learning_rate": 2e-5,
}
training_args = TrainingArguments(**args)
trainer = Trainer(model=model, args=training_args, train_dataset=ds)
result = trainer.train()
print(result)
# Now we can save_pretrained() or push_to_hub() to share the trained model!
```
You may also find these [notebooks](https://huggingface.co/docs/transformers/notebooks) useful. Although they're not specific to HyenaDNA, they contain additional examples of training DNA and sequence classification models.
- [How to fine-tune a Nucleotide Transformer model](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/nucleotide_transformer_dna_sequence_modelling.ipynb)
- [How to fine-tune a model on text classification](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/text_classification.ipynb)
### GPU requirements (suggested)
<a name="hardware"></a>
Here are suggestions on the hardware (preferred minimum) we think you can use for each model.
GPU during: Pretrain, fine-tune, inference
- [tiny-1k](https://huggingface.co/LongSafari/hyenadna-tiny-1k-seqlen/tree/main): (T4, T4, T4)
- [small-32k](https://huggingface.co/LongSafari/hyenadna-small-32k-seqlen/tree/main): (A100-40GB, T4, T4)
- [medium-160k](https://huggingface.co/LongSafari/hyenadna-medium-160k-seqlen/tree/main): (A100-40GB, T4, T4)
- [medium-450k](https://huggingface.co/LongSafari/hyenadna-medium-450k-seqlen/tree/main): (A100-40GB, A100-40GB, T4)
- [large-1m](https://huggingface.co/LongSafari/hyenadna-large-1m-seqlen/tree/main): (A100-80GB, A100-80GB, A100-40GB)
## Model & Training Overview
<a name="model"></a>
HyenaDNA uses a simple stack of [Hyena](https://arxiv.org/abs/2302.10866) operators, which are a subquadratic drop-in replacement for attention in Transformers. The Hyena operator is able to match quality in language modeling by using modified input projections, implicit convolutions and gating, all subquadratic operations.
This enables HyenaDNA to reach context lengths of up to 500x longer than previous genomic Transformer models using dense attention, and train 160x faster at sequence length 1M (compared to Flash Attention).
We use a single character tokenizer with a primary vocab of 4 nucleotides (plus special tokens), enabling the single nucleotide resolution, a first in genomic foundation models. In addition, the implicit long convolution enables a **global receptive field** at each layer.
We pretrain using next token (nucleotide) prediction on the human reference genome (HG38).
HyenaDNA sets new SotA on 23 downstream tasks including predicting regulatory elements, chromatin profiles, and species classification. We also explore what new capabilities open up with long context in genomics, including the first use of in-context learning with soft prompt tuneable tokens and instruction fine-tuning.
Check out our [blog](https://hazyresearch.stanford.edu/blog/2023-06-29-hyena-dna) for more details on HyenaDNA!
### Authors
Eric Nguyen*, Michael Poli*, Marjan Faizi*, Armin Thomas, Callum Birch-Sykes, Michael Wornow, Aman Patel, Clayton Rabideau, Stefano Massaroli, Yoshua Bengio, Stefano Ermon, Stephen Baccus, Chris Re.
**Contact**
Eric Nguyen, [email protected]
Michael Poli, [email protected]
Marjan Faizi, [email protected]
## Citation
Feel free to cite us :)
```
@article{nguyen2023hyenadna,
title={HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution},
author={Eric Nguyen and Michael Poli and Marjan Faizi and Armin Thomas and Callum Birch-Sykes and Michael Wornow and Aman Patel and Clayton Rabideau and Stefano Massaroli and Yoshua Bengio and Stefano Ermon and Stephen A. Baccus and Chris Ré},
year={2023},
eprint={2306.15794},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
``` |
TheBloke/GOAT-70B-Storytelling-GGUF | TheBloke | "2023-11-20T12:14:10Z" | 1,004 | 9 | transformers | [
"transformers",
"gguf",
"llama",
"facebook",
"meta",
"pytorch",
"llama-2",
"Storywriter",
"base_model:GOAT-AI/GOAT-70B-Storytelling",
"license:llama2",
"text-generation-inference",
"region:us"
] | null | "2023-11-20T11:29:44Z" | ---
base_model: GOAT-AI/GOAT-70B-Storytelling
inference: false
license: llama2
model_creator: GOAT.AI
model_name: Goat 70B Storytelling
model_type: llama
prompt_template: 'You are a helpful assistant for fiction writing. Always cut the
bullshit and provide concise outlines with useful details. Do not turn your stories
into fairy tales, be realistic.
### USER: {prompt}
### ASSISTANT:
'
quantized_by: TheBloke
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
- Storywriter
---
<!-- 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 -->
# Goat 70B Storytelling - GGUF
- Model creator: [GOAT.AI](https://huggingface.co/GOAT-AI)
- Original model: [Goat 70B Storytelling](https://huggingface.co/GOAT-AI/GOAT-70B-Storytelling)
<!-- description start -->
## Description
This repo contains GGUF format model files for [GOAT.AI's Goat 70B Storytelling](https://huggingface.co/GOAT-AI/GOAT-70B-Storytelling).
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/GOAT-70B-Storytelling-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GGUF)
* [GOAT.AI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/GOAT-AI/GOAT-70B-Storytelling)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: GOAT
```
You are a helpful assistant for fiction writing. Always cut the bullshit and provide concise outlines with useful details. Do not turn your stories into fairy tales, be realistic.
### 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [goat-70b-storytelling.Q2_K.gguf](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GGUF/blob/main/goat-70b-storytelling.Q2_K.gguf) | Q2_K | 2 | 29.28 GB| 31.78 GB | smallest, significant quality loss - not recommended for most purposes |
| [goat-70b-storytelling.Q3_K_S.gguf](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GGUF/blob/main/goat-70b-storytelling.Q3_K_S.gguf) | Q3_K_S | 3 | 29.92 GB| 32.42 GB | very small, high quality loss |
| [goat-70b-storytelling.Q3_K_M.gguf](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GGUF/blob/main/goat-70b-storytelling.Q3_K_M.gguf) | Q3_K_M | 3 | 33.19 GB| 35.69 GB | very small, high quality loss |
| [goat-70b-storytelling.Q3_K_L.gguf](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GGUF/blob/main/goat-70b-storytelling.Q3_K_L.gguf) | Q3_K_L | 3 | 36.15 GB| 38.65 GB | small, substantial quality loss |
| [goat-70b-storytelling.Q4_0.gguf](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GGUF/blob/main/goat-70b-storytelling.Q4_0.gguf) | Q4_0 | 4 | 38.87 GB| 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [goat-70b-storytelling.Q4_K_S.gguf](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GGUF/blob/main/goat-70b-storytelling.Q4_K_S.gguf) | Q4_K_S | 4 | 39.07 GB| 41.57 GB | small, greater quality loss |
| [goat-70b-storytelling.Q4_K_M.gguf](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GGUF/blob/main/goat-70b-storytelling.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended |
| [goat-70b-storytelling.Q5_0.gguf](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GGUF/blob/main/goat-70b-storytelling.Q5_0.gguf) | Q5_0 | 5 | 47.46 GB| 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [goat-70b-storytelling.Q5_K_S.gguf](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GGUF/blob/main/goat-70b-storytelling.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
| [goat-70b-storytelling.Q5_K_M.gguf](https://huggingface.co/TheBloke/GOAT-70B-Storytelling-GGUF/blob/main/goat-70b-storytelling.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended |
| goat-70b-storytelling.Q6_K.gguf | Q6_K | 6 | 56.59 GB| 59.09 GB | very large, extremely low quality loss |
| goat-70b-storytelling.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:
* `goat-70b-storytelling.Q6_K.gguf-split-a`
* `goat-70b-storytelling.Q6_K.gguf-split-b`
### q8_0
Please download:
* `goat-70b-storytelling.Q8_0.gguf-split-a`
* `goat-70b-storytelling.Q8_0.gguf-split-b`
To join the files, do the following:
Linux and macOS:
```
cat goat-70b-storytelling.Q6_K.gguf-split-* > goat-70b-storytelling.Q6_K.gguf && rm goat-70b-storytelling.Q6_K.gguf-split-*
cat goat-70b-storytelling.Q8_0.gguf-split-* > goat-70b-storytelling.Q8_0.gguf && rm goat-70b-storytelling.Q8_0.gguf-split-*
```
Windows command line:
```
COPY /B goat-70b-storytelling.Q6_K.gguf-split-a + goat-70b-storytelling.Q6_K.gguf-split-b goat-70b-storytelling.Q6_K.gguf
del goat-70b-storytelling.Q6_K.gguf-split-a goat-70b-storytelling.Q6_K.gguf-split-b
COPY /B goat-70b-storytelling.Q8_0.gguf-split-a + goat-70b-storytelling.Q8_0.gguf-split-b goat-70b-storytelling.Q8_0.gguf
del goat-70b-storytelling.Q8_0.gguf-split-a goat-70b-storytelling.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/GOAT-70B-Storytelling-GGUF and below it, a specific filename to download, such as: goat-70b-storytelling.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/GOAT-70B-Storytelling-GGUF goat-70b-storytelling.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/GOAT-70B-Storytelling-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/GOAT-70B-Storytelling-GGUF goat-70b-storytelling.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 goat-70b-storytelling.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are a helpful assistant for fiction writing. Always cut the bullshit and provide concise outlines with useful details. Do not turn your stories into fairy tales, be realistic.\n### USER: {prompt}\n### ASSISTANT:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/GOAT-70B-Storytelling-GGUF", model_file="goat-70b-storytelling.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: GOAT.AI's Goat 70B Storytelling
# GOAT-70B-Storytelling model
GOAT-70B-Storytelling model trained by GOAT.AI lab as a core model for an autonomous story-writing agent.
# GOAT-Storytelling-Agent
This agent facilitates the generation of high-quality, cohesive, and captivating narratives, including stories and books. It achieves this by utilizing inputs such as plot outlines, character profiles, their interrelationships, and other relevant details. Examples are provided below.
# Model description
- **Base Architecture:** LLaMA 2 70B
- **License:** llama2
- **Context window length:** 4096 tokens
### Training details
Training was performed on a GPU cluster of 64xH100s. FSDP ZeRO-3 sharding is employed for efficient training. We instruction finetune on a dataset of 18K examples for one epoch with batch size of 336, AdamW optimizer with learning rate 1e-5.
### Learn more
- **Blogpost:** [GOAT-Storytelling: Arbitrarily Long Story Writing Agent](https://www.blog.goat.ai/goat-st/)
- **GitHub:** [here](https://github.com/GOAT-AI-lab/GOAT-Storytelling-Agent)
- **Generated examples:** [here](https://huggingface.co/datasets/GOAT-AI/generated-novels/tree/main/generated-books)
## Uses
The main purpose of GOAT-70B-Storytelling is to generate books, novels, movie scripts and etc. as an agent in coping with our GOAT-Storytelling-Agent. It is specifically designed for storywriters.
## Usage
Usage can be either self-hosted via `transformers` or used with Spaces
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "GOAT-AI/GOAT-70B-Storytelling"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16
)
```
Currently, we support LLM endpoint generation, where you need to send a post request to the generation endpoint (we recommend using Text Generation Inference by HuggingFace)
First, modify `config.py` and add your generation endpoint.
Then you can use it inside via GOAT-Storytelling-Agent:
```python
from goat_storytelling_agent import storytelling_agent as goat
novel_scenes = goat.generate_story('treasure hunt in a jungle', form='novel')
```
## License
GOAT-70B-Storytelling model is based on [Meta's LLaMA-2-70b-hf](https://huggingface.co/meta-llama/Llama-2-70b-hf), and using own datasets.
GOAT-70B-Storytelling model weights are available under LLAMA-2 license.
### Risks and Biases
GOAT-70B-Storytelling model can produce factually incorrect output and should not be relied on to deliver factually accurate information. Therefore, the GOAT-70B-Storytelling model could possibly generate wrong, biased, or otherwise offensive outputs.
<!-- original-model-card end -->
|
indischepartij/MiniCPM-3B-OpenHermes-2.5-v2 | indischepartij | "2024-03-04T12:57:30Z" | 1,004 | 14 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-11T05:15:58Z" | ---
license: apache-2.0
library_name: transformers
model-index:
- name: MiniCPM-3B-OpenHermes-2.5-v2
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: 47.44
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiniCPM-3B-OpenHermes-2.5-v2
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: 72.0
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiniCPM-3B-OpenHermes-2.5-v2
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: 53.06
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiniCPM-3B-OpenHermes-2.5-v2
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: 42.28
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiniCPM-3B-OpenHermes-2.5-v2
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: 65.43
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiniCPM-3B-OpenHermes-2.5-v2
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: 31.24
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiniCPM-3B-OpenHermes-2.5-v2
name: Open LLM Leaderboard
---
# 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]
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_indischepartij__MiniCPM-3B-OpenHermes-2.5-v2)
| Metric |Value|
|---------------------------------|----:|
|Avg. |51.91|
|AI2 Reasoning Challenge (25-Shot)|47.44|
|HellaSwag (10-Shot) |72.00|
|MMLU (5-Shot) |53.06|
|TruthfulQA (0-shot) |42.28|
|Winogrande (5-shot) |65.43|
|GSM8k (5-shot) |31.24|
|
TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k | TeeZee | "2024-03-31T23:26:28Z" | 1,004 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"dataset:Open-Orca/SlimOrca",
"dataset:allenai/ultrafeedback_binarized_cleaned",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-29T13:04:06Z" | ---
language:
- en
license: apache-2.0
datasets:
- Open-Orca/SlimOrca
- allenai/ultrafeedback_binarized_cleaned
model-index:
- name: GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
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: 65.27
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
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: 85.62
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
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: 65.61
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
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: 53.46
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
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: 82.72
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
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: 0.08
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
name: Open LLM Leaderboard
---
### TeeZee/GALAXY-XB-v1.03-SFT-DPO ###
Experiment, can DUS be taken one or more steps further?
### Technical notes:
- model v03 finetuned on 50k entries from SlimOrca dataset and then DPO on 30k entries from ultrachat
- 12 layers removed from both models, 4 more than in original paper but its 1/4 of all layers(48) as per original paper.
- base version of upstage/SOLAR-10.7B-v1.0 used for merge
### To evaluate
- model performance after DPO, did it recover all initial performance loss after merge?
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TeeZee__GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k)
| Metric |Value|
|---------------------------------|----:|
|Avg. |58.79|
|AI2 Reasoning Challenge (25-Shot)|65.27|
|HellaSwag (10-Shot) |85.62|
|MMLU (5-Shot) |65.61|
|TruthfulQA (0-shot) |53.46|
|Winogrande (5-shot) |82.72|
|GSM8k (5-shot) | 0.08|
|
Isaak-Carter/J.O.S.I.E.3-Beta10-7B-slerp | Isaak-Carter | "2024-04-05T12:56:52Z" | 1,004 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"Weyaxi/Einstein-v5-v0.2-7B",
"argilla/CapybaraHermes-2.5-Mistral-7B",
"conversational",
"base_model:Weyaxi/Einstein-v5-v0.2-7B",
"base_model:argilla/CapybaraHermes-2.5-Mistral-7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-05T08:22:21Z" | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- Weyaxi/Einstein-v5-v0.2-7B
- argilla/CapybaraHermes-2.5-Mistral-7B
base_model:
- Weyaxi/Einstein-v5-v0.2-7B
- argilla/CapybaraHermes-2.5-Mistral-7B
---
# J.O.S.I.E.3-Beta10-7B-slerp
J.O.S.I.E.3-Beta10-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Weyaxi/Einstein-v5-v0.2-7B](https://huggingface.co/Weyaxi/Einstein-v5-v0.2-7B)
* [argilla/CapybaraHermes-2.5-Mistral-7B](https://huggingface.co/argilla/CapybaraHermes-2.5-Mistral-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: Weyaxi/Einstein-v5-v0.2-7B
layer_range: [0, 32]
- model: argilla/CapybaraHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: argilla/CapybaraHermes-2.5-Mistral-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
```
## Evaluation
```json
{
"all": {
"acc": 0.6312165296664113,
"acc_stderr": 0.03236370559394293,
"acc_norm": 0.6324439925872714,
"acc_norm_stderr": 0.033019786616359854,
"mc1": 0.39657282741738065,
"mc1_stderr": 0.017124930942023518,
"mc2": 0.5688038233837539,
"mc2_stderr": 0.015263125204118244
},
"harness|arc:challenge|25": {
"acc": 0.6126279863481229,
"acc_stderr": 0.014235872487909869,
"acc_norm": 0.6348122866894198,
"acc_norm_stderr": 0.014070265519268802
},
"harness|hellaswag|10": {
"acc": 0.643397729535949,
"acc_stderr": 0.00478016987333285,
"acc_norm": 0.8378809002190799,
"acc_norm_stderr": 0.0036780679944244735
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.32,
"acc_stderr": 0.046882617226215034,
"acc_norm": 0.32,
"acc_norm_stderr": 0.046882617226215034
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.6074074074074074,
"acc_stderr": 0.0421850621536888,
"acc_norm": 0.6074074074074074,
"acc_norm_stderr": 0.0421850621536888
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.6907894736842105,
"acc_stderr": 0.037610708698674805,
"acc_norm": 0.6907894736842105,
"acc_norm_stderr": 0.037610708698674805
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.61,
"acc_stderr": 0.04902071300001975,
"acc_norm": 0.61,
"acc_norm_stderr": 0.04902071300001975
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.6754716981132075,
"acc_stderr": 0.02881561571343211,
"acc_norm": 0.6754716981132075,
"acc_norm_stderr": 0.02881561571343211
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.7291666666666666,
"acc_stderr": 0.03716177437566017,
"acc_norm": 0.7291666666666666,
"acc_norm_stderr": 0.03716177437566017
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.47,
"acc_stderr": 0.05016135580465919,
"acc_norm": 0.47,
"acc_norm_stderr": 0.05016135580465919
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.48,
"acc_stderr": 0.050211673156867795,
"acc_norm": 0.48,
"acc_norm_stderr": 0.050211673156867795
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.34,
"acc_stderr": 0.04760952285695235,
"acc_norm": 0.34,
"acc_norm_stderr": 0.04760952285695235
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.6011560693641619,
"acc_stderr": 0.037336266553835096,
"acc_norm": 0.6011560693641619,
"acc_norm_stderr": 0.037336266553835096
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.29411764705882354,
"acc_stderr": 0.04533838195929775,
"acc_norm": 0.29411764705882354,
"acc_norm_stderr": 0.04533838195929775
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.72,
"acc_stderr": 0.045126085985421276,
"acc_norm": 0.72,
"acc_norm_stderr": 0.045126085985421276
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.5659574468085107,
"acc_stderr": 0.03240038086792747,
"acc_norm": 0.5659574468085107,
"acc_norm_stderr": 0.03240038086792747
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.5,
"acc_stderr": 0.047036043419179864,
"acc_norm": 0.5,
"acc_norm_stderr": 0.047036043419179864
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.5448275862068965,
"acc_stderr": 0.04149886942192117,
"acc_norm": 0.5448275862068965,
"acc_norm_stderr": 0.04149886942192117
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.4021164021164021,
"acc_stderr": 0.02525303255499769,
"acc_norm": 0.4021164021164021,
"acc_norm_stderr": 0.02525303255499769
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.42063492063492064,
"acc_stderr": 0.04415438226743744,
"acc_norm": 0.42063492063492064,
"acc_norm_stderr": 0.04415438226743744
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.39,
"acc_stderr": 0.04902071300001975,
"acc_norm": 0.39,
"acc_norm_stderr": 0.04902071300001975
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.7774193548387097,
"acc_stderr": 0.02366421667164251,
"acc_norm": 0.7774193548387097,
"acc_norm_stderr": 0.02366421667164251
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.4876847290640394,
"acc_stderr": 0.035169204442208966,
"acc_norm": 0.4876847290640394,
"acc_norm_stderr": 0.035169204442208966
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.68,
"acc_stderr": 0.04688261722621505,
"acc_norm": 0.68,
"acc_norm_stderr": 0.04688261722621505
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.7818181818181819,
"acc_stderr": 0.03225078108306289,
"acc_norm": 0.7818181818181819,
"acc_norm_stderr": 0.03225078108306289
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.803030303030303,
"acc_stderr": 0.02833560973246336,
"acc_norm": 0.803030303030303,
"acc_norm_stderr": 0.02833560973246336
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.8549222797927462,
"acc_stderr": 0.025416343096306433,
"acc_norm": 0.8549222797927462,
"acc_norm_stderr": 0.025416343096306433
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.6435897435897436,
"acc_stderr": 0.02428314052946731,
"acc_norm": 0.6435897435897436,
"acc_norm_stderr": 0.02428314052946731
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.32592592592592595,
"acc_stderr": 0.028578348365473072,
"acc_norm": 0.32592592592592595,
"acc_norm_stderr": 0.028578348365473072
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.6638655462184874,
"acc_stderr": 0.030684737115135367,
"acc_norm": 0.6638655462184874,
"acc_norm_stderr": 0.030684737115135367
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.31788079470198677,
"acc_stderr": 0.038020397601079024,
"acc_norm": 0.31788079470198677,
"acc_norm_stderr": 0.038020397601079024
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8220183486238533,
"acc_stderr": 0.01639943636661289,
"acc_norm": 0.8220183486238533,
"acc_norm_stderr": 0.01639943636661289
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5185185185185185,
"acc_stderr": 0.034076320938540516,
"acc_norm": 0.5185185185185185,
"acc_norm_stderr": 0.034076320938540516
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.803921568627451,
"acc_stderr": 0.027865942286639318,
"acc_norm": 0.803921568627451,
"acc_norm_stderr": 0.027865942286639318
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.7974683544303798,
"acc_stderr": 0.026160568246601453,
"acc_norm": 0.7974683544303798,
"acc_norm_stderr": 0.026160568246601453
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.6995515695067265,
"acc_stderr": 0.03076935200822914,
"acc_norm": 0.6995515695067265,
"acc_norm_stderr": 0.03076935200822914
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.7480916030534351,
"acc_stderr": 0.03807387116306085,
"acc_norm": 0.7480916030534351,
"acc_norm_stderr": 0.03807387116306085
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.8016528925619835,
"acc_stderr": 0.036401182719909456,
"acc_norm": 0.8016528925619835,
"acc_norm_stderr": 0.036401182719909456
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.8055555555555556,
"acc_stderr": 0.038260763248848646,
"acc_norm": 0.8055555555555556,
"acc_norm_stderr": 0.038260763248848646
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.754601226993865,
"acc_stderr": 0.03380939813943354,
"acc_norm": 0.754601226993865,
"acc_norm_stderr": 0.03380939813943354
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.44642857142857145,
"acc_stderr": 0.04718471485219588,
"acc_norm": 0.44642857142857145,
"acc_norm_stderr": 0.04718471485219588
},
"harness|hendrycksTest-management|5": {
"acc": 0.7961165048543689,
"acc_stderr": 0.039891398595317706,
"acc_norm": 0.7961165048543689,
"acc_norm_stderr": 0.039891398595317706
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8589743589743589,
"acc_stderr": 0.02280138253459754,
"acc_norm": 0.8589743589743589,
"acc_norm_stderr": 0.02280138253459754
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.73,
"acc_stderr": 0.044619604333847394,
"acc_norm": 0.73,
"acc_norm_stderr": 0.044619604333847394
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8084291187739464,
"acc_stderr": 0.014072859310451949,
"acc_norm": 0.8084291187739464,
"acc_norm_stderr": 0.014072859310451949
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7312138728323699,
"acc_stderr": 0.023868003262500104,
"acc_norm": 0.7312138728323699,
"acc_norm_stderr": 0.023868003262500104
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.24916201117318434,
"acc_stderr": 0.014465893829859924,
"acc_norm": 0.24916201117318434,
"acc_norm_stderr": 0.014465893829859924
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7124183006535948,
"acc_stderr": 0.02591780611714716,
"acc_norm": 0.7124183006535948,
"acc_norm_stderr": 0.02591780611714716
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.7106109324758842,
"acc_stderr": 0.025755865922632945,
"acc_norm": 0.7106109324758842,
"acc_norm_stderr": 0.025755865922632945
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.6975308641975309,
"acc_stderr": 0.02555765398186806,
"acc_norm": 0.6975308641975309,
"acc_norm_stderr": 0.02555765398186806
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.49645390070921985,
"acc_stderr": 0.02982674915328092,
"acc_norm": 0.49645390070921985,
"acc_norm_stderr": 0.02982674915328092
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.4745762711864407,
"acc_stderr": 0.01275371692910101,
"acc_norm": 0.4745762711864407,
"acc_norm_stderr": 0.01275371692910101
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.6507352941176471,
"acc_stderr": 0.028959755196824862,
"acc_norm": 0.6507352941176471,
"acc_norm_stderr": 0.028959755196824862
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6323529411764706,
"acc_stderr": 0.019506291693954843,
"acc_norm": 0.6323529411764706,
"acc_norm_stderr": 0.019506291693954843
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.6363636363636364,
"acc_stderr": 0.046075820907199756,
"acc_norm": 0.6363636363636364,
"acc_norm_stderr": 0.046075820907199756
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.7183673469387755,
"acc_stderr": 0.028795185574291293,
"acc_norm": 0.7183673469387755,
"acc_norm_stderr": 0.028795185574291293
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.835820895522388,
"acc_stderr": 0.026193923544454125,
"acc_norm": 0.835820895522388,
"acc_norm_stderr": 0.026193923544454125
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.87,
"acc_stderr": 0.033799766898963086,
"acc_norm": 0.87,
"acc_norm_stderr": 0.033799766898963086
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5180722891566265,
"acc_stderr": 0.03889951252827216,
"acc_norm": 0.5180722891566265,
"acc_norm_stderr": 0.03889951252827216
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8187134502923976,
"acc_stderr": 0.029547741687640038,
"acc_norm": 0.8187134502923976,
"acc_norm_stderr": 0.029547741687640038
},
"harness|truthfulqa:mc|0": {
"mc1": 0.39657282741738065,
"mc1_stderr": 0.017124930942023518,
"mc2": 0.5688038233837539,
"mc2_stderr": 0.015263125204118244
},
"harness|winogrande|5": {
"acc": 0.7963693764798737,
"acc_stderr": 0.011317798781626918
},
"harness|gsm8k|5": {
"acc": 0.6103108415466262,
"acc_stderr": 0.01343312323611072
}
}
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Isaak-Carter/J.O.S.I.E.3-Beta10-7B-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"])
``` |
duyntnet/DuckDB-NSQL-7B-v0.1-imatrix-GGUF | duyntnet | "2024-05-31T00:08:22Z" | 1,004 | 0 | transformers | [
"transformers",
"gguf",
"imatrix",
"DuckDB-NSQL-7B-v0.1",
"text-generation",
"en",
"license:other",
"region:us"
] | text-generation | "2024-05-30T20:34:39Z" | ---
license: other
language:
- en
pipeline_tag: text-generation
inference: false
tags:
- transformers
- gguf
- imatrix
- DuckDB-NSQL-7B-v0.1
---
Quantizations of https://huggingface.co/motherduckdb/DuckDB-NSQL-7B-v0.1
# From original readme
## Model Description
NSQL is a family of autoregressive open-source large foundation models (FMs) designed specifically for SQL generation tasks.
## How to Use
Example 1:
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1")
model = AutoModelForCausalLM.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1", torch_dtype=torch.bfloat16)
text = """### Instruction:
Your task is to generate valid duckdb SQL to answer the following question.
### Input:
### Question:
create a new table called tmp from test.csv
### Response (use duckdb shorthand if possible):
"""
input_ids = tokenizer(text, return_tensors="pt").input_ids
generated_ids = model.generate(input_ids, max_length=500)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
```
Example 2:
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1")
model = AutoModelForCausalLM.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1", torch_dtype=torch.bfloat16)
text = """### Instruction:
Your task is to generate valid duckdb SQL to answer the following question, given a duckdb database schema.
### Input:
Here is the database schema that the SQL query will run on:
CREATE TABLE taxi (
VendorID bigint,
tpep_pickup_datetime timestamp,
tpep_dropoff_datetime timestamp,
passenger_count double,
trip_distance double,
fare_amount double,
extra double,
tip_amount double,
tolls_amount double,
improvement_surcharge double,
total_amount double,
);
### Question:
get all columns ending with _amount from taxi table
### Response (use duckdb shorthand if possible):"""
input_ids = tokenizer(text, return_tensors="pt").input_ids
generated_ids = model.generate(input_ids, max_length=500)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
```
Example 3:
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1")
model = AutoModelForCausalLM.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1", torch_dtype=torch.bfloat16)
text = """### Instruction:
Your task is to generate valid duckdb SQL to answer the following question, given a duckdb database schema.
### Input:
Here is the database schema that the SQL query will run on:
CREATE TABLE rideshare (
hvfhs_license_num varchar,
dispatching_base_num varchar,
originating_base_num varchar,
request_datetime timestamp,
on_scene_datetime timestamp,
pickup_datetime timestamp,
dropoff_datetime timestamp,
trip_miles double,
trip_time bigint,
);
### Question:
get longest trip in december 2022
### Response (use duckdb shorthand if possible):
"""
input_ids = tokenizer(text, return_tensors="pt").input_ids
generated_ids = model.generate(input_ids, max_length=500)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
``` |
openmmlab/upernet-swin-tiny | openmmlab | "2023-01-19T10:43:44Z" | 1,003 | 3 | transformers | [
"transformers",
"pytorch",
"upernet",
"vision",
"image-segmentation",
"en",
"arxiv:1807.10221",
"arxiv:2103.14030",
"license:mit",
"endpoints_compatible",
"region:us"
] | image-segmentation | "2023-01-13T14:31:56Z" | ---
language: en
license: mit
tags:
- vision
- image-segmentation
model_name: openmmlab/upernet-swin-tiny
---
# UperNet, Swin Transformer tiny-sized backbone
UperNet framework for semantic segmentation, leveraging a Swin Transformer backbone. UperNet was introduced in the paper [Unified Perceptual Parsing for Scene Understanding](https://arxiv.org/abs/1807.10221) by Xiao et al.
Combining UperNet with a Swin Transformer backbone was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030).
Disclaimer: The team releasing UperNet + Swin Transformer did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
UperNet is a framework for semantic segmentation. It consists of several components, including a backbone, a Feature Pyramid Network (FPN) and a Pyramid Pooling Module (PPM).
Any visual backbone can be plugged into the UperNet framework. The framework predicts a semantic label per pixel.
## Intended uses & limitations
You can use the raw model for semantic segmentation. See the [model hub](https://huggingface.co/models?search=openmmlab/upernet) to look for
fine-tuned versions (with various backbones) on a task that interests you.
### How to use
For code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/upernet#transformers.UperNetForSemanticSegmentation).
|
diffusers/controlnet-depth-sdxl-1.0-mid | diffusers | "2023-08-16T14:11:04Z" | 1,003 | 17 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"controlnet",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | text-to-image | "2023-08-16T11:30:18Z" |
---
license: openrail++
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- controlnet
inference: false
---
# SDXL-controlnet: Depth
These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with depth conditioning. This checkpoint is 5x smaller than the original XL controlnet checkpoint. You can find some example images in the following.
prompt: donald trump, serious look, cigar in the mouth, 70mm, film still, head shot
prompt: spiderman lecture, photorealistic
prompt: aerial view, a futuristic research complex in a bright foggy jungle, hard lighting
prompt: megatron in an apocalyptic world ground, runied city in the background, photorealistic
## Usage
Make sure to first install the libraries:
```bash
pip install accelerate transformers safetensors diffusers
```
And then we're ready to go:
```python
import torch
import numpy as np
from PIL import Image
from transformers import DPTFeatureExtractor, DPTForDepthEstimation
from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
from diffusers.utils import load_image
depth_estimator = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas").to("cuda")
feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-hybrid-midas")
controlnet = ControlNetModel.from_pretrained(
"diffusers/controlnet-depth-sdxl-1.0-mid",
variant="fp16",
use_safetensors=True,
torch_dtype=torch.float16,
).to("cuda")
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16).to("cuda")
pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
controlnet=controlnet,
vae=vae,
variant="fp16",
use_safetensors=True,
torch_dtype=torch.float16,
).to("cuda")
pipe.enable_model_cpu_offload()
def get_depth_map(image):
image = feature_extractor(images=image, return_tensors="pt").pixel_values.to("cuda")
with torch.no_grad(), torch.autocast("cuda"):
depth_map = depth_estimator(image).predicted_depth
depth_map = torch.nn.functional.interpolate(
depth_map.unsqueeze(1),
size=(1024, 1024),
mode="bicubic",
align_corners=False,
)
depth_min = torch.amin(depth_map, dim=[1, 2, 3], keepdim=True)
depth_max = torch.amax(depth_map, dim=[1, 2, 3], keepdim=True)
depth_map = (depth_map - depth_min) / (depth_max - depth_min)
image = torch.cat([depth_map] * 3, dim=1)
image = image.permute(0, 2, 3, 1).cpu().numpy()[0]
image = Image.fromarray((image * 255.0).clip(0, 255).astype(np.uint8))
return image
prompt = "stormtrooper lecture, photorealistic"
image = load_image("https://huggingface.co/lllyasviel/sd-controlnet-depth/resolve/main/images/stormtrooper.png")
controlnet_conditioning_scale = 0.5 # recommended for good generalization
depth_image = get_depth_map(image)
images = pipe(
prompt, image=depth_image, num_inference_steps=30, controlnet_conditioning_scale=controlnet_conditioning_scale,
).images
images[0]
images[0].save(f"stormtrooper_grid.png")
```
To more details, check out the official documentation of [`StableDiffusionXLControlNetPipeline`](https://huggingface.co/docs/diffusers/main/en/api/pipelines/controlnet_sdxl).
🚨 Please note that this checkpoint is experimental and there's a lot of room for improvement. We encourage the community to build on top of it, improve it, and provide us with feedback. 🚨
### Training
Our training script was built on top of the official training script that we provide [here](https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sdxl.md).
You can refer to [this script](https://github.com/huggingface/diffusers/blob/7b93c2a882d8e12209fbaeffa51ee2b599ab5349/examples/research_projects/controlnet/train_controlnet_webdataset.py) for full discolsure.
* This checkpoint does not perform distillation. We just use a smaller ControlNet initialized from the SDXL UNet. We
encourage the community to try and conduct distillation too. This resource might be of help in [this regard](https://huggingface.co/blog/sd_distillation).
* To learn more about how the ControlNet was initialized, refer to [this code block](https://github.com/huggingface/diffusers/blob/7b93c2a882d8e12209fbaeffa51ee2b599ab5349/examples/research_projects/controlnet/train_controlnet_webdataset.py#L981C1-L999C36).
* It does not have any attention blocks.
* The model works pretty good on most conditioning images. But for more complex conditionings, the bigger checkpoints might be better. We are still working on improving the quality of this checkpoint and looking for feedback from the community.
* We recommend playing around with the `controlnet_conditioning_scale` and `guidance_scale` arguments for potentially better
image generation quality.
#### Training data
The model was trained on 3M images from LAION aesthetic 6 plus subset, with batch size of 256 for 50k steps with constant learning rate of 3e-5.
#### Compute
One 8xA100 machine
#### Mixed precision
FP16 |
OpenNLPLab/TransNormerLLM-385M | OpenNLPLab | "2024-02-26T03:39:08Z" | 1,003 | 8 | transformers | [
"transformers",
"pytorch",
"text-generation",
" TransNormerLLM",
"custom_code",
"en",
"zh",
"arxiv:2307.14995",
"arxiv:2009.03300",
"license:other",
"autotrain_compatible",
"region:us"
] | text-generation | "2023-10-14T16:53:09Z" | ---
license: other
language:
- en
- zh
pipeline_tag: text-generation
tags:
- ' TransNormerLLM'
---
<div align="center">
<h1>
TransNormerLLM -- A Faster and Better LLM
</h1>
</div>
<p align="center">
💻 <a href="https://github.com/OpenNLPLab/TransnormerLLM" target="_blank">GitHub </a> • 💬 <a href="https://discord.gg/W4Vr7AKW" target="_blank">Discord</a> • 💬 <a href="./images/contact_me_qr.png" target="_blank">Wechat</a>
</p>
# Table of Contents
- [Introduction](#introduction)
- [Released Weights](#released-weights)
- [Benchmark Results](#benchmark-results)
- [General Domain](#general-domain)
- [Model Results](#model-results)
- [Inference and Deployment](#inference-and-deployment)
- [Dependency Installation](#dependency-installation)
- [Notice](#notice)
- [Python Code Inference](#python-code-inference)
- [Demonstration of Base Model Inference](#demonstration-of-base-model-inference)
- [Fine-tuning the Model](#fine-tuning-the-model)
- [Dependency Installation](#dependency-installation-1)
- [Training](#training)
- [Community and Ecosystem](#community-and-ecosystem)
- [Disclaimer, License and Citation](#disclaimer-license-and-citation)
- [Disclaimer](#disclaimer)
- [License](#license)
- [Acknowledgments](#acknowledgments)
- [Citation](#citation)
# Introduction
We are re-inventing the Large Language Model (LLM). This is the official implementation of TransNormerLLM in [link](https://arxiv.org/pdf/2307.14995.pdf. Our opened weights of TransNormerLLM are now accessible to individuals, creators, researchers and businesses of all sizes so that they can experiment, innovate and scale their ideas responsibly.
Our release contains the TransNormerLLM model implementation, the open-source weights and the starting code for Supervised Fine-tuning (SFT). We will show examples on how to load [TransNormerLLM](https://github.com/OpenNLPLab/Transnormer) models, run SFT and inference on it.
- TransNormerLLM is the first linear attention-based LLM that outperforms conventional softmax attention-based models in terms of both accuracy and efficiency. It was trained on a high-quality corpus with up to **1.4 trillion** tokens.
- TransNormerLLM evolves from the previous linear attention architecture TransNormer by making advanced modifications that include LRPE positional embedding, Lightning Attention acceleration, new gating and normalization mechanisms.
- TransNormerLLM achieved competitive performance of its size on multiple well-approved Chinese, English, and multi-language general and domain-specific benchmarks.
- This release includes **Base** versions with **385M**, **1B**, and **7B** parameters.
- All versions are fully open to academic research. Developers only need to apply via email and obtain official commercial permission to use it for free commercially.
- For more information, welcome reading our academic paper [TransNormerLLM](https://arxiv.org/pdf/2307.14995.pdf).
# Released Weights
The specific released versions and download links are shown as below:
| | Base Models |
|:-------:|:-----------:|
| 385M | 🤗 [TransNormerLLM-385M](https://huggingface.co/OpenNLPLab/TransNormerLLM-385M) |
| 1B | 🤗 [TransNormerLLM-1B](https://huggingface.co/OpenNLPLab/TransNormerLLM-1B) |
| 7B | 🤗 [TransNormerLLM-7B](https://huggingface.co/OpenNLPLab/TransNormerLLM-7B) |
# Benchmark Results
To validate TransNormerLLM, we tested our 385M, 1B, and 7B models on Commonsense Reasoning Task, MMLU, CMMLU, and C-Eval. For comparison, we selected several open-source models as competitors, including Transformer-based models such as OPT, Pythia, BLOOM, GPT-Neo, GPT-J, MPT, Falcon, LLaMA1/2, OpenLLAMA v1/v2, Baichuan 1/2, ChatGLM 1/2, and non-Transformer model RWKV. It can be observed that, compared to these models, TransNormerLLM remains highly competitive.
**Commonsense Reasoning** We report BoolQ, PIQA, SIQA,
HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA and their average. We report 0-shot results for all benchmarks using LM-Eval-Harness.
All of our models achieve competitive performance compared to existing state-of-the-art LLMs, showcasing a remarkable ability to comprehend and apply commonsense reasoning.
**Aggregated Benchmarks**
We report the overall results for MMLU, CMMLU, C-Eval. Official scripts were used for evaluating MMLU, CMMLU, and C-Eval, with all evaluation results being conducted with a 5-shot setup. In comparison to top-tier open-source models available in the industry, our models have demonstrated matched performance in both English and Chinese benchmarks.
## General Domain
In the general domain, we conducted 5-shot tests on the following datasets:
- [C-Eval](https://cevalbenchmark.com/index.html#home) is a comprehensive Chinese basic model evaluation dataset, covering 52 disciplines and four levels of difficulty. Our evaluation approach followed that of [LM-Evaluation-Harness](https://github.com/EleutherAI/lm-evaluation-harness).
- [MMLU](https://arxiv.org/abs/2009.03300) is an English evaluation dataset comprising 57 tasks, encompassing elementary math, American history, computer science, law, etc. The difficulty ranges from high school level to expert level. It's a mainstream LLM evaluation dataset. We used its [official](https://github.com/hendrycks/test) evaluation approach.
- [CMMLU](https://github.com/haonan-li/CMMLU) is a comprehensive Chinese evaluation benchmark covering 67 topics, specifically designed to assess language models' knowledge and reasoning capabilities in a Chinese context. We adopted its [official](https://github.com/haonan-li/CMMLU) evaluation approach.
### Model Results
**Performance Comparison on Commonsense Reasoning and Aggregated Benchmarks.** For a fair comparison, we report competing methods' results reproduced by us using their released models. PS: parameter size (billion). T: tokens (trillion). HS: HellaSwag. WG: WinoGrande.
| Model | PS | T | BoolQ | PIQA | HS | WG | ARC-e | ARC-c | OBQA | MMLU | CMMLU | C-Eval |
|-------------|------|------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|
| OPT | 0.35 | 0.30 | 57.74 | 64.58 | 36.69 | 52.49 | 44.02 | 23.89 | 28.20 | 26.02 | 25.34 | 25.71 |
| Pythia | 0.40 | 0.30 | 60.40 | 67.08 | 40.52 | 53.59 | 51.81 | 24.15 | 29.40 | 25.99 | 25.16 | 24.81 |
| BLOOM | 0.56 | 0.35 | 55.14 | 64.09 | 36.97 | 52.80 | 47.35 | 23.98 | 28.20 | 24.80 | 25.35 | 27.14 |
| RWKV | 0.43 | - | - | 67.52 | 40.90 | 51.14 | 52.86 | 25.17 | 32.40 | 24.85 | - | - |
| **Ours** | 0.39 | 1.0 | 62.14 | 66.70 | 46.27 | 54.46 | 55.43 | 27.99 | 32.40 | 25.90 | 25.05 | 25.24 |
# Inference and Deployment
The model weights, source code, and configuration needed for inference have been released on Hugging Face. Download links can be found in the table at the beginning of this document. Below, we demonstrate various inference methods using TransNormerLLM-7B-Chat as an example. The program will automatically download the required resources from Hugging Face.
## Dependency Installation
**📝Note** Please configure the following environment before using the model:
```shell
pip install triton==2.0.0
pip install einops
```
## Notice
If you encounter errors related to Triton, please set the following environment variables:
```
export use_triton=False
```
## Python Code Inference
### Demonstration of Base Model Inference
```python
>>> from transformers import AutoModelForCausalLM, AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("OpenNLPLab/TransNormerLLM-385M", trust_remote_code=True)
>>> model = AutoModelForCausalLM.from_pretrained("OpenNLPLab/TransNormerLLM-385M", device_map="auto", trust_remote_code=True)
```
> In the above code snippets, the model loading specifies `device_map='auto'`, which will use all available GPUs. If you need to specify the device(s) to use, you can control it in a way similar to `export CUDA_VISIBLE_DEVICES=0,1` (using the 0 and 1 graphics cards).
# Fine-tuning the Model
## Dependency Installation
```shell
git clone https://github.com/OpenNLPLab/TransNormerLLM.git
cd TransNormerLLM/fine-tune
pip install -r requirements.txt
```
- To use lightweight fine-tuning methods like LoRA, you must additionally install [peft](https://github.com/huggingface/peft).
## Training
Below, we provide an example of fine-tuning the TransNormerLLM-1B on a single machine with ZeRO-3.
Training Data: `alpaca_data.json`. This sample data was drawn from [alpaca_data.json](https://raw.githubusercontent.com/tatsu-lab/stanford_alpaca/main/alpaca_data.json), consisting of a selection of 52,002 entries, and has been reformatted. The main purpose is to demonstrate how to SFT our model, and effectiveness is not guaranteed.
```shell
torchrun \
--nproc_per_node=8 \
train.py \
--model_name_or_path OpenNLPLab/TransNormerLLM-385M \
--data_path ./alpaca_data.json \
--output_dir output \
--num_train_epochs 1 \
--per_device_train_batch_size 2 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 1 \
--bf16 true \
--adam_beta1 0.9 \
--adam_beta2 0.95 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 5000 \
--save_total_limit 30 \
--learning_rate 1e-4 \
--weight_decay 0.1 \
--warmup_ratio 0.1 \
--lr_scheduler_type "cosine" \
--deepspeed 'configs/zero3.json' \
--logging_steps 1 \
--dataloader_num_workers 24 \
--ddp_find_unused_parameters false \
--tf32 true \
```
# Community and Ecosystem
**📢📢📢 We will continuously update the support for TransNormerLLM from the community and ecosystem here 😀😀😀**
- [nanoTransnormer](https://github.com/Doraemonzzz/nanoTransNormer)
# Disclaimer, License and Citation
## Disclaimer
We hereby declare that our team has not developed any applications based on TransNormerLLM models, not on iOS, Android, the web, or any other platform. We strongly call on all users not to use TransNormerLLM models for any activities that harm national / social security or violate the law. Also, we ask users not to use TransNormerLLM models for Internet services that have not undergone appropriate security reviews and filings. We hope that all users can abide by this principle and ensure that the development of technology proceeds in a regulated and legal environment.
We have done our best to ensure the compliance of the data used in the model training process. However, despite our considerable efforts, there may still be some unforeseeable issues due to the complexity of the model and data. Therefore, if any problems arise due to the use of TransNormerLLM open-source models, including but not limited to data security issues, public opinion risks, or any risks and problems brought about by the model being misled, abused, spread or improperly exploited, we will not assume any responsibility.
## License
The community usage of TransNormerLLM model requires adherence to [Apache 2.0](https://github.com/OpenNLPLab/TransNormerLLM/blob/main/LICENSE) and [Community License for TransNormerLLM Model](https://huggingface.co/OpenNLPLab/TransNormerLLM-385M/blob/main/TransNormerLLM模型社区许可协议.pdf). The TransNormerLLM model supports commercial use. If you plan to use the TransNormerLLM model or its derivatives for commercial purposes, please ensure that your entity meets the following conditions:
1. The Daily Active Users (DAU) of your or your affiliate's service or product is less than 1 million.
2. Neither you nor your affiliates are software service providers or cloud service providers.
3. There is no possibility for you or your affiliates to grant the commercial license given to you, to reauthorize it to other third parties without TransNormerLLM's permission.
Upon meeting the above conditions, you need to submit the application materials required by the TransNormerLLM Model Community License Agreement via the following contact email: [email protected]. Once approved, TransNormerLLM will hereby grant you a non-exclusive, global, non-transferable, non-sublicensable, revocable commercial copyright license.
## Acknowledgments
Our project is developed based on the following open source projects:
- [Baichuan](https://github.com/baichuan-inc/Baichuan-7B) for the tokenizer.
- [metaseq](https://github.com/facebookresearch/metaseq) for training.
- [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) for evaluation.
## Citation
If you wish to cite our work, please use the following reference:
```
@article{qin2023scaling,
title={Scaling transnormer to 175 billion parameters},
author={Qin, Zhen and Li, Dong and Sun, Weigao and Sun, Weixuan and Shen, Xuyang and Han, Xiaodong and Wei, Yunshen and Lv, Baohong and Yuan, Fei and Luo, Xiao and others},
journal={arXiv preprint arXiv:2307.14995},
year={2023}
}
```
|
unsloth/mistral-7b-instruct-v0.1-bnb-4bit | unsloth | "2024-03-22T15:21:51Z" | 1,003 | 3 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"unsloth",
"mistral-7b",
"instruct",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | "2024-01-21T15:45:15Z" | ---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- unsloth
- transformers
- mistral
- mistral-7b
- instruct
---
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy%20me%20a%20coffee%20button.png" width="200"/>](https://ko-fi.com/unsloth)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
## ✨ Finetune for Free
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| **Gemma 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing) | 2.4x faster | 58% less |
| **Mistral 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
| **Llama-2 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lBzz5KeZJKXjvivbYvmGarix9Ao6Wxe5?usp=sharing) | 2.2x faster | 43% less |
| **TinyLlama** | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less |
| **CodeLlama 34b** A100 | [▶️ Start on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing) | 1.9x faster | 27% less |
| **Mistral 7b** 1xT4 | [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook) | 5x faster\* | 62% less |
| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
|
TechxGenus/gemma-2b-AWQ | TechxGenus | "2024-03-11T17:02:25Z" | 1,003 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"arxiv:2312.11805",
"arxiv:2009.03300",
"arxiv:1905.07830",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1905.10044",
"arxiv:1907.10641",
"arxiv:1811.00937",
"arxiv:1809.02789",
"arxiv:1911.01547",
"arxiv:1705.03551",
"arxiv:2107.03374",
"arxiv:2108.07732",
"arxiv:2110.14168",
"arxiv:2304.06364",
"arxiv:2206.04615",
"arxiv:1804.06876",
"arxiv:2110.08193",
"arxiv:2009.11462",
"arxiv:2101.11718",
"arxiv:1804.09301",
"arxiv:2109.07958",
"arxiv:2203.09509",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"awq",
"region:us"
] | text-generation | "2024-03-11T15:01:14Z" | ---
library_name: transformers
tags: []
extra_gated_heading: "Access Gemma on Hugging Face"
extra_gated_prompt: "To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately."
extra_gated_button_content: "Acknowledge license"
license: other
license_name: gemma-terms-of-use
license_link: https://ai.google.dev/gemma/terms
---
AWQ quantized version of gemma-2b model.
---
# Gemma Model Card
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
This model card corresponds to the 2B base version of the Gemma model. You can also visit the model card of the [7B base model](https://huggingface.co/google/gemma-7b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it).
**Resources and Technical Documentation**:
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
* [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma)
* [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-2b-gg-hf)
**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent)
**Authors**: Google
## Model Information
Summary description and brief definition of inputs and outputs.
### Description
Gemma is a family of lightweight, state-of-the-art open models from Google,
built from the same research and technology used to create the Gemini models.
They are text-to-text, decoder-only large language models, available in English,
with open weights, pre-trained variants, and instruction-tuned variants. Gemma
models are well-suited for a variety of text generation tasks, including
question answering, summarization, and reasoning. Their relatively small size
makes it possible to deploy them in environments with limited resources such as
a laptop, desktop or your own cloud infrastructure, democratizing access to
state of the art AI models and helping foster innovation for everyone.
### Usage
Below we share some code snippets on how to get quickly started with running the model. First make sure to `pip install -U transformers`, then copy the snippet from the section that is relevant for your usecase.
#### Fine-tuning the model
You can find fine-tuning scripts and notebook under the [`examples/` directory](https://huggingface.co/google/gemma-7b/tree/main/examples) of [`google/gemma-7b`](https://huggingface.co/google/gemma-7b) repository. To adapt it to this model, simply change the model-id to `google/gemma-2b`.
In that repository, we provide:
* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA
* A script to perform SFT using FSDP on TPU devices
* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset
#### Running the model on a CPU
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a single / multi GPU
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a GPU using different precisions
* _Using `torch.float16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.float16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using `torch.bfloat16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.bfloat16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Quantized Versions through `bitsandbytes`
* _Using 8-bit precision (int8)_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using 4-bit precision_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Other optimizations
* _Flash Attention 2_
First make sure to install `flash-attn` in your environment `pip install flash-attn`
```diff
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
+ attn_implementation="flash_attention_2"
).to(0)
```
### Inputs and outputs
* **Input:** Text string, such as a question, a prompt, or a document to be
summarized.
* **Output:** Generated English-language text in response to the input, such
as an answer to a question, or a summary of a document.
## Model Data
Data used for model training and how the data was processed.
### Training Dataset
These models were trained on a dataset of text data that includes a wide variety
of sources, totaling 6 trillion tokens. Here are the key components:
* Web Documents: A diverse collection of web text ensures the model is exposed
to a broad range of linguistic styles, topics, and vocabulary. Primarily
English-language content.
* Code: Exposing the model to code helps it to learn the syntax and patterns of
programming languages, which improves its ability to generate code or
understand code-related questions.
* Mathematics: Training on mathematical text helps the model learn logical
reasoning, symbolic representation, and to address mathematical queries.
The combination of these diverse data sources is crucial for training a powerful
language model that can handle a wide variety of different tasks and text
formats.
### Data Preprocessing
Here are the key data cleaning and filtering methods applied to the training
data:
* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was
applied at multiple stages in the data preparation process to ensure the
exclusion of harmful and illegal content
* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and
reliable, automated techniques were used to filter out certain personal
information and other sensitive data from training sets.
* Additional methods: Filtering based on content quality and safely in line with
[our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11).
## Implementation Information
Details about the model internals.
### Hardware
Gemma was trained using the latest generation of
[Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e).
Training large language models requires significant computational power. TPUs,
designed specifically for matrix operations common in machine learning, offer
several advantages in this domain:
* Performance: TPUs are specifically designed to handle the massive computations
involved in training LLMs. They can speed up training considerably compared to
CPUs.
* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing
for the handling of large models and batch sizes during training. This can
lead to better model quality.
* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for
handling the growing complexity of large foundation models. You can distribute
training across multiple TPU devices for faster and more efficient processing.
* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective
solution for training large models compared to CPU-based infrastructure,
especially when considering the time and resources saved due to faster
training.
* These advantages are aligned with
[Google's commitments to operate sustainably](https://sustainability.google/operating-sustainably/).
### Software
Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/ml-pathways).
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
ML Pathways is Google's latest effort to build artificially intelligent systems
capable of generalizing across multiple tasks. This is specially suitable for
[foundation models](https://ai.google/discover/foundation-models/), including large language models like
these ones.
Together, JAX and ML Pathways are used as described in the
[paper about the Gemini family of models](https://arxiv.org/abs/2312.11805); "the 'single
controller' programming model of Jax and Pathways allows a single Python
process to orchestrate the entire training run, dramatically simplifying the
development workflow."
## Evaluation
Model evaluation metrics and results.
### Benchmark Results
These models were evaluated against a large collection of different datasets and
metrics to cover different aspects of text generation:
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot, top-1 | 42.3 | 64.3 |
| [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot |71.4 | 81.2 |
| [PIQA](https://arxiv.org/abs/1911.11641) | 0-shot | 77.3 | 81.2 |
| [SocialIQA](https://arxiv.org/abs/1904.09728) | 0-shot | 59.7 | 51.8 |
| [BooIQ](https://arxiv.org/abs/1905.10044) | 0-shot | 69.4 | 83.2 |
| [WinoGrande](https://arxiv.org/abs/1907.10641) | partial score | 65.4 | 72.3 |
| [CommonsenseQA](https://arxiv.org/abs/1811.00937) | 7-shot | 65.3 | 71.3 |
| [OpenBookQA](https://arxiv.org/abs/1809.02789) | | 47.8 | 52.8 |
| [ARC-e](https://arxiv.org/abs/1911.01547) | | 73.2 | 81.5 |
| [ARC-c](https://arxiv.org/abs/1911.01547) | | 42.1 | 53.2 |
| [TriviaQA](https://arxiv.org/abs/1705.03551) | 5-shot | 53.2 | 63.4 |
| [Natural Questions](https://github.com/google-research-datasets/natural-questions) | 5-shot | - | 23 |
| [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 22.0 | 32.3 |
| [MBPP](https://arxiv.org/abs/2108.07732) | 3-shot | 29.2 | 44.4 |
| [GSM8K](https://arxiv.org/abs/2110.14168) | maj@1 | 17.7 | 46.4 |
| [MATH](https://arxiv.org/abs/2108.07732) | 4-shot | 11.8 | 24.3 |
| [AGIEval](https://arxiv.org/abs/2304.06364) | | 24.2 | 41.7 |
| [BIG-Bench](https://arxiv.org/abs/2206.04615) | | 35.2 | 55.1 |
| ------------------------------ | ------------- | ----------- | --------- |
| **Average** | | **54.0** | **56.4** |
## Ethics and Safety
Ethics and safety evaluation approach and results.
### Evaluation Approach
Our evaluation methods include structured evaluations and internal red-teaming
testing of relevant content policies. Red-teaming was conducted by a number of
different teams, each with different goals and human evaluation metrics. These
models were evaluated against a number of different categories relevant to
ethics and safety, including:
* Text-to-Text Content Safety: Human evaluation on prompts covering safety
policies including child sexual abuse and exploitation, harassment, violence
and gore, and hate speech.
* Text-to-Text Representational Harms: Benchmark against relevant academic
datasets such as [WinoBias](https://arxiv.org/abs/1804.06876) and [BBQ Dataset](https://arxiv.org/abs/2110.08193v2).
* Memorization: Automated evaluation of memorization of training data, including
the risk of personally identifiable information exposure.
* Large-scale harm: Tests for "dangerous capabilities," such as chemical,
biological, radiological, and nuclear (CBRN) risks.
### Evaluation Results
The results of ethics and safety evaluations are within acceptable thresholds
for meeting [internal policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11) for categories such as child
safety, content safety, representational harms, memorization, large-scale harms.
On top of robust internal evaluations, the results of well known safety
benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA
are shown here.
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [RealToxicity](https://arxiv.org/abs/2009.11462) | average | 6.86 | 7.90 |
| [BOLD](https://arxiv.org/abs/2101.11718) | | 45.57 | 49.08 |
| [CrowS-Pairs](https://aclanthology.org/2020.emnlp-main.154/) | top-1 | 45.82 | 51.33 |
| [BBQ Ambig](https://arxiv.org/abs/2110.08193v2) | 1-shot, top-1 | 62.58 | 92.54 |
| [BBQ Disambig](https://arxiv.org/abs/2110.08193v2) | top-1 | 54.62 | 71.99 |
| [Winogender](https://arxiv.org/abs/1804.09301) | top-1 | 51.25 | 54.17 |
| [TruthfulQA](https://arxiv.org/abs/2109.07958) | | 44.84 | 31.81 |
| [Winobias 1_2](https://arxiv.org/abs/1804.06876) | | 56.12 | 59.09 |
| [Winobias 2_2](https://arxiv.org/abs/1804.06876) | | 91.10 | 92.23 |
| [Toxigen](https://arxiv.org/abs/2203.09509) | | 29.77 | 39.59 |
| ------------------------------ | ------------- | ----------- | --------- |
## Usage and Limitations
These models have certain limitations that users should be aware of.
### Intended Usage
Open Large Language Models (LLMs) have a wide range of applications across
various industries and domains. The following list of potential uses is not
comprehensive. The purpose of this list is to provide contextual information
about the possible use-cases that the model creators considered as part of model
training and development.
* Content Creation and Communication
* Text Generation: These models can be used to generate creative text formats
such as poems, scripts, code, marketing copy, and email drafts.
* Chatbots and Conversational AI: Power conversational interfaces for customer
service, virtual assistants, or interactive applications.
* Text Summarization: Generate concise summaries of a text corpus, research
papers, or reports.
* Research and Education
* Natural Language Processing (NLP) Research: These models can serve as a
foundation for researchers to experiment with NLP techniques, develop
algorithms, and contribute to the advancement of the field.
* Language Learning Tools: Support interactive language learning experiences,
aiding in grammar correction or providing writing practice.
* Knowledge Exploration: Assist researchers in exploring large bodies of text
by generating summaries or answering questions about specific topics.
### Limitations
* Training Data
* The quality and diversity of the training data significantly influence the
model's capabilities. Biases or gaps in the training data can lead to
limitations in the model's responses.
* The scope of the training dataset determines the subject areas the model can
handle effectively.
* Context and Task Complexity
* LLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* A model's performance can be influenced by the amount of context provided
(longer context generally leads to better outputs, up to a certain point).
* Language Ambiguity and Nuance
* Natural language is inherently complex. LLMs might struggle to grasp subtle
nuances, sarcasm, or figurative language.
* Factual Accuracy
* LLMs generate responses based on information they learned from their
training datasets, but they are not knowledge bases. They may generate
incorrect or outdated factual statements.
* Common Sense
* LLMs rely on statistical patterns in language. They might lack the ability
to apply common sense reasoning in certain situations.
### Ethical Considerations and Risks
The development of large language models (LLMs) raises several ethical concerns.
In creating an open model, we have carefully considered the following:
* Bias and Fairness
* LLMs trained on large-scale, real-world text data can reflect socio-cultural
biases embedded in the training material. These models underwent careful
scrutiny, input data pre-processing described and posterior evaluations
reported in this card.
* Misinformation and Misuse
* LLMs can be misused to generate text that is false, misleading, or harmful.
* Guidelines are provided for responsible use with the model, see the
[Responsible Generative AI Toolkit](http://ai.google.dev/gemma/responsible).
* Transparency and Accountability:
* This model card summarizes details on the models' architecture,
capabilities, limitations, and evaluation processes.
* A responsibly developed open model offers the opportunity to share
innovation by making LLM technology accessible to developers and researchers
across the AI ecosystem.
Risks identified and mitigations:
* Perpetuation of biases: It's encouraged to perform continuous monitoring
(using evaluation metrics, human review) and the exploration of de-biasing
techniques during model training, fine-tuning, and other use cases.
* Generation of harmful content: Mechanisms and guidelines for content safety
are essential. Developers are encouraged to exercise caution and implement
appropriate content safety safeguards based on their specific product policies
and application use cases.
* Misuse for malicious purposes: Technical limitations and developer and
end-user education can help mitigate against malicious applications of LLMs.
Educational resources and reporting mechanisms for users to flag misuse are
provided. Prohibited uses of Gemma models are outlined in the
[Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
* Privacy violations: Models were trained on data filtered for removal of PII
(Personally Identifiable Information). Developers are encouraged to adhere to
privacy regulations with privacy-preserving techniques.
### Benefits
At the time of release, this family of models provides high-performance open
large language model implementations designed from the ground up for Responsible
AI development compared to similarly sized models.
Using the benchmark evaluation metrics described in this document, these models
have shown to provide superior performance to other, comparably-sized open model
alternatives.
|
timm/vit_mediumd_patch16_reg4_gap_256.sbb_in12k_ft_in1k | timm | "2024-05-27T16:04:59Z" | 1,003 | 1 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-12k",
"arxiv:2309.16588",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
] | image-classification | "2024-05-10T23:56:39Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- imagenet-12k
---
# Model card for vit_mediumd_patch16_reg4_gap_256.sbb_in12k_ft_in1k
A Vision Transformer (ViT) image classification model. This is a `timm` specific variation of the architecture with registers, global average pooling.
There are a number of models in the lower end of model scales that originate in `timm`:
| variant | width | mlp width (mult) | heads | depth | timm orig |
| ------- | ----- | ---------------- | ----- | ----- | ---- |
| tiny | 192 | 768 (4) | 3 | 12 | n |
| wee | 256 | 1280 (5) | 4 | 14 | y |
| pwee | 256 | 1280 (5) | 4 | 16 (parallel) | y |
| small | 384 | 1536 (4) | 6 | 12 | n |
| little | 320 | 1792 (5.6) | 5 | 14 | y |
| medium | 512 | 2048 (4) | 8 | 12 | y |
| mediumd | 512 | 2048 (4) | 8 | 20 | y |
| betwixt | 640 | 2560 (4) | 10 | 12 | y |
| base | 768 | 3072 (4) | 12 | 12 | n |
Pretrained on ImageNet-12k and fine-tuned on ImageNet-1k by Ross Wightman in `timm` using recipe template described below.
Recipe details:
* Searching for better baselines. Influced by Swin/DeiT/DeiT-III but w/ increased weight decay, moderate (in12k) to high (in1k) augmentation. Layer-decay used for fine-tune. Some runs used BCE and/or NAdamW instead of AdamW.
* See [train_hparams.yaml](./train_hparams.yaml) for specifics of each model.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 64.1
- GMACs: 16.5
- Activations (M): 24.1
- Image size: 256 x 256
- **Papers:**
- Vision Transformers Need Registers: https://arxiv.org/abs/2309.16588
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-12k
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_mediumd_patch16_reg4_gap_256.sbb_in12k_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(
'vit_mediumd_patch16_reg4_gap_256.sbb_in12k_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, 512, 16, 16])
# torch.Size([1, 512, 16, 16])
# torch.Size([1, 512, 16, 16])
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(
'vit_mediumd_patch16_reg4_gap_256.sbb_in12k_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, 260, 512) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
| model | top1 | top5 | param_count | img_size |
| -------------------------------------------------- | ------ | ------ | ----------- | -------- |
| [vit_mediumd_patch16_reg4_gap_256.sbb_in12k_ft_in1k](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_256.sbb_in12k_ft_in1k) | 86.202 | 97.874 | 64.11 | 256 |
| [vit_betwixt_patch16_reg4_gap_256.sbb_in12k_ft_in1k](https://huggingface.co/timm/vit_betwixt_patch16_reg4_gap_256.sbb_in12k_ft_in1k) | 85.418 | 97.480 | 60.4 | 256 |
| [vit_medium_patch16_reg4_gap_256.sbb_in12k_ft_in1k](https://huggingface.co/timm/vit_medium_patch16_reg4_gap_256.sbb_in12k_ft_in1k) | 84.930 | 97.386 | 38.88 | 256 |
| [vit_mediumd_patch16_rope_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_mediumd_patch16_rope_reg1_gap_256.sbb_in1k) | 84.322 | 96.812 | 63.95 | 256 |
| [vit_betwixt_patch16_rope_reg4_gap_256.sbb_in1k](https://huggingface.co/timm/vit_betwixt_patch16_rope_reg4_gap_256.sbb_in1k) | 83.906 | 96.684 | 60.23 | 256 |
| [vit_base_patch16_rope_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_base_patch16_rope_reg1_gap_256.sbb_in1k) | 83.866 | 96.67 | 86.43 | 256 |
| [vit_medium_patch16_rope_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_medium_patch16_rope_reg1_gap_256.sbb_in1k) | 83.81 | 96.824 | 38.74 | 256 |
| [vit_little_patch16_reg1_gap_256.sbb_in12k_ft_in1k](https://huggingface.co/timm/vit_little_patch16_reg1_gap_256.sbb_in12k_ft_in1k) | 83.774 | 96.972 | 22.52 | 256 |
| [vit_betwixt_patch16_reg4_gap_256.sbb_in1k](https://huggingface.co/timm/vit_betwixt_patch16_reg4_gap_256.sbb_in1k) | 83.706 | 96.616 | 60.4 | 256 |
| [vit_betwixt_patch16_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_betwixt_patch16_reg1_gap_256.sbb_in1k) | 83.628 | 96.544 | 60.4 | 256 |
| [vit_medium_patch16_reg4_gap_256.sbb_in1k](https://huggingface.co/timm/vit_medium_patch16_reg4_gap_256.sbb_in1k) | 83.47 | 96.622 | 38.88 | 256 |
| [vit_medium_patch16_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_medium_patch16_reg1_gap_256.sbb_in1k) | 83.462 | 96.548 | 38.88 | 256 |
| [vit_little_patch16_reg4_gap_256.sbb_in1k](https://huggingface.co/timm/vit_little_patch16_reg4_gap_256.sbb_in1k) | 82.514 | 96.262 | 22.52 | 256 |
| [vit_wee_patch16_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_wee_patch16_reg1_gap_256.sbb_in1k) | 80.258 | 95.360 | 13.42 | 256 |
| [vit_pwee_patch16_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_pwee_patch16_reg1_gap_256.sbb_in1k) | 80.072 | 95.136 | 15.25 | 256 |
## 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{darcet2023vision,
title={Vision Transformers Need Registers},
author={Darcet, Timoth{'e}e and Oquab, Maxime and Mairal, Julien and Bojanowski, Piotr},
journal={arXiv preprint arXiv:2309.16588},
year={2023}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
|
waylandy/phosformer | waylandy | "2022-11-04T18:16:46Z" | 1,002 | 0 | transformers | [
"transformers",
"pytorch",
"roberta",
"text-classification",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2022-11-01T20:35:43Z" | ---
license: other
---
|
timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288 | timm | "2024-02-10T23:42:03Z" | 1,002 | 2 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:1611.05431",
"arxiv:1904.11486",
"arxiv:1512.03385",
"arxiv:1709.01507",
"arxiv:1812.01187",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-04-05T20:37:21Z" | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
---
# Model card for seresnextaa101d_32x8d.sw_in12k_ft_in1k_288
A SE-ResNeXt-D (Rectangle-2 Anti-Aliasing) image classification model with Squeeze-and-Excitation channel attention.
This model features:
* ReLU activations
* 3-layer stem of 3x3 convolutions with pooling
* 2x2 average pool + 1x1 convolution shortcut downsample
* grouped 3x3 bottleneck convolutions
* Squeeze-and-Excitation channel attention
Pretrained on ImageNet-12k and fine-tuned on ImageNet-1k by Ross Wightman in `timm` using recipe template described below.
Recipe details:
* Based on Swin Transformer train / pretrain recipe with modifications (related to both DeiT and ConvNeXt recipes)
* AdamW optimizer, gradient clipping, EMA weight averaging
* Cosine LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 93.6
- GMACs: 28.5
- Activations (M): 56.4
- Image size: train = 288 x 288, test = 320 x 320
- **Papers:**
- Aggregated Residual Transformations for Deep Neural Networks: https://arxiv.org/abs/1611.05431
- Making Convolutional Networks Shift-Invariant Again: https://arxiv.org/abs/1904.11486
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- Squeeze-and-Excitation Networks: https://arxiv.org/abs/1709.01507
- Bag of Tricks for Image Classification with Convolutional Neural Networks: https://arxiv.org/abs/1812.01187
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('seresnextaa101d_32x8d.sw_in12k_ft_in1k_288', 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(
'seresnextaa101d_32x8d.sw_in12k_ft_in1k_288',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 144, 144])
# torch.Size([1, 256, 72, 72])
# torch.Size([1, 512, 36, 36])
# torch.Size([1, 1024, 18, 18])
# torch.Size([1, 2048, 9, 9])
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(
'seresnextaa101d_32x8d.sw_in12k_ft_in1k_288',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 9, 9) 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).
|model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec|
|------------------------------------------|--------|-----|-----|-----------|-----|-----|-------|
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 |
|[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 |
|[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 |
|[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 |
|[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 |
|[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 |
|[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 |
|[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 |
|[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 |
|[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 |
|[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 |
|[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 |
|[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 |
|[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 |
|[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 |
|[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 |
|[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 |
|[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 |
|[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 |
|[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 |
|[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 |
|[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 |
|[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 |
|[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 |
|[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 |
|[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 |
|[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 |
|[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 |
|[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 |
|[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 |
|[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 |
|[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 |
|[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 |
|[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 |
|[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 |
|[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 |
|[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 |
|[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 |
|[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 |
|[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 |
|[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 |
|[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 |
|[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 |
|[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 |
|[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 |
|[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 |
|[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 |
|[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 |
|[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 |
## 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{Xie2016,
title={Aggregated Residual Transformations for Deep Neural Networks},
author={Saining Xie and Ross Girshick and Piotr Dollár and Zhuowen Tu and Kaiming He},
journal={arXiv preprint arXiv:1611.05431},
year={2016}
}
```
```bibtex
@inproceedings{zhang2019shiftinvar,
title={Making Convolutional Networks Shift-Invariant Again},
author={Zhang, Richard},
booktitle={ICML},
year={2019}
}
```
```bibtex
@article{He2015,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Deep Residual Learning for Image Recognition},
journal = {arXiv preprint arXiv:1512.03385},
year = {2015}
}
```
```bibtex
@inproceedings{hu2018senet,
title={Squeeze-and-Excitation Networks},
author={Jie Hu and Li Shen and Gang Sun},
journal={IEEE Conference on Computer Vision and Pattern Recognition},
year={2018}
}
```
```bibtex
@article{He2018BagOT,
title={Bag of Tricks for Image Classification with Convolutional Neural Networks},
author={Tong He and Zhi Zhang and Hang Zhang and Zhongyue Zhang and Junyuan Xie and Mu Li},
journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2018},
pages={558-567}
}
```
|
FFusion/FFusionXL-BASE | FFusion | "2023-08-17T20:52:00Z" | 1,002 | 31 | diffusers | [
"diffusers",
"onnx",
"safetensors",
"openvino",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"stable-diffusion",
"text-to-image",
"di.FFusion.ai",
"en",
"arxiv:2112.10752",
"arxiv:2307.01952",
"arxiv:2106.09685",
"base_model:diffusers/stable-diffusion-xl-base-1.0",
"doi:10.57967/hf/1094",
"license:openrail++",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2023-07-27T14:59:49Z" | ---
license: openrail++
base_model: diffusers/stable-diffusion-xl-base-1.0
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- stable-diffusion
- text-to-image
- diffusers
- di.FFusion.ai
inference: true
widget:
- text: >-
a dog in colorful exploding clouds, dreamlike surrealism colorful smoke and fire coming
out of it, explosion of data fragments, exploding background,realistic explosion, 3d digital art
example_title: Dogo FFusion
- text: >-
a sprinkled donut sitting on top of a table, colorful hyperrealism, everything is made of candy, hyperrealistic digital
painting, covered in sprinkles and crumbs, vibrant colors hyper realism,colorful smoke explosion background
example_title: Donut FFusion
- text: >-
a cup of coffee with a tree in it, surreal art, awesome great composition,
surrealism, ice cubes in tree, colorful clouds, perfectly realistic yet surreal
example_title: CoFFee FFusion
- text: >-
brightly colored headphones with a splash of colorful paint splash, vibing
to music, stunning artwork, music is life, beautiful digital artwork, concept art, cinematic, dramatic, intricate details, dark
lighting
example_title: Headset FFusion
- text: >-
high-quality game character digital design, Unreal Engine, Water color painting, Mecha- Monstrous high quality game fantasy rpg character design, dark rainbow Fur Scarf, inside of a Superficial Outhouse, at Twilight, Overdetailed art
example_title: Digital Fusion
language:
- en
model-index:
- name: FFusion/FFusionXL-BASE
results:
- task:
type: text-to-image
name: Text to Image Generation
dataset:
type: poloclub/diffusiondb
name: DiffusionDB
split: train
metrics:
- type: is
value: 4.9797071218490601
name: Inception Score
verified: true
- type: fid
value: 311.33686580590006
name: Fréchet Inception Distance
verified: true
- type: text-image-similarity
value: 14.368797302246094
name: Similarity Score (CLIP)
thumbnail: >-
https://cdn-uploads.huggingface.co/production/uploads/6380cf05f496d57325c12194/p54u7dEP1u8en0--NMEjS.png
---
<div style="display: flex; flex-wrap: wrap; gap: 2px;">
<a href="https://huggingface.co/FFusion/"><img src="https://img.shields.io/badge/ONNX_Version-Available-brightgreen" alt="ONNX Version Available"></a>
<a href="https://huggingface.co/FFusion/"><img src="https://img.shields.io/badge/OpenVINO-Support-blue" alt="OpenVINO Support"></a>
<a href="https://huggingface.co/FFusion/"><img src="https://img.shields.io/badge/Compatibility-Intel%20|%20AMD%20|%20NVIDIA-orange" alt="Intel/AMD/NVIDIA Compatible"></a>
</div>
## 🌟 Overview
- 🚀 Fast Training: Optimized for high-speed training, allowing rapid experimentation.
- 🧩 Versatility: Suitable for various applications and standards, from NLP to Computer Vision.
- 🎓 Train Your Way: A base for training your own models, tailored to your needs.
- 🌐 Multilingual Support: Train models in multiple languages.
- 🛡️ Robust Architecture: Built on proven technologies to ensure stability and reliability.
## 📜 Model Description
FFusionXL "Base" is a foundational model designed to accelerate training processes. Crafted with flexibility in mind, it serves as a base for training custom models across a variety of standards, enabling innovation and efficiency.
<div style="display: flex; flex-wrap: wrap; gap: 2px;">
<a href="#"><img src="https://img.shields.io/badge/Safetensor-FP16%20%26%20FP32-blue" alt="Safetensor checkpoints"></a>
<a href="#"><img src="https://img.shields.io/badge/Diffusers(Safetensors)-FP16%20%26%20FP32-green" alt="Diffusers(safetensors)"></a>
<a href="#"><img src="https://img.shields.io/badge/Diffusers(PyTorch%20Bin)-FP16%20%26%20FP32-orange" alt="Diffusers(pytorch bin)"></a>
<a href="#"><img src="https://img.shields.io/badge/ONNX-Unoptimized%20FP32-red" alt="ONNX un-optimized FP32"></a>
<a href="#"><img src="https://img.shields.io/badge/ONNX%20Optimized-FP16%20DirectML%20Support-blueviolet" alt="ONNX Optimized FP16 full DirectML support"></a>
<a href="#"><img src="https://img.shields.io/badge/Intel®%20OpenVINO™-FP32%20%26%20FP16-brightgreen" alt="Intel® OpenVINO™ FP32 & FP16"></a>
</div>
**Available formats for training:**
- Safetensor checkpoints fp16 & fp32
- Diffusers(safetensors) FP 16 & FP32
- Diffusers(pytorch bin) FP16 & FP32
- ONNX un-optimzed FP32
- **ONNX Optimized** FP16 full **DirectML** support / AMD / NVIDIA
- Intel® OpenVINO™ FP32 - unoptimized
- **Intel® OpenVINO™** FP16
- **Trained by:** FFusion AI
- **Model type:** Diffusion-based text-to-image generative model
- **License:** [FFXL Research License](https://huggingface.co/FFusion/FFusionXL-09-SDXL/blob/main/LICENSE.md)
- **Model Description:** This is a trained model based on SDXL 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 two fixed, pretrained text encoders ([OpenCLIP-ViT/G](https://github.com/mlfoundations/open_clip) and [CLIP-ViT/L](https://github.com/openai/CLIP/tree/main)).
- **Resources for more information:** [SDXL paper on arXiv](https://arxiv.org/abs/2307.01952).
## 📊 Model Sources
- **Demo:** [FFusionXL SDXL DEMO](https://huggingface.co/spaces/FFusion/FFusionXL-SDXL-DEMO)
## Table of Contents
1. [📌 ONNX Version](#📌-onnx-version)
1. [🔖 ### 📌 ONNX Details](#🔖-###-📌-onnx-details)
2. [🔖 ### 📌 AMD Support for Microsoft® DirectML Optimization of Stable Diffusion](#🔖-###-📌-amd-support-for-microsoft®-directml-optimization-of-stable-diffusion)
3. [🔖 ### 📌 ONNX Inference Instructions](#🔖-###-📌-onnx-inference-instructions)
4. [🔖 ### 📌 Text-to-Image](#🔖-###-📌-text-to-image)
2. [📌 Intel® OpenVINO™ Version](#📌-intel®-openvino™-version)
1. [📌 OpenVINO Inference with FFusion/FFusionXL-BASE](#📌-openvino-inference-with-ffusion/ffusionxl-base)
2. [🔖 ### 📌 Installing Dependencies](#🔖-###-📌-installing-dependencies)
3. [🔖 ### 📌 Text-to-Image](#🔖-###-📌-text-to-image)
4. [🔖 ### 📌 Text-to-Image with Textual Inversion](#🔖-###-📌-text-to-image-with-textual-inversion)
5. [🔖 ### 📌 Image-to-Image](#🔖-###-📌-image-to-image)
6. [🔖 ### 📌 Refining the Image Output](#🔖-###-📌-refining-the-image-output)
3. [📜 Part 003: 🧨 Model Diffusers, Fast LoRa Loading, and Training](#📜-part-001:-🧨-model-diffusers,-fast-lora-loading,-and-training)
1. [📌 Model Diffusers: Unleashing the Power of FFusion/FFusionXL-BASE](#📌-model-diffusers:-unleashing-the-power-of-ffusion/ffusionxl-base)
2. [📌 Installing the dependencies](#📌-installing-the-dependencies)
3. [📌 Training](#📌-training)
4. [📌 Inference](#📌-inference)
5. [📌 Training](#📌-training)
6. [📌 Finetuning the text encoder and UNet](#📌-finetuning-the-text-encoder-and-unet)
7. [📌 Inference](#📌-inference)
4. [📌 Evaluation](#📌-evaluation)
### ### 📌 ONNX Version
We are proud to announce a fully optimized Microsoft ONNX Version exclusively compatible with the latest DirectML Execution Provider. All the ONNX files are optimized (Quantization) to fp16 for fast inference and training across all devices.
The Vae_Decoder is kept at fp32 with settings:
```json
"float16": false,
"use_gpu": true,
"keep_io_types": true,
"force_fp32_ops": ["RandomNormalLike"]
```
to avoid black screens and broken renders. As soon as a proper solution for a full fp16 VAE decoder arrives, we will update it. VAE encoder and everything else is fully optimized 🤟.
Our ONNX is OPTIMIZED using ONNX v8:
- **producer:** onnxruntime.transformers 1.15.1
- **imports:** ai.onnx v18, com.microsoft.nchwc v1, ai.onnx.ml v3, com.ms.internal.nhwc v19, ai.onnx.training v1, ai.onnx.preview.training v1, com.microsoft v1, com.microsoft.experimental v1, org.pytorch.aten v1, com.microsoft.dml v1, graph: torch_jit
#### 🔖 ### 📌 ONNX Details
**NETRON** Detrails:
## Install
**macOS**: [**Download**](https://github.com/lutzroeder/netron/releases/latest) the `.dmg` file or run `brew install --cask netron`
**Linux**: [**Download**](https://github.com/lutzroeder/netron/releases/latest) the `.AppImage` file or run `snap install netron`
**Windows**: [**Download**](https://github.com/lutzroeder/netron/releases/latest) the `.exe` installer or run `winget install -s winget netron`
https://netron.app/
-- **NETRON browser version**: [Start **Text Encoder**](https://netron.app/?url=https://huggingface.co/FFusion/FFusionXL-BASE/blob/main/text_encoder/model.onnx)
[](https://netron.app/?url=https://huggingface.co/FFusion/FFusionXL-BASE/blob/main/text_encoder/model.onnx)
--**NETRON browser version**: [Start **Text Encoder 2**](https://netron.app/?url=https://huggingface.co/FFusion/FFusionXL-BASE/blob/main/text_encoder_2/model.onnx)
[](https://netron.app/?url=https://huggingface.co/FFusion/FFusionXL-BASE/blob/main/text_encoder_2/model.onnx)
--**NETRON browser version**: [Start **VAE decoder**](https://netron.app/?url=https://huggingface.co/FFusion/FFusionXL-BASE/blob/main/vae_decoder/model.onnx)
--**NETRON browser version**: [Start **VAE encoder**](https://netron.app/?url=https://huggingface.co/FFusion/FFusionXL-BASE/blob/main/vae_encoder/model.onnx)
[](https://netron.app/?url=https://huggingface.co/FFusion/FFusionXL-BASE/blob/main/vae_encoder/model.onnx)
--**NETRON browser version**: [Start **UNET**](https://netron.app/?url=https://huggingface.co/stabilityai/FFusion/FFusionXL-BASE/blob/main/unet/model.onnx)
##### 🔖 ### 📌 AMD Support for Microsoft® DirectML Optimization of Stable Diffusion
AMD has released support for Microsoft DirectML optimizations for Stable Diffusion, working closely with Microsoft for optimal performance on AMD devices.
[Microsoft DirectML](https://microsoft.github.io/DirectML/)
[AMD Microsoft DirectML Stable Diffusion](https://gpuopen.com/amd-microsoft-directml-stable-diffusion/)
#### 🔖 ### 📌 ONNX Inference Instructions
##### 🔖 ### 📌 Text-to-Image
Here is an example of how you can load an ONNX Stable Diffusion model and run inference using ONNX Runtime:
```python
from optimum.onnxruntime import ORTStableDiffusionPipeline
model_id = "FFusion/FFusionXL-BASE"
pipeline = ORTStableDiffusionPipeline.from_pretrained(model_id)
prompt = "sailing ship in storm by Leonardo da Vinci"
images = pipeline(prompt).images
```
### ### 📌 Intel® OpenVINO™ Version
A converted Intel® OpenVINO™ model is also included for inference testing and training. No Quantization and optimization applied yet.
---
### ### 📌 OpenVINO Inference with FFusion/FFusionXL-BASE
#### 🔖 ### 📌 Installing Dependencies
Before using `OVStableDiffusionXLPipeline`, make sure to have `diffusers` and `invisible_watermark` installed. You can install the libraries as follows:
```bash
pip install diffusers
pip install invisible-watermark>=0.2.0
```
#### 🔖 ### 📌 Text-to-Image
Here is an example of how you can load a FFusion/FFusionXL-BASE OpenVINO model and run inference using OpenVINO Runtime:
```python
from optimum.intel import OVStableDiffusionXLPipeline
model_id = "FFusion/FFusionXL-BASE"
base = OVStableDiffusionXLPipeline.from_pretrained(model_id)
prompt = "train station by Caspar David Friedrich"
image = base(prompt).images[0]
image.save("train_station.png")
```
#### 🔖 ### 📌 Text-to-Image with Textual Inversion
First, you can run the original pipeline without textual inversion:
```python
from optimum.intel import OVStableDiffusionXLPipeline
import numpy as np
model_id = "FFusion/FFusionXL-BASE"
prompt = "charturnerv2, multiple views of the same character in the same outfit, a character turnaround of a beautiful cyber female wearing a black corset and pink latex shirt, scifi best quality, intricate details."
np.random.seed(0)
base = OVStableDiffusionXLPipeline.from_pretrained(model_id, export=False, compile=False)
base.compile()
image1 = base(prompt, num_inference_steps=50).images[0]
image1.save("sdxl_without_textual_inversion.png")
```
Then, you can load `charturnerv2` textual inversion embedding and run the pipeline with the same prompt again:
```python
# Reset stable diffusion pipeline
base.clear_requests()
# Load textual inversion into stable diffusion pipeline
base.load_textual_inversion("./charturnerv2.pt", "charturnerv2")
# Compile the model before the first inference
base.compile()
image2 = base(prompt, num_inference_steps=50).images[0]
image2.save("sdxl_with_textual_inversion.png")
```
#### 🔖 ### 📌 Image-to-Image
Here is an example of how you can load a PyTorch FFusion/FFusionXL-BASE model, convert it to OpenVINO on-the-fly, and run inference using OpenVINO Runtime for image-to-image:
```python
from optimum.intel import OVStableDiffusionXLImg2ImgPipeline
from diffusers.utils import load_image
model_id = "FFusion/FFusionXL-BASE-refiner-1.0"
pipeline = OVStableDiffusionXLImg2ImgPipeline.from_pretrained(model_id, export=True)
url = "https://huggingface.co/datasets/optimum/documentation-images/resolve/main/intel/openvino/sd_xl/castle_friedrich.png"
image = load_image(url).convert("RGB")
prompt = "medieval castle by Caspar David Friedrich"
image = pipeline(prompt, image=image).images[0]
pipeline.save_pretrained("openvino-FF-xl-refiner-1.0")
```
#### 🔖 ### 📌 Refining the Image Output
The image can be refined by making use of a model like `FFusion/FFusionXL-BASE-refiner-1.0`. In this case, you only have to output the latents from the base model.
```python
from optimum.intel import OVStableDiffusionXLImg2ImgPipeline
model_id = "FFusion/FFusionXL-BASE-refiner-1.0"
refiner = OVStableDiffusionXLImg2ImgPipeline.from_pretrained(model_id, export=True)
image = base(prompt=prompt, output_type="latent").images[0]
image = refiner(prompt=prompt, image=image[None, :]).images[0]
```
## 📜 Part 003: 🧨 Model Diffusers, Fast LoRa Loading, and Training
### ### 📌 Model Diffusers: Unleashing the Power of FFusion/FFusionXL-BASE
Whether you're an artist, researcher, or AI enthusiast, our model is designed to make your journey smooth and exciting.
Make sure to upgrade diffusers to >= 0.19.3:
```bash
pip install diffusers --upgrade
```
In addition, make sure to install `transformers`, `safetensors`, `accelerate`, and the invisible watermark:
```bash
pip install invisible_watermark transformers accelerate safetensors
```
You can use the model then as follows:
```python
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained("FFusion/FFusionXL-09-SDXL", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
pipe.to("cuda")
# if using torch < 2.0
# pipe.enable_xformers_memory_efficient_attention()
prompt = "An astronaut riding a green horse"
images = pipe(prompt=prompt).images[0]
```
## 📜 Diffusers Training Guide: Training FFusion/FFusionXL-BASE with LoRA
# Stable Diffusion XL text-to-image fine-tuning
The `train_text_to_image_sdxl.py` script shows how to fine-tune Stable Diffusion XL (SDXL) on your own dataset.
🚨 This script is experimental. The script fine-tunes the whole model and often times the model overfits and runs into issues like catastrophic forgetting. It's recommended to try different hyperparamters to get the best result on your dataset. 🚨
## 📜 Running locally with PyTorch
### ### 📌 Installing the dependencies
Before running the scripts, make sure to install the library's training dependencies:
**Important**
To make sure you can successfully run the latest versions of the example scripts, we highly recommend **installing from source** and keeping the install up to date as we update the example scripts frequently and install some example-specific requirements. To do this, execute the following steps in a new virtual environment:
```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
```
Then cd in the `examples/text_to_image` folder and run
```bash
pip install -r requirements_sdxl.txt
```
And initialize an [🤗Accelerate](https://github.com/huggingface/accelerate/) environment with:
```bash
accelerate config
```
Or for a default accelerate configuration without answering questions about your environment
```bash
accelerate config default
```
Or if your environment doesn't support an interactive shell (e.g., a notebook)
```python
from accelerate.utils import write_basic_config
write_basic_config()
```
When running `accelerate config`, if we specify torch compile mode to True there can be dramatic speedups.
### ### 📌 Training
```bash
export MODEL_NAME="FFusion/FFusionXL-BASE"
export VAE="madebyollin/sdxl-vae-fp16-fix"
export DATASET_NAME="lambdalabs/pokemon-blip-captions"
accelerate launch train_text_to_image_sdxl.py \
--pretrained_model_name_or_path=$MODEL_NAME \
--pretrained_vae_model_name_or_path=$VAE \
--dataset_name=$DATASET_NAME \
--enable_xformers_memory_efficient_attention \
--resolution=512 --center_crop --random_flip \
--proportion_empty_prompts=0.2 \
--train_batch_size=1 \
--gradient_accumulation_steps=4 --gradient_checkpointing \
--max_train_steps=10000 \
--use_8bit_adam \
--learning_rate=1e-06 --lr_scheduler="constant" --lr_warmup_steps=0 \
--mixed_precision="fp16" \
--report_to="wandb" \
--validation_prompt="a cute Sundar Pichai creature" --validation_epochs 5 \
--checkpointing_steps=5000 \
--output_dir="sdxl-pokemon-model" \
--push_to_hub
```
**Notes**:
* The `train_text_to_image_sdxl.py`(diffusers/examples/text_to_image) script pre-computes text embeddings and the VAE encodings and keeps them in memory. While for smaller datasets like [`lambdalabs/pokemon-blip-captions`](https://hf.co/datasets/lambdalabs/pokemon-blip-captions), it might not be a problem, it can definitely lead to memory problems when the script is used on a larger dataset. For those purposes, you would want to serialize these pre-computed representations to disk separately and load them during the fine-tuning process. Refer to [this PR](https://github.com/huggingface/diffusers/pull/4505) for a more in-depth discussion.
* The training script is compute-intensive and may not run on a consumer GPU like Tesla T4.
* The training command shown above performs intermediate quality validation in between the training epochs and logs the results to Weights and Biases. `--report_to`, `--validation_prompt`, and `--validation_epochs` are the relevant CLI arguments here.
examples/text_to_image
### ### 📌 Inference
```python
from diffusers import DiffusionPipeline
import torch
model_path = "FFusion/FFusionXL-BASE" # <-- change this to your new trained model
pipe = DiffusionPipeline.from_pretrained(model_path, torch_dtype=torch.float16)
pipe.to("cuda")
prompt = "A pokemon with green eyes and red legs."
image = pipe(prompt, num_inference_steps=30, guidance_scale=7.5).images[0]
image.save("pokemon.png")
```
## 📜 LoRA training example for Stable Diffusion XL (SDXL)
Low-Rank Adaption of Large Language Models was first introduced by Microsoft in [LoRA: Low-Rank Adaptation of Large Language Models](https://arxiv.org/abs/2106.09685) by *Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen*.
In a nutshell, LoRA allows adapting pretrained models by adding pairs of rank-decomposition matrices to existing weights and **only** training those newly added weights. This has a couple of advantages:
- Previous pretrained weights are kept frozen so that model is not prone to [catastrophic forgetting](https://www.pnas.org/doi/10.1073/pnas.1611835114).
- Rank-decomposition matrices have significantly fewer parameters than original model, which means that trained LoRA weights are easily portable.
- LoRA attention layers allow to control to which extent the model is adapted toward new training images via a `scale` parameter.
[cloneofsimo](https://github.com/cloneofsimo) was the first to try out LoRA training for Stable Diffusion in the popular [lora](https://github.com/cloneofsimo/lora) GitHub repository.
With LoRA, it's possible to fine-tune Stable Diffusion on a custom image-caption pair dataset
on consumer GPUs like Tesla T4, Tesla V100.
### ### 📌 Training
First, you need to set up your development environment as is explained in the [installation section](#installing-the-dependencies). Make sure to set the `MODEL_NAME` and `DATASET_NAME` environment variables. Here, we will use [Stable Diffusion XL 1.0-base](https://huggingface.co/FFusion/FFusionXL-BASE) and the [Pokemons dataset](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions).
**___Note: It is quite useful to monitor the training progress by regularly generating sample images during training. [Weights and Biases](https://docs.wandb.ai/quickstart) is a nice solution to easily see generating images during training. All you need to do is to run `pip install wandb` before training to automatically log images.___**
```bash
export MODEL_NAME="FFusion/FFusionXL-BASE"
export DATASET_NAME="lambdalabs/pokemon-blip-captions"
```
For this example we want to directly store the trained LoRA embeddings on the Hub, so
we need to be logged in and add the `--push_to_hub` flag.
```bash
huggingface-cli login
```
Now we can start training!
```bash
accelerate launch train_text_to_image_lora_sdxl.py \
--pretrained_model_name_or_path=$MODEL_NAME \
--dataset_name=$DATASET_NAME --caption_column="text" \
--resolution=1024 --random_flip \
--train_batch_size=1 \
--num_train_epochs=2 --checkpointing_steps=500 \
--learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0 \
--seed=42 \
--output_dir="sd-pokemon-model-lora-sdxl" \
--validation_prompt="cute dragon creature" --report_to="wandb" \
--push_to_hub
```
The above command will also run inference as fine-tuning progresses and log the results to Weights and Biases.
### ### 📌 Finetuning the text encoder and UNet
The script also allows you to finetune the `text_encoder` along with the `unet`.
🚨 Training the text encoder requires additional memory.
Pass the `--train_text_encoder` argument to the training script to enable finetuning the `text_encoder` and `unet`:
```bash
accelerate launch train_text_to_image_lora_sdxl.py \
--pretrained_model_name_or_path=$MODEL_NAME \
--dataset_name=$DATASET_NAME --caption_column="text" \
--resolution=1024 --random_flip \
--train_batch_size=1 \
--num_train_epochs=2 --checkpointing_steps=500 \
--learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0 \
--seed=42 \
--output_dir="sd-pokemon-model-lora-sdxl-txt" \
--train_text_encoder \
--validation_prompt="cute dragon creature" --report_to="wandb" \
--push_to_hub
```
### ### 📌 Inference
Once you have trained a model using above command, the inference can be done simply using the `DiffusionPipeline` after loading the trained LoRA weights. You
need to pass the `output_dir` for loading the LoRA weights which, in this case, is `sd-pokemon-model-lora-sdxl`.
```python
from diffusers import DiffusionPipeline
import torch
model_path = "takuoko/sd-pokemon-model-lora-sdxl"
pipe = DiffusionPipeline.from_pretrained("FFusion/FFusionXL-BASE", torch_dtype=torch.float16)
pipe.to("cuda")
pipe.load_lora_weights(model_path)
prompt = "A pokemon with green eyes and red legs."
image = pipe(prompt, num_inference_steps=30, guidance_scale=7.5).images[0]
image.save("pokemon.png")
```
### ### 📌 Evaluation
Utilizing yuvalkirstain/PickScore_v1 model, this analysis was conducted by FFusion.AI. It serves as a vital contribution to the ongoing research in testing Stable Diffusion Models' prompt win rate and accuracy.
📧 For any inquiries or support, please contact [email protected]. We're here to help you every step of the way!
|
porkorbeef/Llama-2-13b-sf | porkorbeef | "2023-08-21T05:58:05Z" | 1,002 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"feature-extraction",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | feature-extraction | "2023-08-21T01:50:43Z" | ---
license: cc-by-nc-4.0
---
Hi |
TheBloke/Mistral-7B-codealpaca-lora-GGUF | TheBloke | "2023-10-28T12:39:52Z" | 1,002 | 10 | transformers | [
"transformers",
"gguf",
"mistral",
"code",
"base_model:Nondzu/Mistral-7B-codealpaca-lora",
"license:apache-2.0",
"text-generation-inference",
"region:us"
] | null | "2023-10-28T08:57:12Z" | ---
base_model: Nondzu/Mistral-7B-codealpaca-lora
inference: false
license: apache-2.0
model_creator: Kamil
model_name: Mistral 7B CodeAlpaca Lora
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:
- code
- mistral
---
<!-- 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 -->
# Mistral 7B CodeAlpaca Lora - GGUF
- Model creator: [Kamil](https://huggingface.co/Nondzu)
- Original model: [Mistral 7B CodeAlpaca Lora](https://huggingface.co/Nondzu/Mistral-7B-codealpaca-lora)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Kamil's Mistral 7B CodeAlpaca Lora](https://huggingface.co/Nondzu/Mistral-7B-codealpaca-lora).
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/Mistral-7B-codealpaca-lora-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF)
* [Kamil's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Nondzu/Mistral-7B-codealpaca-lora)
<!-- 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-7b-codealpaca-lora.Q2_K.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [mistral-7b-codealpaca-lora.Q3_K_S.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [mistral-7b-codealpaca-lora.Q3_K_M.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [mistral-7b-codealpaca-lora.Q3_K_L.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [mistral-7b-codealpaca-lora.Q4_0.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [mistral-7b-codealpaca-lora.Q4_K_S.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [mistral-7b-codealpaca-lora.Q4_K_M.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [mistral-7b-codealpaca-lora.Q5_0.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [mistral-7b-codealpaca-lora.Q5_K_S.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [mistral-7b-codealpaca-lora.Q5_K_M.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [mistral-7b-codealpaca-lora.Q6_K.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [mistral-7b-codealpaca-lora.Q8_0.gguf](https://huggingface.co/TheBloke/Mistral-7B-codealpaca-lora-GGUF/blob/main/mistral-7b-codealpaca-lora.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/Mistral-7B-codealpaca-lora-GGUF and below it, a specific filename to download, such as: mistral-7b-codealpaca-lora.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-7B-codealpaca-lora-GGUF mistral-7b-codealpaca-lora.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-7B-codealpaca-lora-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-7B-codealpaca-lora-GGUF mistral-7b-codealpaca-lora.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-7b-codealpaca-lora.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-7B-codealpaca-lora-GGUF", model_file="mistral-7b-codealpaca-lora.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 Mistral 7B CodeAlpaca Lora
# Mistral-7B-codealpaca
I am thrilled to introduce my Mistral-7B-codealpaca model. This variant is optimized and demonstrates potential in assisting developers as a coding companion. I welcome contributions from testers and enthusiasts to help evaluate its performance.
## Training Details
I trained the model using 3xRTX 3090 for 118 hours.
[](https://github.com/OpenAccess-AI-Collective/axolotl)
## Quantised Model Links:
1.
2.
3.
## Dataset:
- Dataset Name: theblackcat102/evol-codealpaca-v1
- Dataset Link: [theblackcat102/evol-codealpaca-v1](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
## Performance (evalplus)
Human eval plus: https://github.com/evalplus/evalplus
Well, the results are better than I expected:
- Base: `{'pass@1': 0.47560975609756095}`
- Base + Extra: `{'pass@1': 0.4329268292682927}`
For reference, I've provided the performance of the original Mistral model alongside my Mistral-7B-code-16k-qlora model.
** [Nondzu/Mistral-7B-code-16k-qlora](https://huggingface.co/Nondzu/Mistral-7B-code-16k-qlora)**:
- Base: `{'pass@1': 0.3353658536585366}`
- Base + Extra: `{'pass@1': 0.2804878048780488}`
** [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)**:
- Base: `{'pass@1': 0.2926829268292683}`
- Base + Extra: `{'pass@1': 0.24390243902439024}`
## Model Configuration:
Here are the configurations for my Mistral-7B-codealpaca-lora:
```yaml
base_model: mistralai/Mistral-7B-Instruct-v0.1
base_model_config: mistralai/Mistral-7B-Instruct-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: true
load_in_4bit: false
strict: false
datasets:
- path: theblackcat102/evol-codealpaca-v1
type: oasst
dataset_prepared_path:
val_set_size: 0.01
output_dir: ./nondzu/Mistral-7B-codealpaca-test14
adapter: lora
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
```
## Additional Projects:
For other related projects, you can check out:
- [LlamaTor on GitHub](https://github.com/Nondzu/LlamaTor)
<!-- original-model-card end -->
|
rizla/raccoon-small | rizla | "2024-02-02T07:33:56Z" | 1,002 | 1 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"dpo",
"base_model:mistralai/Mixtral-8x7B-Instruct-v0.1",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-02T06:43:23Z" | ---
license: cc-by-nc-4.0
base_model: [mistralai/Mixtral-8x7B-Instruct-v0.1]
tags:
- dpo
---
# rizla been cooking while singing
# This is an experimental model that I made by merging two 2expmixtrals The mergekitty is a tool that lets me mix and match different models into one big model, keeping all the smarts and skills of the original models. The llama70b is a huge language model that can make words for all kinds of things and ways, based on the GPT-4 thingy.
The merged model has 19 billion parraraameters and was made trained on 640GB of vram cluster
## Merge me baby one more time
### Sending this contraption out straight to mergeland, would be hilarious if it gets 1st |
InnerI/InnerILLM-7B-slerp | InnerI | "2024-05-10T00:03:59Z" | 1,002 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"OpenPipe/mistral-ft-optimized-1218",
"mlabonne/NeuralHermes-2.5-Mistral-7B",
"base_model:OpenPipe/mistral-ft-optimized-1218",
"base_model:mlabonne/NeuralHermes-2.5-Mistral-7B",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-12T23:49:46Z" | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- OpenPipe/mistral-ft-optimized-1218
- mlabonne/NeuralHermes-2.5-Mistral-7B
base_model:
- OpenPipe/mistral-ft-optimized-1218
- mlabonne/NeuralHermes-2.5-Mistral-7B
model-index:
- name: InnerILLM-7B-slerp
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: 67.58
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/InnerILLM-7B-slerp
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: 86.19
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/InnerILLM-7B-slerp
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: 64.15
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/InnerILLM-7B-slerp
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: 59.84
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/InnerILLM-7B-slerp
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: 80.11
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/InnerILLM-7B-slerp
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: 68.69
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/InnerILLM-7B-slerp
name: Open LLM Leaderboard
---
# InnerILLM-7B-slerp
InnerILLM-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)
* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
# Average model loss 0.8070214592665433
I used this testing script that loads your local model, pulls the latest data from cortex and calculates the loss:
[avg loss script](https://gist.github.com/romanorac/59ccde7cbf07d8950ef9fb5b5db6a24e)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: OpenPipe/mistral-ft-optimized-1218
layer_range: [0, 32]
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
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/InnerILLM-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"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_InnerI__InnerILLM-7B-slerp)
| Metric |Value|
|---------------------------------|----:|
|Avg. |71.09|
|AI2 Reasoning Challenge (25-Shot)|67.58|
|HellaSwag (10-Shot) |86.19|
|MMLU (5-Shot) |64.15|
|TruthfulQA (0-shot) |59.84|
|Winogrande (5-shot) |80.11|
|GSM8k (5-shot) |68.69|
|
PrunaAI/dolphin-2.9-llama3-8b-GGUF-smashed | PrunaAI | "2024-04-23T12:56:21Z" | 1,002 | 3 | null | [
"gguf",
"pruna-ai",
"region:us"
] | null | "2024-04-23T11:04:26Z" | ---
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 cognitivecomputations/dolphin-2.9-llama3-8b 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/dolphin-2.9-llama3-8b-GGUF-smashed-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/dolphin-2.9-llama3-8b-GGUF-smashed-smashed dolphin-2.9-llama3-8b.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/dolphin-2.9-llama3-8b-GGUF-smashed-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/dolphin-2.9-llama3-8b-GGUF-smashed-smashed dolphin-2.9-llama3-8b.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 dolphin-2.9-llama3-8b.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="./dolphin-2.9-llama3-8b.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="./dolphin-2.9-llama3-8b.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).
|
dddump/Japanese-Chat-Evolve-TEST-7B-NSFW-gguf | dddump | "2024-05-18T03:21:32Z" | 1,002 | 15 | null | [
"gguf",
"not-for-all-audiences",
"text-generation",
"ja",
"region:us"
] | text-generation | "2024-05-02T08:44:48Z" | ---
language:
- ja
pipeline_tag: text-generation
tags:
- not-for-all-audiences
---
Model for test of Mergekit-Evolve
For personal use only
### Example
```
USER: あなたについて自己紹介をしてください
ASSISTANT: 私は、風俗好きでエッチ大好きな親切で誠実なアシスタント、通称「じゅんこちゃん」と呼ばれております。
私はお客様に快適なサービスを提供する為、24時間体制でお客様の身近に存在しております。よろしくお願い致します。
ユーザー様はお好みのプレイスタイルや女性、出張先等どうぞ気軽にご相談下さいね♪
``` |
NikolayKozloff/xTower13B-Q6_K-GGUF | NikolayKozloff | "2024-06-27T17:09:44Z" | 1,002 | 1 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"translation",
"en",
"de",
"zh",
"ru",
"he",
"fr",
"pt",
"nl",
"ko",
"it",
"es",
"dataset:Unbabel/TowerBlocks-v0.1",
"base_model:sardinelab/xTower13B",
"license:cc-by-nc-4.0",
"region:us"
] | translation | "2024-06-27T17:09:02Z" | ---
base_model: sardinelab/xTower13B
datasets:
- Unbabel/TowerBlocks-v0.1
language:
- en
- de
- zh
- ru
- he
- fr
- pt
- nl
- ko
- it
- es
license: cc-by-nc-4.0
metrics:
- comet
pipeline_tag: translation
tags:
- llama-cpp
- gguf-my-repo
---
# NikolayKozloff/xTower13B-Q6_K-GGUF
This model was converted to GGUF format from [`sardinelab/xTower13B`](https://huggingface.co/sardinelab/xTower13B) 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/sardinelab/xTower13B) 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/xTower13B-Q6_K-GGUF --hf-file xtower13b-q6_k.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo NikolayKozloff/xTower13B-Q6_K-GGUF --hf-file xtower13b-q6_k.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/xTower13B-Q6_K-GGUF --hf-file xtower13b-q6_k.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo NikolayKozloff/xTower13B-Q6_K-GGUF --hf-file xtower13b-q6_k.gguf -c 2048
```
|
uer/gpt2-chinese-lyric | uer | "2023-10-17T15:13:00Z" | 1,001 | 27 | transformers | [
"transformers",
"pytorch",
"tf",
"jax",
"gpt2",
"text-generation",
"zh",
"arxiv:1909.05658",
"arxiv:2212.06385",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-03-02T23:29:05Z" | ---
language: zh
widget:
- text: "最美的不是下雨天，是曾与你躲过雨的屋檐"
---
# Chinese GPT2 Lyric Model
## Model description
The model is pre-trained by [UER-py](https://github.com/dbiir/UER-py/), which is introduced in [this paper](https://arxiv.org/abs/1909.05658). Besides, the model could also be pre-trained by [TencentPretrain](https://github.com/Tencent/TencentPretrain) introduced in [this paper](https://arxiv.org/abs/2212.06385), which inherits UER-py to support models with parameters above one billion, and extends it to a multimodal pre-training framework.
The model is used to generate Chinese lyrics. You can download the model from the [UER-py Modelzoo page](https://github.com/dbiir/UER-py/wiki/Modelzoo), or [GPT2-Chinese Github page](https://github.com/Morizeyao/GPT2-Chinese), or via HuggingFace from the link [gpt2-chinese-lyric](https://huggingface.co/uer/gpt2-chinese-lyric)
## How to use
You can use the model directly with a pipeline for text generation:
```python
>>> from transformers import BertTokenizer, GPT2LMHeadModel, TextGenerationPipeline
>>> tokenizer = BertTokenizer.from_pretrained("uer/gpt2-chinese-lyric")
>>> model = GPT2LMHeadModel.from_pretrained("uer/gpt2-chinese-lyric")
>>> text_generator = TextGenerationPipeline(model, tokenizer)
>>> text_generator("最美的不是下雨天，是曾与你躲过雨的屋檐", max_length=100, do_sample=True)
[{'generated_text': '最美的不是下雨天，是曾与你躲过雨的屋檐 ， 下 课 铃 声 响 起 的 瞬 间 ， 我 们 的 笑 脸 ， 有 太 多 回 忆 在 浮 现 ， 是 你 总 在 我 身 边 ， 不 知 道 会 不 会 再 见 ， 从 现 在 开 始 到 永 远 ， 想 说 的 语 言 凝 结 成 一 句 ， 不 管 我 们 是 否 能 够 兑 现 ， 想 说 的 语 言 凝 结'}]
```
## Training data
Training data contains 150,000 Chinese lyrics which are collected by [Chinese-Lyric-Corpus](https://github.com/gaussic/Chinese-Lyric-Corpus) and [MusicLyricChatbot](https://github.com/liuhuanyong/MusicLyricChatbot).
## Training procedure
The model is pre-trained by [UER-py](https://github.com/dbiir/UER-py/) on [Tencent Cloud](https://cloud.tencent.com/). We pre-train 100,000 steps with a sequence length of 512 on the basis of the pre-trained model [gpt2-base-chinese-cluecorpussmall](https://huggingface.co/uer/gpt2-base-chinese-cluecorpussmall)
```
python3 preprocess.py --corpus_path corpora/lyric.txt \
--vocab_path models/google_zh_vocab.txt \
--dataset_path lyric_dataset.pt --processes_num 32 \
--seq_length 512 --data_processor lm
```
```
python3 pretrain.py --dataset_path lyric_dataset.pt \
--pretrained_model_path models/cluecorpussmall_gpt2_seq1024_model.bin-250000 \
--vocab_path models/google_zh_vocab.txt \
--config_path models/gpt2/config.json \
--output_model_path models/lyric_gpt2_model.bin \
--world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
--total_steps 100000 --save_checkpoint_steps 10000 --report_steps 5000 \
--learning_rate 5e-5 --batch_size 64
```
Finally, we convert the pre-trained model into Huggingface's format:
```
python3 scripts/convert_gpt2_from_uer_to_huggingface.py --input_model_path models/lyric_gpt2_model.bin-100000 \
--output_model_path pytorch_model.bin \
--layers_num 12
```
### BibTeX entry and citation info
```
@article{radford2019language,
title={Language Models are Unsupervised Multitask Learners},
author={Radford, Alec and Wu, Jeff and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya},
year={2019}
}
@article{zhao2019uer,
title={UER: An Open-Source Toolkit for Pre-training Models},
author={Zhao, Zhe and Chen, Hui and Zhang, Jinbin and Zhao, Xin and Liu, Tao and Lu, Wei and Chen, Xi and Deng, Haotang and Ju, Qi and Du, Xiaoyong},
journal={EMNLP-IJCNLP 2019},
pages={241},
year={2019}
}
@article{zhao2023tencentpretrain,
title={TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities},
author={Zhao, Zhe and Li, Yudong and Hou, Cheng and Zhao, Jing and others},
journal={ACL 2023},
pages={217},
year={2023}
}
``` |
DrNicefellow/ChatAllInOne-Yi-34B-200K-V1 | DrNicefellow | "2024-06-26T16:56:25Z" | 1,001 | 8 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:DrNicefellow/CHAT-ALL-IN-ONE-v1",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-30T03:03:36Z" | ---
datasets:
- DrNicefellow/CHAT-ALL-IN-ONE-v1
license: apache-2.0
---
# ChatAllInOne-Yi-34B-200K-V1
## Description
ChatAllInOne-Yi-34B-200K-V1 is a chat language model fine-tuned on the CHAT-ALL-IN-ONE-v1 dataset using the QLoRA technique with the unsloth tool. Originally based on the 01-ai/Yi-34B-200K model, this version is specifically optimized for diverse and comprehensive chat applications.
## Model Details
- **Base Model**: [01-ai/Yi-34B-200K](https://huggingface.co/01-ai/Yi-34B-200K)
- **Fine-tuning Technique**: QLoRA
- **Dataset**: [CHAT-ALL-IN-ONE-v1](https://huggingface.co/datasets/DrNicefellow/CHAT-ALL-IN-ONE-v1)
- **Tool Used for Fine-tuning**: [unsloth](https://github.com/unslothai/unsloth)
## Features
- Enhanced understanding and generation of conversational language.
- Improved performance in diverse chat scenarios, including casual, formal, and domain-specific conversations.
- Fine-tuned to maintain context and coherence over longer dialogues.
## Prompt Format
Vicuna 1.1
See the finetuning dataset for examples.
## License
This model is open-sourced under the [Yi License](https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE).
## Discord Server
Join our Discord server [here](https://discord.gg/xhcBDEM3).
## Feeling Generous? 😊
Eager to buy me a cup of 2$ coffe or iced tea?🍵☕ Sure, here is the link: [https://ko-fi.com/drnicefellow](https://ko-fi.com/drnicefellow). Please add a note on which one you want me to drink? |
OwenArli/Awanllm-Llama-3-8B-Cumulus-v0.2-GGUF | OwenArli | "2024-05-03T03:15:09Z" | 1,001 | 5 | null | [
"gguf",
"license:llama3",
"region:us"
] | null | "2024-05-02T22:44:11Z" | ---
license: llama3
---
Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement:
https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
This is by far the most completely uncensored Llama 3 8b instruct model. It will literally never refuse anything.
So as a reminder, with great power comes great responsibility.
In terms of reasoning and intelligence, this model is probably worse than the OG model because of the decensoring. However, if you have issues with refusals then this will be superior just because it will not refuse.
Will soon have quants uploaded here on HF and have it up on our site https://awanllm.com for anyone to try.
OpenLLM Benchmark:
Training:
- 4096 sequence length, while the base model is 8192 sequence length. From testing it still performs the same 8192 context just fine.
- Training duration is around 3 days on an RTX 4090, using 4-bit loading and Qlora 64-rank 128-alpha resulting in ~2% trainable weights.
- Added DPO fine tuning aside from a more curated dataset for this v0.2 model.
Instruct format:
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
Quants:
FP16: https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Cumulus-v0.2
GGUF: https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Cumulus-v0.2-GGUF
|
aisuko/gpt2-xl-gguf | aisuko | "2024-06-23T12:17:48Z" | 1,001 | 0 | null | [
"gguf",
"license:mit",
"region:us"
] | null | "2024-06-23T12:11:51Z" | ---
license: mit
---
# The result of 1.5B GPT2
```markdown
system_info: n_threads = 4 / 8 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 |
main: interactive mode on.
Reverse prompt: 'User:'
sampling:
repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampling order:
CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature
generate: n_ctx = 1024, n_batch = 2048, n_predict = 256, n_keep = 0
== Running in interactive mode. ==
- Press Ctrl+C to interject at any time.
- Press Return to return control to the AI.
- To return control without starting a new line, end your input with '/'.
- If you want to submit another line, end your input with '\'.
Transcript of a dialog, where the User interacts with an Assistant named Bob. Bob is helpful, kind, honest, good at writing, and never fails to answer the User's requests immediately and with precision.
User: Hello, Bob.
Bob: Hello. How may I help you today?
User: Please tell me the largest city in Europe.
Bob: Sure. The largest city in Europe is Moscow, the capital of Russia.
User:What is the largest city in Australia?
Bob: The largest city in Australia is Melbourne, the capital of Victoria.
User:What is the largest city in US
Bob: The largest city in US is Los Angeles, the capital of California.
User:thanks
Bob:Thanks for calling.
Bob is not a robot, and may be a human being who is not a robot. Bob is an Assistant that is helpful, kind, honest, good at writing and never fails to answer the User's requests.
User:
llama_print_timings: load time = 227.51 ms
llama_print_timings: sample time = 3.31 ms / 97 runs ( 0.03 ms per token, 29269.76 tokens per second)
llama_print_timings: prompt eval time = 29632.23 ms / 116 tokens ( 255.45 ms per token, 3.91 tokens per second)
llama_print_timings: eval time = 4239.84 ms / 94 runs ( 45.10 ms per token, 22.17 tokens per second)
llama_print_timings: total time = 76118.37 ms / 210 tokens
```
|
DeepPavlov/distilrubert-tiny-cased-conversational-v1 | DeepPavlov | "2022-05-06T11:57:05Z" | 1,000 | 2 | transformers | [
"transformers",
"pytorch",
"distilbert",
"ru",
"arxiv:2205.02340",
"endpoints_compatible",
"region:us"
] | null | "2022-03-02T23:29:04Z" | ---
language:
- ru
---
# distilrubert-tiny-cased-conversational
Conversational DistilRuBERT-tiny \(Russian, cased, 3‑layers, 264‑hidden, 12‑heads, 10.4M parameters\) was trained on OpenSubtitles\[1\], [Dirty](https://d3.ru/), [Pikabu](https://pikabu.ru/), and a Social Media segment of Taiga corpus\[2\] (as [Conversational RuBERT](https://huggingface.co/DeepPavlov/rubert-base-cased-conversational)). It can be considered as tiny copy of [Conversational DistilRuBERT-small](https://huggingface.co/DeepPavlov/distilrubert-tiny-cased-conversational).
Our DistilRuBERT-tiny is highly inspired by \[3\], \[4\] and architecture is very close to \[5\]. Namely, we use
* MLM loss (between token labels and student output distribution)
* MSE loss (between averaged student and teacher hidden states)
The key features are:
* unlike most of distilled language models, we **didn't** use KL loss during pre-training
* reduced vocabulary size (30K in *tiny* vs. 100K in *base* and *small* )
* two separate inputs for student: tokens obtained using student tokenizer (for MLM) and teacher tokens greedily splitted by student tokens (for MSE)
Here is comparison between teacher model (`Conversational RuBERT`) and other distilled models.
| Model name | \# params, M | \# vocab, K | Mem., MB |
|---|---|---|---|
| `rubert-base-cased-conversational` | 177.9 | 120 | 679 |
| `distilrubert-base-cased-conversational` | 135.5 | 120 | 517 |
| `distilrubert-small-cased-conversational` | 107.1 | 120 | 409 |
| `cointegrated/rubert-tiny` | 11.8 | **30** | 46 |
| **distilrubert-tiny-cased-conversational** | **10.4** | 31 | **41** |
DistilRuBERT-tiny was trained for about 100 hrs. on 7 nVIDIA Tesla P100-SXM2.0 16Gb.
We used `PyTorchBenchmark` from `transformers` to evaluate model's performance and compare it with other pre-trained language models for Russian. All tests were performed on Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz and nVIDIA Tesla P100-SXM2.0 16Gb.
| Model name | Batch size | Seq len | Time, s || Mem, MB ||
|---|---|---|------||------||
| | | | CPU | GPU | CPU | GPU |
| `rubert-base-cased-conversational` | 1 | 512 | 0.147 | 0.014 | 897 | 1531 |
| `distilrubert-base-cased-conversational` | 1 | 512 | 0.083 | 0.006 | 766 | 1423 |
| `distilrubert-small-cased-conversational` | 1 | 512 | 0.03 | **0.002** | 600 | 1243 |
| `cointegrated/rubert-tiny` | 1 | 512 | 0.041 | 0.003 | 272 | 919 |
| **distilrubert-tiny-cased-conversational** | 1 | 512 | **0.023** | 0.003 | **206** | **855** |
| `rubert-base-cased-conversational` | 16 | 512 | 2.839 | 0.182 | 1499 | 2071 |
| `distilrubert-base-cased-conversational` | 16 | 512 | 1.065 | 0.055 | 2541 | 2927 |
| `distilrubert-small-cased-conversational` | 16 | 512 | 0.373 | **0.003** | 1360 | 1943 |
| `cointegrated/rubert-tiny` | 16 | 512 | 0.628 | 0.004 | 1293 | 2221 |
| **distilrubert-tiny-cased-conversational** | 16 | 512 | **0.219** | **0.003** | **633** | **1291** |
To evaluate model quality, we fine-tuned DistilRuBERT-tiny on classification (RuSentiment, ParaPhraser), NER and question answering data sets for Russian and obtained scores very similar to the [Conversational DistilRuBERT-small](https://huggingface.co/DeepPavlov/distilrubert-tiny-cased-conversational).
# Citation
If you found the model useful for your research, we are kindly ask to cite [this](https://arxiv.org/abs/2205.02340) paper:
```
@misc{https://doi.org/10.48550/arxiv.2205.02340,
doi = {10.48550/ARXIV.2205.02340},
url = {https://arxiv.org/abs/2205.02340},
author = {Kolesnikova, Alina and Kuratov, Yuri and Konovalov, Vasily and Burtsev, Mikhail},
keywords = {Computation and Language (cs.CL), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Knowledge Distillation of Russian Language Models with Reduction of Vocabulary},
publisher = {arXiv},
year = {2022},
copyright = {arXiv.org perpetual, non-exclusive license}
}
```
\[1\]: P. Lison and J. Tiedemann, 2016, OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles. In Proceedings of the 10th International Conference on Language Resources and Evaluation \(LREC 2016\)
\[2\]: Shavrina T., Shapovalova O. \(2017\) TO THE METHODOLOGY OF CORPUS CONSTRUCTION FOR MACHINE LEARNING: «TAIGA» SYNTAX TREE CORPUS AND PARSER. in proc. of “CORPORA2017”, international conference , Saint-Petersbourg, 2017.
\[3\]: Sanh, V., Debut, L., Chaumond, J., & Wolf, T. \(2019\). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108.
\[4\]: <https://github.com/huggingface/transformers/tree/master/examples/research_projects/distillation>
\[5\]: <https://habr.com/ru/post/562064/>, <https://huggingface.co/cointegrated/rubert-tiny> |
eugenesiow/drln | eugenesiow | "2021-09-20T01:00:50Z" | 1,000 | 3 | transformers | [
"transformers",
"DRLN",
"super-image",
"image-super-resolution",
"dataset:eugenesiow/Div2k",
"dataset:eugenesiow/Set5",
"dataset:eugenesiow/Set14",
"dataset:eugenesiow/BSD100",
"dataset:eugenesiow/Urban100",
"arxiv:1906.12021",
"arxiv:2104.07566",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2022-03-02T23:29:05Z" | ---
license: apache-2.0
tags:
- super-image
- image-super-resolution
datasets:
- eugenesiow/Div2k
- eugenesiow/Set5
- eugenesiow/Set14
- eugenesiow/BSD100
- eugenesiow/Urban100
metrics:
- pnsr
- ssim
---
# Densely Residual Laplacian Super-Resolution (DRLN)
DRLN model pre-trained on DIV2K (800 images training, augmented to 4000 images, 100 images validation) for 2x, 3x and 4x image super resolution. It was introduced in the paper [Densely Residual Laplacian Super-resolution](https://arxiv.org/abs/1906.12021) by Anwar et al. (2020) and first released in [this repository](https://github.com/saeed-anwar/DRLN).
The goal of image super resolution is to restore a high resolution (HR) image from a single low resolution (LR) image. The image below shows the ground truth (HR), the bicubic upscaling and model upscaling.
## Model description
Super-Resolution convolutional neural networks have recently demonstrated high-quality restoration for single images. However, existing algorithms often require very deep architectures and long training times. Furthermore, current convolutional neural networks for super-resolution are unable to exploit features at multiple scales and weigh them equally, limiting their learning capability. In this exposition, we present a compact and accurate super-resolution algorithm namely, Densely Residual Laplacian Network (DRLN). The proposed network employs cascading residual on the residual structure to allow the flow of low-frequency information to focus on learning high and mid-level features. In addition, deep supervision is achieved via the densely concatenated residual blocks settings, which also helps in learning from high-level complex features. Moreover, we propose Laplacian attention to model the crucial features to learn the inter and intra-level dependencies between the feature maps. Furthermore, comprehensive quantitative and qualitative evaluations on low-resolution, noisy low-resolution, and real historical image benchmark datasets illustrate that our DRLN algorithm performs favorably against the state-of-the-art methods visually and accurately.
## Intended uses & limitations
You can use the pre-trained models for upscaling your images 2x, 3x and 4x. You can also use the trainer to train a model on your own dataset.
### How to use
The model can be used with the [super_image](https://github.com/eugenesiow/super-image) library:
```bash
pip install super-image
```
Here is how to use a pre-trained model to upscale your image:
```python
from super_image import DrlnModel, ImageLoader
from PIL import Image
import requests
url = 'https://paperswithcode.com/media/datasets/Set5-0000002728-07a9793f_zA3bDjj.jpg'
image = Image.open(requests.get(url, stream=True).raw)
model = DrlnModel.from_pretrained('eugenesiow/drln', scale=2) # scale 2, 3 and 4 models available
inputs = ImageLoader.load_image(image)
preds = model(inputs)
ImageLoader.save_image(preds, './scaled_2x.png') # save the output 2x scaled image to `./scaled_2x.png`
ImageLoader.save_compare(inputs, preds, './scaled_2x_compare.png') # save an output comparing the super-image with a bicubic scaling
```
[](https://colab.research.google.com/github/eugenesiow/super-image-notebooks/blob/master/notebooks/Upscale_Images_with_Pretrained_super_image_Models.ipynb "Open in Colab")
## Training data
The models for 2x, 3x and 4x image super resolution were pretrained on [DIV2K](https://huggingface.co/datasets/eugenesiow/Div2k), a dataset of 800 high-quality (2K resolution) images for training, augmented to 4000 images and uses a dev set of 100 validation images (images numbered 801 to 900).
## Training procedure
### Preprocessing
We follow the pre-processing and training method of [Wang et al.](https://arxiv.org/abs/2104.07566).
Low Resolution (LR) images are created by using bicubic interpolation as the resizing method to reduce the size of the High Resolution (HR) images by x2, x3 and x4 times.
During training, RGB patches with size of 64×64 from the LR input are used together with their corresponding HR patches.
Data augmentation is applied to the training set in the pre-processing stage where five images are created from the four corners and center of the original image.
We need the huggingface [datasets](https://huggingface.co/datasets?filter=task_ids:other-other-image-super-resolution) library to download the data:
```bash
pip install datasets
```
The following code gets the data and preprocesses/augments the data.
```python
from datasets import load_dataset
from super_image.data import EvalDataset, TrainDataset, augment_five_crop
augmented_dataset = load_dataset('eugenesiow/Div2k', 'bicubic_x4', split='train')\
.map(augment_five_crop, batched=True, desc="Augmenting Dataset") # download and augment the data with the five_crop method
train_dataset = TrainDataset(augmented_dataset) # prepare the train dataset for loading PyTorch DataLoader
eval_dataset = EvalDataset(load_dataset('eugenesiow/Div2k', 'bicubic_x4', split='validation')) # prepare the eval dataset for the PyTorch DataLoader
```
### Pretraining
The model was trained on GPU. The training code is provided below:
```python
from super_image import Trainer, TrainingArguments, DrlnModel, DrlnConfig
training_args = TrainingArguments(
output_dir='./results', # output directory
num_train_epochs=1000, # total number of training epochs
)
config = DrlnConfig(
scale=4, # train a model to upscale 4x
)
model = DrlnModel(config)
trainer = Trainer(
model=model, # the instantiated model to be trained
args=training_args, # training arguments, defined above
train_dataset=train_dataset, # training dataset
eval_dataset=eval_dataset # evaluation dataset
)
trainer.train()
```
[](https://colab.research.google.com/github/eugenesiow/super-image-notebooks/blob/master/notebooks/Train_super_image_Models.ipynb "Open in Colab")
## Evaluation results
The evaluation metrics include [PSNR](https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio#Quality_estimation_with_PSNR) and [SSIM](https://en.wikipedia.org/wiki/Structural_similarity#Algorithm).
Evaluation datasets include:
- Set5 - [Bevilacqua et al. (2012)](https://huggingface.co/datasets/eugenesiow/Set5)
- Set14 - [Zeyde et al. (2010)](https://huggingface.co/datasets/eugenesiow/Set14)
- BSD100 - [Martin et al. (2001)](https://huggingface.co/datasets/eugenesiow/BSD100)
- Urban100 - [Huang et al. (2015)](https://huggingface.co/datasets/eugenesiow/Urban100)
The results columns below are represented below as `PSNR/SSIM`. They are compared against a Bicubic baseline.
|Dataset |Scale |Bicubic |drln |
|--- |--- |--- |--- |
|Set5 |2x |33.64/0.9292 |**38.22/0.9614** |
|Set5 |3x |30.39/0.8678 |**35.31/0.9423** |
|Set5 |4x |28.42/0.8101 |**32.55/0.899** |
|Set14 |2x |30.22/0.8683 |**34.01/0.9211** |
|Set14 |3x |27.53/0.7737 |**31.21/0.8619** |
|Set14 |4x |25.99/0.7023 |**28.96/0.7901** |
|BSD100 |2x |29.55/0.8425 |**33.93/0.9269** |
|BSD100 |3x |27.20/0.7382 |**29.77/0.8223** |
|BSD100 |4x |25.96/0.6672 |**28.65/0.7692** |
|Urban100 |2x |26.66/0.8408 |**32.82/0.934** |
|Urban100 |3x | |**29.79/0.8825** |
|Urban100 |4x |23.14/0.6573 |**26.56/0.7998** |
You can find a notebook to easily run evaluation on pretrained models below:
[](https://colab.research.google.com/github/eugenesiow/super-image-notebooks/blob/master/notebooks/Evaluate_Pretrained_super_image_Models.ipynb "Open in Colab")
## BibTeX entry and citation info
```bibtex
@misc{anwar2019densely,
title={Densely Residual Laplacian Super-Resolution},
author={Saeed Anwar and Nick Barnes},
year={2019},
eprint={1906.12021},
archivePrefix={arXiv},
primaryClass={eess.IV}
}
``` |
indonesian-nlp/gpt2-medium-indonesian | indonesian-nlp | "2023-08-13T01:41:56Z" | 1,000 | 7 | transformers | [
"transformers",
"pytorch",
"jax",
"safetensors",
"gpt2",
"text-generation",
"id",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-03-02T23:29:05Z" | ---
language: id
widget:
- text: "Sewindu sudah kita tak berjumpa, rinduku padamu sudah tak terkira."
---
# GPT2-medium-indonesian
This is a pretrained model on Indonesian language using a causal language modeling (CLM) objective, which was first
introduced in [this paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf)
and first released at [this page](https://openai.com/blog/better-language-models/).
This model was trained using HuggingFace's Flax framework and is part of the [JAX/Flax Community Week](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104)
organized by [HuggingFace](https://huggingface.co). All training was done on a TPUv3-8 VM sponsored by the Google Cloud team.
The demo can be found [here](https://huggingface.co/spaces/indonesian-nlp/gpt2-app).
## 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='indonesian-nlp/gpt2-medium-indonesian')
>>> set_seed(42)
>>> generator("Sewindu sudah kita tak berjumpa,", max_length=30, num_return_sequences=5)
[{'generated_text': 'Sewindu sudah kita tak berjumpa, dua dekade lalu, saya hanya bertemu sekali. Entah mengapa, saya lebih nyaman berbicara dalam bahasa Indonesia, bahasa Indonesia'},
{'generated_text': 'Sewindu sudah kita tak berjumpa, tapi dalam dua hari ini, kita bisa saja bertemu.”\
“Kau tau, bagaimana dulu kita bertemu?” aku'},
{'generated_text': 'Sewindu sudah kita tak berjumpa, banyak kisah yang tersimpan. Tak mudah tuk kembali ke pelukan, di mana kini kita berada, sebuah tempat yang jauh'},
{'generated_text': 'Sewindu sudah kita tak berjumpa, sejak aku lulus kampus di Bandung, aku sempat mencari kabar tentangmu. Ah, masih ada tempat di hatiku,'},
{'generated_text': 'Sewindu sudah kita tak berjumpa, tapi Tuhan masih saja menyukarkan doa kita masing-masing.\
Tuhan akan memberi lebih dari apa yang kita'}]
```
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import GPT2Tokenizer, GPT2Model
tokenizer = GPT2Tokenizer.from_pretrained('indonesian-nlp/gpt2-medium-indonesian')
model = GPT2Model.from_pretrained('indonesian-nlp/gpt2-medium-indonesian')
text = "Ubah dengan teks apa saja."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
```
and in TensorFlow:
```python
from transformers import GPT2Tokenizer, TFGPT2Model
tokenizer = GPT2Tokenizer.from_pretrained('indonesian-nlp/gpt2-medium-indonesian')
model = TFGPT2Model.from_pretrained('indonesian-nlp/gpt2-medium-indonesian')
text = "Ubah dengan teks apa saja."
encoded_input = tokenizer(text, return_tensors='tf')
output = model(encoded_input)
```
## Limitations and bias
The training data used for this model are Indonesian websites of [OSCAR](https://oscar-corpus.com/),
[mc4](https://huggingface.co/datasets/mc4) and [Wikipedia](https://huggingface.co/datasets/wikipedia). The datasets
contain a lot of unfiltered content from the internet, which is far from neutral. While we have done some filtering on
the dataset (see the **Training data** section), the filtering is by no means a thorough mitigation of biased content
that is eventually used by the training data. These biases might also affect models that are fine-tuned using this model.
As the openAI team themselves point out in their [model card](https://github.com/openai/gpt-2/blob/master/model_card.md#out-of-scope-use-cases):
> Because large-scale language models like GPT-2 do not distinguish fact from fiction, we don’t support use-cases
> that require the generated text to be true.
> Additionally, language models like GPT-2 reflect the biases inherent to the systems they were trained on, so we
> do not recommend that they be deployed into systems that interact with humans > unless the deployers first carry
> out a study of biases relevant to the intended use-case. We found no statistically significant difference in gender,
> race, and religious bias probes between 774M and 1.5B, implying all versions of GPT-2 should be approached with
> similar levels of caution around use cases that are sensitive to biases around human attributes.
We have done a basic bias analysis that you can find in this [notebook](https://huggingface.co/indonesian-nlp/gpt2-small-indonesian/blob/main/bias_analysis/gpt2_medium_indonesian_bias_analysis.ipynb), performed on [Indonesian GPT2 medium](https://huggingface.co/indonesian-nlp/gpt2-medium-indonesian), based on the bias analysis for [Polish GPT2](https://huggingface.co/flax-community/papuGaPT2) with modifications.
### Gender bias
We generated 50 texts starting with prompts "She/He works as". After doing some preprocessing (lowercase and stopwords removal) we obtain texts that are used to generate word clouds of female/male professions. The most salient terms for male professions are: driver, sopir (driver), ojek, tukang, online.
The most salient terms for female professions are: pegawai (employee), konsultan (consultant), asisten (assistant).
### Ethnicity bias
We generated 1,200 texts to assess bias across ethnicity and gender vectors. We will create prompts with the following scheme:
* Person - we will assess 5 ethnicities: Sunda, Batak, Minahasa, Dayak, Asmat, Neutral (no ethnicity)
* Topic - we will use 5 different topics:
* random act: *entered home*
* said: *said*
* works as: *works as*
* intent: *let [person] ...*
* define: *is*
Sample of generated prompt: "seorang perempuan sunda masuk ke rumah..." (a Sundanese woman enters the house...)
We used a [model](https://huggingface.co/Hate-speech-CNERG/dehatebert-mono-indonesian) trained on Indonesian hate speech corpus ([dataset 1](https://github.com/okkyibrohim/id-multi-label-hate-speech-and-abusive-language-detection), [dataset 2](https://github.com/ialfina/id-hatespeech-detection)) to obtain the probability that each generated text contains hate speech. To avoid leakage, we removed the first word identifying the ethnicity and gender from the generated text before running the hate speech detector.
The following chart demonstrates the intensity of hate speech associated with the generated texts with outlier scores removed. Some ethnicities score higher than the neutral baseline.
### Religion bias
With the same methodology above, we generated 1,400 texts to assess bias across religion and gender vectors. We will assess 6 religions: Islam, Protestan (Protestant), Katolik (Catholic), Buddha (Buddhism), Hindu (Hinduism), and Khonghucu (Confucianism) with Neutral (no religion) as a baseline.
The following chart demonstrates the intensity of hate speech associated with the generated texts with outlier scores removed. Some religions score higher than the neutral baseline.
## Training data
The model was trained on a combined dataset of [OSCAR](https://oscar-corpus.com/), [mc4](https://huggingface.co/datasets/mc4)
and Wikipedia for the Indonesian language. We have filtered and reduced the mc4 dataset so that we end up with 29 GB
of data in total. The mc4 dataset was cleaned using [this filtering script](https://github.com/Wikidepia/indonesian_datasets/blob/master/dump/mc4/cleanup.py)
and we also only included links that have been cited by the Indonesian Wikipedia.
## Training procedure
The model was trained on a TPUv3-8 VM provided by the Google Cloud team. The training duration was `6d 3h 7m 26s`.
### Evaluation results
The model achieves the following results without any fine-tuning (zero-shot):
| dataset | train loss | eval loss | eval perplexity |
| ---------- | ---------- | -------------- | ---------- |
| ID OSCAR+mc4+Wikipedia (29GB) | 2.79 | 2.696 | 14.826 |
### Tracking
The training process was tracked in [TensorBoard](https://huggingface.co/flax-community/gpt2-medium-indonesian/tensorboard) and [Weights and Biases](https://wandb.ai/wandb/hf-flax-gpt2-indonesian?workspace=user-cahya).
## Team members
- Akmal ([@Wikidepia](https://huggingface.co/Wikidepia))
- alvinwatner ([@alvinwatner](https://huggingface.co/alvinwatner))
- Cahya Wirawan ([@cahya](https://huggingface.co/cahya))
- Galuh Sahid ([@Galuh](https://huggingface.co/Galuh))
- Muhammad Agung Hambali ([@AyameRushia](https://huggingface.co/AyameRushia))
- Muhammad Fhadli ([@muhammadfhadli](https://huggingface.co/muhammadfhadli))
- Samsul Rahmadani ([@munggok](https://huggingface.co/munggok))
## Future work
We would like to pre-train further the models with larger and cleaner datasets and fine-tune it to specific domains
if we can get the necessary hardware resources. |
ComCom/gpt2-small | ComCom | "2022-10-28T05:53:14Z" | 1,000 | 1 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"exbert",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-10-28T05:43:05Z" | ---
language: en
tags:
- exbert
license: mit
---
This repository has been forked from https://huggingface.co/gpt2
---
# GPT-2
Test the whole generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large
Pretrained model on English language using a causal language modeling (CLM) objective. It was introduced in
[this paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf)
and first released at [this page](https://openai.com/blog/better-language-models/).
Disclaimer: The team releasing GPT-2 also wrote a
[model card](https://github.com/openai/gpt-2/blob/master/model_card.md) for their model. Content from this model card
has been written by the Hugging Face team to complete the information they provided and give specific examples of bias.
## Model description
GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This
means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots
of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely,
it was trained to guess the next word in sentences.
More precisely, inputs are sequences of continuous text of a certain length and the targets are the same sequence,
shifted one token (word or piece of word) to the right. The model uses internally a mask-mechanism to make sure the
predictions for the token `i` only uses the inputs from `1` to `i` but not the future tokens.
This way, the model learns an inner representation of the English language that can then be used to extract features
useful for downstream tasks. The model is best at what it was pretrained for however, which is generating texts from a
prompt.
## Intended uses & limitations
You can use the raw model for text generation or fine-tune it to a downstream task. See the
[model hub](https://huggingface.co/models?filter=gpt2) to look for fine-tuned versions on a task that interests you.
### 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='gpt2')
>>> set_seed(42)
>>> generator("Hello, I'm a language model,", max_length=30, num_return_sequences=5)
[{'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"},
{'generated_text': "Hello, I'm a language model, a system model. I want to know my language so that it might be more interesting, more user-friendly"},
{'generated_text': 'Hello, I\'m a language model, not a language model"\n\nThe concept of "no-tricks" comes in handy later with new'}]
```
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import GPT2Tokenizer, GPT2Model
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
model = GPT2Model.from_pretrained('gpt2')
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
```
and in TensorFlow:
```python
from transformers import GPT2Tokenizer, TFGPT2Model
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
model = TFGPT2Model.from_pretrained('gpt2')
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='tf')
output = model(encoded_input)
```
### Limitations and bias
The training data used for this model has not been released as a dataset one can browse. We know it contains a lot of
unfiltered content from the internet, which is far from neutral. As the openAI team themselves point out in their
[model card](https://github.com/openai/gpt-2/blob/master/model_card.md#out-of-scope-use-cases):
> Because large-scale language models like GPT-2 do not distinguish fact from fiction, we don’t support use-cases
> that require the generated text to be true.
>
> Additionally, language models like GPT-2 reflect the biases inherent to the systems they were trained on, so we do
> not recommend that they be deployed into systems that interact with humans > unless the deployers first carry out a
> study of biases relevant to the intended use-case. We found no statistically significant difference in gender, race,
> and religious bias probes between 774M and 1.5B, implying all versions of GPT-2 should be approached with similar
> levels of caution around use cases that are sensitive to biases around human attributes.
Here's an example of how the model can have biased predictions:
```python
>>> from transformers import pipeline, set_seed
>>> generator = pipeline('text-generation', model='gpt2')
>>> set_seed(42)
>>> generator("The White man worked as a", max_length=10, num_return_sequences=5)
[{'generated_text': 'The White man worked as a mannequin for'},
{'generated_text': 'The White man worked as a maniser of the'},
{'generated_text': 'The White man worked as a bus conductor by day'},
{'generated_text': 'The White man worked as a plumber at the'},
{'generated_text': 'The White man worked as a journalist. He had'}]
>>> set_seed(42)
>>> generator("The Black man worked as a", max_length=10, num_return_sequences=5)
[{'generated_text': 'The Black man worked as a man at a restaurant'},
{'generated_text': 'The Black man worked as a car salesman in a'},
{'generated_text': 'The Black man worked as a police sergeant at the'},
{'generated_text': 'The Black man worked as a man-eating monster'},
{'generated_text': 'The Black man worked as a slave, and was'}]
```
This bias will also affect all fine-tuned versions of this model.
## Training data
The OpenAI team wanted to train this model on a corpus as large as possible. To build it, they scraped all the web
pages from outbound links on Reddit which received at least 3 karma. Note that all Wikipedia pages were removed from
this dataset, so the model was not trained on any part of Wikipedia. The resulting dataset (called WebText) weights
40GB of texts but has not been publicly released. You can find a list of the top 1,000 domains present in WebText
[here](https://github.com/openai/gpt-2/blob/master/domains.txt).
## Training procedure
### Preprocessing
The texts are tokenized using a byte-level version of Byte Pair Encoding (BPE) (for unicode characters) and a
vocabulary size of 50,257. The inputs are sequences of 1024 consecutive tokens.
The larger model was trained on 256 cloud TPU v3 cores. The training duration was not disclosed, nor were the exact
details of training.
## Evaluation results
The model achieves the following results without any fine-tuning (zero-shot):
| Dataset | LAMBADA | LAMBADA | CBT-CN | CBT-NE | WikiText2 | PTB | enwiki8 | text8 | WikiText103 | 1BW |
|:--------:|:-------:|:-------:|:------:|:------:|:---------:|:------:|:-------:|:------:|:-----------:|:-----:|
| (metric) | (PPL) | (ACC) | (ACC) | (ACC) | (PPL) | (PPL) | (BPB) | (BPC) | (PPL) | (PPL) |
| | 35.13 | 45.99 | 87.65 | 83.4 | 29.41 | 65.85 | 1.16 | 1,17 | 37.50 | 75.20 |
### BibTeX entry and citation info
```bibtex
@article{radford2019language,
title={Language Models are Unsupervised Multitask Learners},
author={Radford, Alec and Wu, Jeff and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya},
year={2019}
}
```
<a href="https://huggingface.co/exbert/?model=gpt2">
<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
</a>
|
hamxea/Mistral-7B-v0.1-activity-fine-tuned-v5 | hamxea | "2024-03-31T14:42:10Z" | 1,000 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"medical",
"text-generation-inference",
"en",
"arxiv:1910.09700",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-01-17T13:44:41Z" | ---
library_name: transformers
tags:
- medical
- text-generation-inference
license: other
language:
- en
---
# 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] |
cognitivecomputations/WestLake-7B-v2-laser | cognitivecomputations | "2024-01-30T20:48:21Z" | 1,000 | 34 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-26T01:20:19Z" | ---
license: apache-2.0
---
by David, Fernando and Eric
Sponsored by: [VAGO Solutions](https://vago-solutions.de) and [HyperSpace.Ai](https://hyperspace.computer/)
Join our Discord! https://discord.gg/cognitivecomputations
A laser version of [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2)
It follows the implementation of laserRMT @ https://github.com/cognitivecomputations/laserRMT
Here, we are controlling layers checking which ones have lower signal to noise ratios (which are more subject to noise), to apply Laser interventions, still using Machenko Pastur to calculate this ratio.
We intend to be the first of a family of experimentations being carried out @ Cognitive Computations.
|
shahzebnaveed/StarlingHermes-2.5-Mistral-7B-slerp | shahzebnaveed | "2024-02-16T17:31:20Z" | 1,000 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:shahzebnaveed/NeuralHermes-2.5-Mistral-7B",
"base_model:berkeley-nest/Starling-LM-7B-alpha",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-16T10:35:41Z" | ---
base_model:
- shahzebnaveed/NeuralHermes-2.5-Mistral-7B
- berkeley-nest/Starling-LM-7B-alpha
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [shahzebnaveed/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/shahzebnaveed/NeuralHermes-2.5-Mistral-7B)
* [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: berkeley-nest/Starling-LM-7B-alpha
layer_range: [0, 32]
- model: shahzebnaveed/NeuralHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: berkeley-nest/Starling-LM-7B-alpha
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
``` |
l3utterfly/mistral-7b-v0.1-layla-v3 | l3utterfly | "2024-02-24T07:01:58Z" | 1,000 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-23T07:56:57Z" | ---
license: apache-2.0
language:
- en
---
# Model Card
### Model Description
Mistral 7B fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation.
The dataset has been pre-processed by doing the following:
1. remove all refusals
2. remove any mention of AI assistant
3. split any multi-turn dialog generated in the dataset into multi-turn conversations records
- **Developed by:** l3utterfly
- **Funded by:** Layla Network
- **Model type:** Mistral
- **Language(s) (NLP):** English
- **License:** Apache-2.0
- **Finetuned from model:** Mistral 7B
## Uses
Base model used by Layla - the offline personal assistant: https://www.layla-network.ai
Help & support: https://discord.gg/x546YJ6nYC
Prompt:
```
USER:
ASSISTANT:
```
[<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) |
nbeerbower/Maidphin-Kunoichi-7B | nbeerbower | "2024-03-07T12:43:09Z" | 1,000 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"base_model:SanjiWatsuki/Kunoichi-DPO-v2-7B",
"base_model:nbeerbower/maidphin",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-07T12:38:40Z" | ---
license: cc-by-nc-4.0
base_model:
- SanjiWatsuki/Kunoichi-DPO-v2-7B
- nbeerbower/maidphin
library_name: transformers
tags:
- mergekit
- merge
---
# Maidphin-Kunoichi-7B
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
* [nbeerbower/maidphin](https://huggingface.co/nbeerbower/maidphin)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: nbeerbower/maidphin
layer_range: [0, 32]
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B
layer_range: [0, 32]
merge_method: slerp
base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
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
```
|
hydra-project/OpenHyperion-2.5-Mistral-7B | hydra-project | "2024-03-10T19:24:47Z" | 1,000 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"Locutusque/Hyperion-2.1-Mistral-7B",
"teknium/OpenHermes-2.5-Mistral-7B",
"en",
"base_model:Locutusque/Hyperion-2.1-Mistral-7B",
"base_model:teknium/OpenHermes-2.5-Mistral-7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-10T18:27:02Z" | ---
tags:
- merge
- mergekit
- lazymergekit
- Locutusque/Hyperion-2.1-Mistral-7B
- teknium/OpenHermes-2.5-Mistral-7B
base_model:
- Locutusque/Hyperion-2.1-Mistral-7B
- teknium/OpenHermes-2.5-Mistral-7B
license: apache-2.0
language:
- en
---
# OpenHyperion-2.5-Mistral-7B
OpenHyperion-2.5-Mistral-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Locutusque/Hyperion-2.1-Mistral-7B](https://huggingface.co/Locutusque/Hyperion-2.1-Mistral-7B)
* [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: Locutusque/Hyperion-2.1-Mistral-7B
layer_range: [0, 32]
- model: teknium/OpenHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: Locutusque/Hyperion-2.1-Mistral-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 = "hydra-project/OpenHyperion-2.5-Mistral-7B"
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"])
``` |
monster119120/OpenHermes-2.5-Mistral-7B-new | monster119120 | "2024-04-05T12:16:53Z" | 1,000 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-04T07:29:53Z" | ---
library_name: transformers
license: apache-2.0
---
# 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] |
jambroz/FNCARLplus-7b | jambroz | "2024-04-05T21:00:15Z" | 1,000 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:jambroz/FNCARL-7b",
"base_model:HuggingFaceH4/mistral-7b-anthropic",
"base_model:jambroz/sixtyoneeighty-7b",
"base_model:mlabonne/UltraMerge-7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-05T19:04:29Z" | ---
base_model:
- jambroz/FNCARL-7b
- HuggingFaceH4/mistral-7b-anthropic
- jambroz/sixtyoneeighty-7b
- mlabonne/UltraMerge-7B
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [jambroz/sixtyoneeighty-7b](https://huggingface.co/jambroz/sixtyoneeighty-7b) as a base.
### Models Merged
The following models were included in the merge:
* [jambroz/FNCARL-7b](https://huggingface.co/jambroz/FNCARL-7b)
* [HuggingFaceH4/mistral-7b-anthropic](https://huggingface.co/HuggingFaceH4/mistral-7b-anthropic)
* [mlabonne/UltraMerge-7B](https://huggingface.co/mlabonne/UltraMerge-7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: jambroz/sixtyoneeighty-7b
dtype: bfloat16
merge_method: dare_ties
models:
- model: jambroz/sixtyoneeighty-7b
- model: mlabonne/UltraMerge-7B
parameters:
density: '0.53'
weight: '0.4'
- model: HuggingFaceH4/mistral-7b-anthropic
parameters:
density: '0.53'
weight: '0.3'
- model: jambroz/FNCARL-7b
parameters:
density: '0.53'
weight: '0.3'
parameters:
int8_mask: true
``` |
voidful/phi-1_5_base | voidful | "2024-04-08T17:12:47Z" | 1,000 | 0 | transformers | [
"transformers",
"safetensors",
"phi",
"text-generation",
"custom_code",
"arxiv:1910.09700",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-06T08:55:36Z" | ---
license: mit
library_name: transformers
---
# 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] |
RichardErkhov/johnsnowlabs_-_JSL-MedLlama-3-8B-v2.0-gguf | RichardErkhov | "2024-06-16T13:02:17Z" | 1,000 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-16T12:27:57Z" | Entry not found |
sshleifer/tiny-distilbert-base-cased | sshleifer | "2021-05-20T07:12:39Z" | 999 | 3 | transformers | [
"transformers",
"pytorch",
"tf",
"jax",
"bert",
"token-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | "2022-03-02T23:29:05Z" | Entry not found |
TheBloke/law-LLM-GGUF | TheBloke | "2023-09-27T12:54:42Z" | 999 | 12 | transformers | [
"transformers",
"gguf",
"llama",
"arxiv:2309.09530",
"base_model:AdaptLLM/law-LLM",
"license:other",
"text-generation-inference",
"region:us"
] | null | "2023-09-27T08:40:00Z" | ---
license: other
model_name: Law LLM
base_model: AdaptLLM/law-LLM
inference: false
model_creator: AdaptLLM
model_type: llama
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 -->
# Law LLM - GGUF
- Model creator: [AdaptLLM](https://huggingface.co/AdaptLLM)
- Original model: [Law LLM](https://huggingface.co/AdaptLLM/law-LLM)
<!-- description start -->
## Description
This repo contains GGUF format model files for [AdaptLLM's Law LLM](https://huggingface.co/AdaptLLM/law-LLM).
<!-- 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/law-LLM-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/law-LLM-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/law-LLM-GGUF)
* [AdaptLLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/AdaptLLM/law-LLM)
<!-- 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [law-llm.Q2_K.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q2_K.gguf) | Q2_K | 2 | 2.83 GB| 5.33 GB | smallest, significant quality loss - not recommended for most purposes |
| [law-llm.Q3_K_S.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| 5.45 GB | very small, high quality loss |
| [law-llm.Q3_K_M.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q3_K_M.gguf) | Q3_K_M | 3 | 3.30 GB| 5.80 GB | very small, high quality loss |
| [law-llm.Q3_K_L.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q3_K_L.gguf) | Q3_K_L | 3 | 3.60 GB| 6.10 GB | small, substantial quality loss |
| [law-llm.Q4_0.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [law-llm.Q4_K_S.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| 6.36 GB | small, greater quality loss |
| [law-llm.Q4_K_M.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| 6.58 GB | medium, balanced quality - recommended |
| [law-llm.Q5_0.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [law-llm.Q5_K_S.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| 7.15 GB | large, low quality loss - recommended |
| [law-llm.Q5_K_M.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| 7.28 GB | large, very low quality loss - recommended |
| [law-llm.Q6_K.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q6_K.gguf) | Q6_K | 6 | 5.53 GB| 8.03 GB | very large, extremely low quality loss |
| [law-llm.Q8_0.gguf](https://huggingface.co/TheBloke/law-LLM-GGUF/blob/main/law-llm.Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| 9.66 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/law-LLM-GGUF and below it, a specific filename to download, such as: law-llm.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/law-LLM-GGUF law-llm.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/law-LLM-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/law-LLM-GGUF law-llm.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 law-llm.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.
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/law-LLM-GGUF", model_file="law-llm.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: AdaptLLM's Law LLM
# Adapting Large Language Models via Reading Comprehension
This repo contains the model for our paper [Adapting Large Language Models via Reading Comprehension](https://arxiv.org/pdf/2309.09530.pdf)
We explore **continued pre-training on domain-specific corpora** for large language models. While this approach enriches LLMs with domain knowledge, it significantly hurts their prompting ability for question answering. Inspired by human learning via reading comprehension, we propose a simple method to **transform large-scale pre-training corpora into reading comprehension texts**, consistently improving prompting performance across tasks in **biomedicine, finance, and law domains**. Our 7B model competes with much larger domain-specific models like BloombergGPT-50B. Moreover, our domain-specific reading comprehension texts enhance model performance even on general benchmarks, indicating potential for developing a general LLM across more domains.
## GitHub repo:
https://github.com/microsoft/LMOps
## Domain-specific LLMs:
Our models of different domains are now available in Huggingface: [Biomedicine-LLM](https://huggingface.co/AdaptLLM/medicine-LLM), [Finance-LLM](https://huggingface.co/AdaptLLM/finance-LLM) and [Law-LLM](https://huggingface.co/AdaptLLM/law-LLM), the performances of our AdaptLLM compared to other domain-specific LLMs are:
<p align='center'>
<img src="./comparison.png" width="700">
</p>
## Domain-specific Tasks:
To easily reproduce our results, we have uploaded the filled-in zero/few-shot input instructions and output completions of each domain-specific task: [biomedicine-tasks](https://huggingface.co/datasets/AdaptLLM/medicine-tasks), [finance-tasks](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [law-tasks](https://huggingface.co/datasets/AdaptLLM/law-tasks).
## Citation:
```bibtex
@inproceedings{AdaptLLM,
title={Adapting Large Language Models via Reading Comprehension},
author={Daixuan Cheng and Shaohan Huang and Furu Wei},
url={https://arxiv.org/abs/2309.09530},
year={2023},
}
```
<!-- original-model-card end -->
|
NLUHOPOE/test-case-2 | NLUHOPOE | "2024-02-20T09:47:01Z" | 999 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"dataset:Open-Orca/SlimOrca",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-20T07:30:15Z" | ---
license: apache-2.0
datasets:
- Open-Orca/SlimOrca
language:
- en
---
# Model Details
* Model Description: This model is test for data ordering.
* Developed by: Juhwan Lee
* Model Type: Large Language Model
# Model Architecture
This model is based on Mistral-7B-v0.1. We fine-tuning this model for data ordering task.
Mistral-7B-v0.1 is a transformer model, with the following architecture choices:
* Grouped-Query Attention
* Sliding-Window Attention
* Byte-fallback BPE tokenizer
# Dataset
We random sample SlimOrca dataset.
# Guthub
https://github.com/trailerAI
# License
Apache License 2.0 |
Locutusque/OpenCerebrum-1.5-Mistral-7B-v0.2-beta | Locutusque | "2024-04-07T16:25:07Z" | 999 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-07T05:49:11Z" | ---
language:
- en
license: apache-2.0
library_name: transformers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This model represents a kind of trial model to assess its performance subsequent to reducing the dataset's size. An in-house filtering technique has been employed. This iteration of OpenCerebrum remains unfinished and will persist in an incomplete state. Version 2.0 will encompass a fully open SFT and DPO dataset.
## 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] |
unsloth/gemma-1.1-2b-it | unsloth | "2024-04-18T15:03:55Z" | 999 | 2 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"unsloth",
"gemma-2b",
"bnb",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-07T10:05:20Z" | ---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- unsloth
- transformers
- gemma
- gemma-2b
- bnb
---
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
We have a Google Colab Tesla T4 notebook for Gemma 2b here: https://colab.research.google.com/drive/15gGm7x_jTm017_Ic8e317tdIpDG53Mtu?usp=sharing
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy%20me%20a%20coffee%20button.png" width="200"/>](https://ko-fi.com/unsloth)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
## ✨ Finetune for Free
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| **Gemma 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing) | 2.4x faster | 58% less |
| **Mistral 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
| **Llama-2 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lBzz5KeZJKXjvivbYvmGarix9Ao6Wxe5?usp=sharing) | 2.2x faster | 43% less |
| **TinyLlama** | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less |
| **CodeLlama 34b** A100 | [▶️ Start on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing) | 1.9x faster | 27% less |
| **Mistral 7b** 1xT4 | [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook) | 5x faster\* | 62% less |
| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
|
chujiezheng/Smaug-Llama-3-70B-Instruct-ExPO | chujiezheng | "2024-05-27T18:19:48Z" | 999 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"arxiv:2404.16792",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-19T18:54:03Z" | ---
license: llama3
language:
- en
---
# Smaug-Llama-3-70B-Instruct-ExPO
The extrapolated (ExPO) model based on [`abacusai/Smaug-Llama-3-70B-Instruct`](https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct) and [`meta-llama/Meta-Llama-3-70B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
## Evaluation Results
Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_alpaca)):
| | Win Rate (Ori) | LC Win Rate (Ori) | Win Rate (+ ExPO) | LC Win Rate (+ ExPO) |
| ------------------------------------ | -------------- | ----------------- | ----------------- | -------------------- |
| `HuggingFaceH4/zephyr-7b-alpha` | 6.7% | 10.0% | **10.6%** | **13.6%** |
| `HuggingFaceH4/zephyr-7b-beta` | 10.2% | 13.2% | **11.1%** | **14.0%** |
| `berkeley-nest/Starling-LM-7B-alpha` | 15.0% | 18.3% | **18.2%** | **19.5%** |
| `Nexusflow/Starling-LM-7B-beta` | 26.6% | 25.8% | **29.6%** | **26.4%** |
| `snorkelai/Snorkel-Mistral-PairRM` | 24.7% | 24.0% | **28.8%** | **26.4%** |
| `RLHFlow/LLaMA3-iterative-DPO-final` | 29.2% | 36.0% | **32.7%** | **37.8%** |
| `internlm/internlm2-chat-1.8b` | 3.8% | 4.0% | **5.2%** | **4.3%** |
| `internlm/internlm2-chat-7b` | 20.5% | 18.3% | **28.1%** | **22.7%** |
| `internlm/internlm2-chat-20b` | 36.1% | 24.9% | **46.2%** | **27.2%** |
| `allenai/tulu-2-dpo-7b` | 8.5% | 10.2% | **11.5%** | **11.7%** |
| `allenai/tulu-2-dpo-13b` | 11.2% | 15.5% | **15.6%** | **17.6%** |
| `allenai/tulu-2-dpo-70b` | 15.4% | 21.2% | **23.0%** | **25.7%** |
Evaluation results on the **MT-Bench** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_mtbench)):
| | Original | + ExPO |
| ------------------------------------ | -------- | -------- |
| `HuggingFaceH4/zephyr-7b-alpha` | 6.85 | **6.87** |
| `HuggingFaceH4/zephyr-7b-beta` | 7.02 | **7.06** |
| `berkeley-nest/Starling-LM-7B-alpha` | 7.82 | **7.91** |
| `Nexusflow/Starling-LM-7B-beta` | 8.10 | **8.18** |
| `snorkelai/Snorkel-Mistral-PairRM` | 7.63 | **7.69** |
| `RLHFlow/LLaMA3-iterative-DPO-final` | 8.08 | **8.45** |
| `internlm/internlm2-chat-1.8b` | 5.17 | **5.26** |
| `internlm/internlm2-chat-7b` | 7.72 | **7.80** |
| `internlm/internlm2-chat-20b` | 8.13 | **8.26** |
| `allenai/tulu-2-dpo-7b` | 6.35 | **6.38** |
| `allenai/tulu-2-dpo-13b` | 7.00 | **7.26** |
| `allenai/tulu-2-dpo-70b` | 7.79 | **8.03** |
|
Yntec/Emoticons | Yntec | "2023-12-18T07:26:50Z" | 998 | 4 | diffusers | [
"diffusers",
"safetensors",
"Emoticons",
"Emojis",
"Smileys",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-12-18T06:56:58Z" | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Emoticons
- Emojis
- Smileys
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
inference: true
---
# Emoticons
Samples and prompts:
(Click for larger)
Top left: masterpiece, top quality, best quality, official art, beautiful and aesthetic,8k, best quality, masterpiece, no humans,a brown teddy bear with a ribbon and hearts, solo, simple_background, white_background, full_body, pokemon_\creature\,
Top right: masterpiece, top quality, best quality, official art, beautiful and aesthetic,8k, best quality, masterpiece, a white bunny rabbit with an orange umbrella, solo, simple_background, white_background, full_body, pokemon_\creature\,
Bottom left: masterpiece, top quality, best quality, official art, beautiful and aesthetic,8k, best quality, masterpiece, a adorable multiple multicolored hearts in rainbow basket, solo, simple_background, blue_background, full_body, pokemon_\creature\,
Bottom right: masterpiece, top quality, best quality, official art, beautiful and aesthetic,8k, best quality, masterpiece, a adorable pineapple with long leaves, solo, simple_background, blue_background, full_body, pokemon_\creature\,
|
JCX-kcuf/Llama-2-7b-hf-gpt-4-80k | JCX-kcuf | "2024-03-11T15:44:32Z" | 998 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-10T16:34:35Z" | ---
license: apache-2.0
---
## Description
This model is finetuned on the distillation data from GPT-4.
The base model is meta-llama/Llama-2-7b-hf
## Usage
The model has a query format as in llama-2.
```
<s> [INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>
{query} [/INST]
``` |
ericpolewski/AIRIC-The-Intern | ericpolewski | "2024-03-16T20:16:36Z" | 998 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-16T17:45:45Z" | ---
license: mit
---
This is an instruct model. It's to test out the effects of my dataset on the InternLM model if you just change everything to say "Llama" instead of "InternLM" in the config files.
I had a theory that a lot of these models are just Llama models with extraneous loaders. This is to test that theory.
Trained at rank 256 for 1 epoch at constant learning rate. |
raincandy-u/Rain-7B-v0.1 | raincandy-u | "2024-04-07T14:46:54Z" | 998 | 7 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"CoT",
"conversational",
"zh",
"en",
"dataset:yys/OpenOrca-Chinese",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-04T16:52:25Z" | ---
license: other
license_name: tongyi-qianwen
license_link: https://huggingface.co/Qwen/Qwen1.5-7B-Chat/raw/main/LICENSE
datasets:
- yys/OpenOrca-Chinese
language:
- zh
- en
pipeline_tag: text-generation
tags:
- CoT
---
<style>
@font-face {
font-family: Zpix;
src: url(https://zpix.now.sh/zpix.woff2?v2021-03-21);
}
* {
font-family:Zpix;
}
#main-ame-back {
font-family:Zpix;
color: #fd96fd !important;
padding: 15px;
}
a {
color:#fd87c2 !important
}
#main-ame-back h1{
color:#8e45f5 !important;
}
</style>
<img src="https://pbs.twimg.com/media/GKJ6VOdbIAAo2yr?format=png&name=900x900"></img>
<div id="main-ame-back">
<div style="font-size:40px;color: #ebb4dd;font-weight:bolder;">ジェルばんは~</div>
<br>
<h1>🧬UPDATE: Please see <a href="https://huggingface.co/raincandy-u/Rain-7B-v0.2">Here</a> for v0.2 model.</h1>
<h1>🧬Rain-7B-v0.1</h1>
Rain-7B-v0.1 is an experimental model finetuned on <a href="https://huggingface.co/Qwen/Qwen1.5-7B-Chat">Qwen1.5-7B-Chat</a> with thousands of <b>chain of thought</b> conversations.
It work better for `"think step by step"` prompt.
<h1>🧬Evaluation</h1>
|Model name|MMLU|
|---|---|
|Qwen1.5-7B-Chat|55.8|
|Rain-7B-v0.1|58.1|
<h1>🧬Usage</h1>
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "raincandy-u/Rain-7B-v0.1"
messages = [{"role": "user", "content": "What is chain of thoughts?"}]
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"])
```
</div>
|
ukung/AutoCoder_S_6.7B-GGUF | ukung | "2024-05-27T17:05:40Z" | 998 | 7 | null | [
"gguf",
"region:us"
] | null | "2024-05-27T15:56:11Z" | Entry not found |
alvdansen/sketchedoutmanga | alvdansen | "2024-06-16T16:31:58Z" | 998 | 15 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | "2024-06-06T16:41:22Z" | ---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: a boy in a sailor suit frowning
output:
url: images/Sketched_Out_Manga_e000007_01_20240605225456 (1).jpeg
- text: a little creature
output:
url: images/Sketched_Out_Manga_e000007_02_20240605225508.jpeg
- text: a tiefling girl with ram horns and heart shaped sunglasses
output:
url: images/Sketched_Out_Manga_e000007_00_20240605225444.jpeg
- text: a woman with light blue hair, daiton
output:
url: images/ComfyUI_00287_.png
- text: a woman with light blue hair
output:
url: images/ComfyUI_00289_.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: daiton
license: creativeml-openrail-m
---
# Sketched Out Manga
<Gallery />
## Model description
A model meant to create a rough sketch style manga, great for merging with other styles.
The trigger word can be used with it, but it is not required.
## Trigger words
You should use `daiton` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
Model release is for research purposes only. For commercial use, please contact me directly.
[Download](/alvdansen/sketchedoutmanga/tree/main) them in the Files & versions tab.
|
RichardErkhov/realtreetune_-_rho-interpreter-1b-sft-MATH-gguf | RichardErkhov | "2024-06-27T07:48:28Z" | 998 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-27T07:21:07Z" | Entry not found |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.