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
|
|---|---|---|---|---|---|---|---|---|---|
chickencaesar/llama2-platypus-llama2-chat-13B-hf | chickencaesar | "2023-09-29T00:21:19Z" | 1,640 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-28T23:06:56Z" | hello
|
harborwater/open-llama-3b-everythingLM-2048 | harborwater | "2024-01-26T07:52:07Z" | 1,640 | 2 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"en",
"dataset:totally-not-an-llm/EverythingLM-data-V3",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-30T23:05:48Z" | ---
language:
- en
license: apache-2.0
library_name: transformers
datasets:
- totally-not-an-llm/EverythingLM-data-V3
model-index:
- name: open-llama-3b-everythingLM-2048
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: 42.75
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048
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: 71.72
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048
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: 27.16
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048
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: 34.26
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048
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: 66.3
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048
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: 1.52
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048
name: Open LLM Leaderboard
---
Trained on 2 epochs on the EverythingLM-data-V3 dataset.
This model uses the alpaca prompt format:
```
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
Instruction
### Input:
Input
### Response:
```
[<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)
# [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_harborwater__open-llama-3b-everythingLM-2048)
| Metric |Value|
|---------------------------------|----:|
|Avg. |40.62|
|AI2 Reasoning Challenge (25-Shot)|42.75|
|HellaSwag (10-Shot) |71.72|
|MMLU (5-Shot) |27.16|
|TruthfulQA (0-shot) |34.26|
|Winogrande (5-shot) |66.30|
|GSM8k (5-shot) | 1.52|
|
adonlee/LLaMA_2_13B_SFT_v0 | adonlee | "2023-11-21T03:42:35Z" | 1,640 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-03T06:51:04Z" | ---
license: apache-2.0
---
# [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_adonlee__LLaMA_2_13B_SFT_v0)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 50.97 |
| ARC (25-shot) | 62.03 |
| HellaSwag (10-shot) | 83.8 |
| MMLU (5-shot) | 58.39 |
| TruthfulQA (0-shot) | 49.92 |
| Winogrande (5-shot) | 77.27 |
| GSM8K (5-shot) | 12.43 |
| DROP (3-shot) | 12.96 |
|
IkariDev/Athena-v4 | IkariDev | "2023-10-09T09:46:29Z" | 1,640 | 17 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-07T22:15:06Z" | ---
license: cc-by-nc-4.0
---
Experimental Athena v4 model. Use Alpaca format. Suitable for RP, ERP and general stuff.
I should state here that this is a HIGHLY experimental model!
<!-- description start -->
## Description
<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
This repo contains fp16 files of Athena-V4.
[GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GGUF)
[GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GPTQ)
[exl2 - by waldie](https://huggingface.co/waldie/Athena-v4-8bpw-h8-exl2)
[AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-AWQ)
[fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v4)
<!-- [GGUF - by IkariDev](https://huggingface.co/IkariDev/Athena-v4-GGUF)-->
[OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v4-GGUF)
## Ratings:
Note: I have permission of all users to upload their ratings, i DONT screenshot random reviews without asking if i can put them here!
If you want your rating to be here, send me a message over on DC and ill put up a screenshot of it here. DC name is "ikaridev".
<!-- description end -->
<!-- description start -->
## Models+loras used and recipe
- Athena-v3
- Xwin-LM/Xwin-LM-13B-V0.1
- Undi95/PsyMedRP-v1-13B
- cgato/Thespis-13b-v0.2
- jondurbin/airoboros-l2-13b-3.0
```
Athena-v4-tmp1 = [ Athena-v3(0.85)+Xwin-LM/Xwin-LM-13B-V0.1(0.15) ]
Athena-v4-tmp2 = [ Undi95/PsyMedRP-v1-13B(0.55)+cgato/Thespis-13b-v0.2(0.45) ]
Athena-v4-tmp3 = Athena-v4-tmp1(0.55) + Athena-v4-tmp2(0.35)
Athena-v4 = Athena-v4-tmp3 + jondurbin/airoboros-l2-13b-3.0(0.1)
```
<!-- description 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:
```
Thanks to [Undi95](https://huggingface.co/Undi95) for providing the machine for Athena v2 and Athena v3, and giving me infos about how things work. Going forward i will use a merging server provided by a friend. |
Yukang/LongAlpaca-13B | Yukang | "2023-11-01T08:29:13Z" | 1,640 | 13 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"arxiv:2309.12307",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-08T06:21:02Z" | # LongLoRA and LongAlpaca for Long-context LLMs
[](https://huggingface.co/Yukang)
[](https://github.com/dvlab-research/LongLoRA)
[](https://huggingface.co/datasets/Yukang/LongAlpaca-12k)
[](https://arxiv.org/abs/2309.12307)
[](https://github.com/dvlab-research/LongLoRA/blob/main/LICENSE)
[](https://github.com/dvlab-research/LongLoRA/blob/main/DATA_LICENSE)
[](https://github.com/dvlab-research/LongLoRA/blob/main/WEIGHT_LICENSE)
For detailed usage and codes, please visit the [Github project](https://github.com/dvlab-research/LongLoRA).
## TABLE OF CONTENTS
1. [News](#news)
2. [Examples](#examples)
3. [Highlights](#highlights)
4. [How to contribute](#how-to-contribute)
5. [Requirements](#usage-requirements)
6. [Installation and quick guide](#installation-and-quick-guide)
7. [LongAlpaca Data](#longalpaca-data)
8. [Models](#models)
9. [Training](#training)
10. [Evaluation](#evaluation)
11. [Demo](#demo)
12. [Data Generation via Pdf2Text](#data-generation-via-pdf2text)
13. [Citation](#citation)
14. [Acknowledgement](#acknowledgement)
15. [License](#license)
## News
- [x] [2023.10.8] **We release the long instruction-following dataset**, [LongAlpaca-12k](https://huggingface.co/datasets/Yukang/LongAlpaca-12k) and **the corresponding models**, [LongAlpaca-7B](https://huggingface.co/Yukang/LongAlpaca-7B), [LongAlpaca-13B](https://huggingface.co/Yukang/LongAlpaca-13B), and [LongAlpaca-70B](https://huggingface.co/Yukang/LongAlpaca-70B).
- (*The previous sft models*, [Llama-2-13b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) and [Llama-2-70b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft), *have been depreciated*.)
- [x] [2023.10.3] We add support GPTNeoX models. Please refer to this [PR](https://github.com/dvlab-research/LongLoRA/pull/32) for usage. Thanks for @naubull2 for this contribution.
- [x] [2023.9.22] We release all our fine-tuned [models](https://huggingface.co/Yukang), including **70B-32k models**, [LLaMA2-LongLoRA-70B-32k](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k), [LLaMA2-LongLoRA-7B-100k](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft). Welcome to check them out!
- [x] [2023.9.22] We release [Paper](http://arxiv.org/abs/2309.12307) and this GitHub repo, including training and evaluation code.
**LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models [[Paper](http://arxiv.org/abs/2309.12307)]** <br />
[Yukang Chen](https://scholar.google.com/citations?user=6p0ygKUAAAAJ&hl=en),
[Shengju Qian](https://scholar.google.com/citations?user=QNnWmasAAAAJ),
[Haotian Tang](https://scholar.google.com/citations?user=WxL13BAAAAAJ&hl),
[Xin Lai](https://scholar.google.com/citations?user=tqNDPA4AAAAJ&hl=zh-CN),
[Zhijian Liu](https://scholar.google.com/citations?user=3coYSTUAAAAJ&hl=en),
[Song Han](https://scholar.google.com/citations?user=E0iCaa4AAAAJ&hl=zh-CN),
[Jiaya Jia](https://scholar.google.com/citations?user=XPAkzTEAAAAJ&hl=en)<br />
## Highlights
1. In LongLoRA approach, The proposed shifted short attention is easy to implement, compatible with Flash-Attention, and is not required during inference.
2. We released all our models, including models from 7B to 70B, context length from 8k to 100k, including [LLaMA2-LongLoRA-7B-100k](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft), [LLaMA2-LongLoRA-13B-64k](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k), and [LLaMA2-LongLoRA-70B-32k](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k).
3. We built up a long-context instruction-following dataset, [LongAlpaca-12k](#longalpaca-data). We released the corresponding [LongAlpaca-7B](https://huggingface.co/Yukang/LongAlpaca-7B), [LongAlpaca-13B](https://huggingface.co/Yukang/LongAlpaca-13B) and [LongAlpaca-70B](https://huggingface.co/Yukang/LongAlpaca-70B) models. To our best knowledge, this is the first open-sourced long-context 70B model.
## How to Contribute
- Make sure to have git installed.
- Create your own [fork](https://github.com/dvlab-research/LongLoRA/fork) of the project.
- Clone the repository on your local machine, using git clone and pasting the url of this project.
- Read both the `Requirements` and `Installation and Quick Guide` sections below.
- Commit and push your changes.
- Make a pull request when finished modifying the project.
## Usage Requirements
To download and use the [pre-trained weights](#pre-trained-weights) you will need:
1. Hugging Face (HF) account with valid email. Note, the email used for HF must alse be used for the license agreement.
2. Accept the Meta [license and acceptable use policy](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
## Installation and Quick Guide
To install and run the application:
1. [Fork this repo](https://github.com/dvlab-research/LongLoRA/fork) on github
2. Clone the repository on your local machine, using git clone and pasting the url of this project.
3. Run the following code:
```
pip install -r requirements.txt
pip install flash-attn --no-build-isolation
```
4. Use either a [Released model](#released-models) or [Fine tune](#fine-tuning) a model to fit your preferences.
5. Test your model by chat.
6. Deploy your own demo.
## LongAlpaca Data
LongAlpaca-12k contains 9k long QA data that we collected and 3k short QA sampled from the original [Alpaca data](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json). This is to avoid the case that the model might degrade at short instruction following. The data we collect contains various types and amounts as the following figure.
| Data | Short QA | Long QA | Total | Download |
|:---------------|----------|----------|----------|----------|
| LongAlpaca-12k | 3k | 9k | 12k | [Link](https://huggingface.co/datasets/Yukang/LongAlpaca-12k) |
Following the original Alpaca format, our Long QA data uses the following prompts for fine-tuning:
- `instruction`: `str`, describes the task the model should perform. For example, to answer a question after reading a book section or paper. We vary the contents and questions to make instructions diverse.
- `output`: `str`, the answer to the instruction.
We did not use the `input` format in the Alpaca format for simplicity.
## Models
### Models with supervised fine-tuning
| Model | Size | Context | Train | Link |
|:---------------|------|---------|---------|-----------------------------------------------------------------------------------------------------------------------|
| LongAlpaca-7B | 7B | 32768 | Full FT | [Model](https://huggingface.co/Yukang/LongAlpaca-7B) |
| LongAlpaca-13B | 13B | 32768 | Full FT | [Model](https://huggingface.co/Yukang/LongAlpaca-13B) |
| LongAlpaca-70B | 70B | 32768 | LoRA+ | [Model](https://huggingface.co/Yukang/LongAlpaca-70B) [(LoRA-weight)](https://huggingface.co/Yukang/LongAlpaca-70B-lora) |
### Models with context extension via fully fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k-ft | 7B | 8192 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k-ft) |
| Llama-2-7b-longlora-16k-ft | 7B | 16384 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k-ft) |
| Llama-2-7b-longlora-32k-ft | 7B | 32768 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k-ft) |
| Llama-2-7b-longlora-100k-ft | 7B | 100000 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft) |
| Llama-2-13b-longlora-8k-ft | 13B | 8192 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k-ft) |
| Llama-2-13b-longlora-16k-ft | 13B | 16384 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k-ft) |
| Llama-2-13b-longlora-32k-ft | 13B | 32768 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k-ft) |
### Models with context extension via improved LoRA fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|---------------------------------------------------------------------|
| Llama-2-7b-longlora-8k | 7B | 8192 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k) |
| Llama-2-7b-longlora-16k | 7B | 16384 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k) |
| Llama-2-7b-longlora-32k | 7B | 32768 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k) |
| Llama-2-13b-longlora-8k | 13B | 8192 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k) |
| Llama-2-13b-longlora-16k | 13B | 16384 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k) |
| Llama-2-13b-longlora-32k | 13B | 32768 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k) |
| Llama-2-13b-longlora-64k | 13B | 65536 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k) |
| Llama-2-70b-longlora-32k | 70B | 32768 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k) |
| Llama-2-70b-chat-longlora-32k | 70B | 32768 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k) |
## Training
### Pre-trained weights
We use LLaMA2 models as the pre-trained weights and fine-tune them to long context window sizes. Download based on your choices.
| Pre-trained weights |
|:-------------------------------------------------------------------------------------|
| [Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) |
|[Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) |
| [Llama-2-70b-hf](https://huggingface.co/meta-llama/Llama-2-70b-hf) |
| [Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) |
| [Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) |
| [Llama-2-70b-chat-hf](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) |
This project also supports GPTNeoX models as the base model architecture. Some candidate pre-trained weights may include [GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b), [Polyglot-ko-12.8B](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) and other variants.
### Fine-tuning
```
torchrun --nproc_per_node=8 fine-tune.py \
--model_name_or_path path_to/Llama-2-7b-hf \
--bf16 True \
--output_dir path_to_saving_checkpoints \
--cache_dir path_to_cache \
--model_max_length 8192 \
--use_flash_attn True \
--low_rank_training False \
--num_train_epochs 1 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 2 \
--gradient_accumulation_steps 8 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 1000 \
--save_total_limit 2 \
--learning_rate 2e-5 \
--weight_decay 0.0 \
--warmup_steps 20 \
--lr_scheduler_type "constant_with_warmup" \
--logging_steps 1 \
--deepspeed "ds_configs/stage2.json" \
--tf32 True \
--max_steps 1000
```
- Please remember to change `path_to/Llama-2-7b-hf`, `path_to_saving_checkpoints`, `path_to_cache` to your own directory.
- Note that you can change `model_max_length` to other values.
- You could change `ds_configs/stage2.json` to `ds_configs/stage3.json` if you want.
- Please set `use_flash_attn` as `False` if you use V100 machines or do not install flash attention.
- You can set `low_rank_training` as `False` if you want to use fully fine-tuning. It will cost more GPU memory and slower, but the performance will be a bit better.
- When training is finished, to get the full model weight:
```
cd path_to_saving_checkpoints && python zero_to_fp32.py . pytorch_model.bin
```
### Supervised Fine-tuning
```
torchrun --nproc_per_node=8 supervised-fine-tune.py \
--model_name_or_path path_to_Llama2_chat_models \
--bf16 True \
--output_dir path_to_saving_checkpoints \
--model_max_length 32768 \
--use_flash_attn True \
--data_path LongAlpaca-12k.json \
--low_rank_training True \
--num_train_epochs 3 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 2 \
--gradient_accumulation_steps 1 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 1000 \
--save_total_limit 2 \
--learning_rate 2e-5 \
--weight_decay 0.0 \
--warmup_steps 20 \
--lr_scheduler_type "constant_with_warmup" \
--logging_steps 1 \
--deepspeed "ds_configs/stage2.json" \
--tf32 True
```
- There is no need to make supervised fine-tuning upon the fine-tuned context extended models. It is all right to directly use base model as Llama2-chat models, as the amount of long instruction following data is enough for SFT.
- Our long instruction following data can be found in [LongAlpaca-12k.json](https://huggingface.co/datasets/Yukang/LongAlpaca-12k).
### Get trainable weights in low-rank training
In low-rank training, we set embedding and normalization layers as trainable. Please use the following line to extract the trainable weights `trainable_params.bin` from `pytorch_model.bin`
```
python3 get_trainable_weights.py --checkpoint_path path_to_saving_checkpoints --trainable_params "embed,norm"
```
### Merge LoRA Weight
Merge the LoRA weights of `pytorch_model.bin` and trainable parameters `trainable_params.bin`, save the resulting model into your desired path in the Hugging Face format:
```
python3 merge_lora_weights_and_save_hf_model.py \
--base_model path_to/Llama-2-7b-hf \
--peft_model path_to_saving_checkpoints \
--context_size 8192 \
--save_path path_to_saving_merged_model
```
For example,
```
python3 merge_lora_weights_and_save_hf_model.py \
--base_model /dataset/pretrained-models/Llama-2-7b-hf \
--peft_model /dataset/yukangchen/hf_models/lora-models/Llama-2-7b-longlora-8k \
--context_size 8192 \
--save_path /dataset/yukangchen/models/Llama-2-7b-longlora-8k-merged
```
## Evaluation
### Perplexity Validation
To evaluate a model that is trained in the low-rank setting, please set both `base_model` and `peft_model`. `base_model` is the pre-trained weight. `peft_model` is the path to the saved checkpoint, which should contain `trainable_params.bin`, `adapter_model.bin` and `adapter_config.json`. For example,
```
python3 eval.py --seq_len 8192 --context_size 8192 --batch_size 1 --base_model path_to/Llama-2-7b-hf --peft_model path_to_saving_checkpoints --data_path pg19/test.bin
```
To evaluate a model that is fully fine-tuned, you only need to set `base_model` as the path to the saved checkpoint, which should contain `pytorch_model.bin` and `config.json`. `peft_model` should be ignored.
```
python3 eval.py --seq_len 8192 --context_size 8192 --batch_size 1 --base_model path_to_saving_checkpoints --data_path pg19/test.bin
```
- Note that `--seq_len` is to set the sequence length for evaluation. `--context_size` is to set the context length of the model during fine-tuning. `--seq_len` should not be larger than `--context_size`.
- We have already tokenized the validation and test splits of PG19 and proof-pile dataset into `pg19/validation.bin`, `pg19/test.bin`, and `proof-pile/test_sampled_data.bin`, with the tokenizer of LLaMA. `proof-pile/test_sampled_data.bin` contains 128 documents that are randomly sampled from the total proof-pile test split. For each document, it has at least 32768 tokens. We also release the sampled ids in [proof-pile/test_sampled_ids.bin](https://drive.google.com/file/d/1cnzWODLRQYAd7HeugzLCIhaqzaLZv7J5/view?usp=share_link). You can download them from the links below.
| Dataset | Split | Link |
|:-----------|------------|--------------------------------------------------------------------------------------------------------------|
| PG19 | validation | [pg19/validation.bin](https://drive.google.com/file/d/1rbJvb0qRIf2mQoN2ON7S93TbTzMnlrN6/view?usp=share_link) |
| PG19 | test | [pg19/test.bin](https://drive.google.com/file/d/1QANDMdctpacPAYgS04adDXqByGEq-Ret/view?usp=share_link) |
| Proof-pile | test | [proof-pile/test_sampled_data.bin](https://drive.google.com/file/d/1bUI5lPDvrqzY_XXJJ2sSuvZx0Y9AZClE/view?usp=share_link) |
### Passkey Retrieval
We provide a manner to test the passkey retrieval accuracy. For example,
```
python3 passkey_retrivial.py \
--context_size 32768 \
--base_model path_to/Llama-2-7b-longlora-32k \
--max_tokens 32768 \
--interval 1000
```
- Note that the `context_size` is the context length during fine-tuning.
- `max_tokens` is maximum length for the document in passkey retrieval evaluation.
- `interval` is the interval during the document length increasing. It is a rough number because the document increases by sentences.
## Demo
### Local Inference
To chat with [Llama-2-13b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) or [Llama-2-70b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft), you need to run `merge_lora_weights_and_save_hf_model.py` first, and then:
```
python3 inference.py \
--base_model path_to_model \
--question $question \
--context_size $context_length \
--max_gen_len $max_gen_len \
--flash_attn True \
--material $material_content \
--material_type $material_type \
--material_title $material_title
```
To ask a question related to a book:
```
python3 inference.py \
--base_model /data/models/Llama-2-13b-chat-longlora-32k-sft \
--question "Why doesn't Professor Snape seem to like Harry?" \
--context_size 32768 \
--max_gen_len 512 \
--flash_attn True \
--material "materials/Harry Potter and the Philosophers Stone_section2.txt" \
--material_type "book" \
--material_title "Harry Potter and the Philosophers Stone"
```
Note that you can ignore `material_type` or `material_title`.
To ask a question related to a paper:
```
python3 inference.py \
--base_model /data/models/Llama-2-13b-chat-longlora-32k-sft \
--question "What are the main contributions and novelties of this work?" \
--context_size 32768 \
--max_gen_len 512 \
--flash_attn True \
--material "materials/paper1.txt" \
--material_type "paper"
```
### Online Demo
To deploy your own demo run
```
python3 demo.py \
--base_model path_to_model \
--context_size $context_size \
--max_gen_len $max_gen_len \
--flash_attn True
```
Example
```
python3 demo.py \
--base_model /data/models/Llama-2-13b-chat-longlora-32k-sft \
--context_size 32768 \
--max_gen_len 512 \
--flash_attn True
```
- Note that `flash_attn=True` will make the generation slow but save much GPU memory.
## Data Generation via Pdf2text
During our dataset collection, we convert paper and books from pdf to text. The conversion quality has a large influence on the final model quality. We think that this step is non-trivial. We release the tool for the pdf2txt conversion, in the folder `pdf2txt`. It is built upon `pdf2image`, `easyocr`, `ditod` and `detectron2`. Please refer to the [README.md](pdf2txt/README.md) in `pdf2txt` for more details.
## Citation
If you find this project useful in your research, please consider citing:
```
@article{longlora,
title={LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models},
author={Yukang Chen and Shengju Qian and Haotian Tang and Xin Lai and Zhijian Liu and Song Han and Jiaya Jia},
journal={arXiv:2309.12307},
year={2023}
}
```
```
@misc{long-alpaca,
author = {Yukang Chen and Shaozuo Yu and Shengju Qian and Haotian Tang and Xin Lai and Zhijian Liu and Song Han and Jiaya Jia},
title = {Long Alpaca: Long-context Instruction-following models},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/dvlab-research/LongLoRA}},
}
```
## Acknowledgement
- This work is built upon the [LLaMA2](https://ai.meta.com/llama) as the pre-trained models.
- This work can also be built upon the [GPTNeoX-HF](https://huggingface.co/docs/transformers/model_doc/gpt_neox) which is based upon [EleutherAI/GPTNeoX](https://github.com/EleutherAI/gpt-neox) as the pre-trained model architecture.
- This work is based on [DeepSpeed](https://github.com/microsoft/DeepSpeed), [peft](https://github.com/huggingface/peft), and [Flash-Attention2](https://github.com/Dao-AILab/flash-attention) for acceleration.
- Some evaluation code is modified upon [Landmark Attention](https://github.com/epfml/landmark-attention).
- We use [LongChat](https://github.com/DachengLi1/LongChat) for the retrieval evaluation.
## License
- LongLoRA is licensed under the Apache License 2.0. This means that it requires the preservation of copyright and license notices.
- Data and weights are under CC-BY-NC 4.0 License. They are licensed for research use only, and allowed only non-commercial. Models trained using the dataset should not be used outside of research purposes. |
AnnaWegmann/Style-Embedding | AnnaWegmann | "2022-05-20T07:46:47Z" | 1,639 | 7 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"roberta",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"endpoints_compatible",
"text-embeddings-inference",
"region:us"
] | sentence-similarity | "2022-05-11T12:42:35Z" | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# Style Embedding
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
for more info see [Style-Embeddings](https://github.com/nlpsoc/Style-Embeddings)
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 26250 with parameters:
```
{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.TripletLoss.TripletLoss` with parameters:
```
{'distance_metric': 'TripletDistanceMetric.COSINE', 'triplet_margin': 0.5}
```
Parameters of the fit()-Method:
```
{
"epochs": 4,
"evaluation_steps": 0,
"evaluator": "sentence_transformers.evaluation.TripletEvaluator.TripletEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'transformers.optimization.AdamW'>",
"optimizer_params": {
"correct_bias": true,
"eps": 1e-08,
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 10500,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information --> |
hassanblend/hassanblend1.4 | hassanblend | "2024-04-30T17:01:30Z" | 1,639 | 435 | diffusers | [
"diffusers",
"stable-diffusion",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2022-11-21T12:43:55Z" | ---
title: Hassanblend1.4
emoji: 📚
colorFrom: green
colorTo: indigo
sdk: gradio
sdk_version: 3.11.0
app_file: app.py
pinned: false
thumbnail: "https://i.imgur.com/PVThZvk.png"
license: creativeml-openrail-m
tags:
- stable-diffusion
- text-to-image
inference: true
---
# HassanBlend1.4
I am hassan, I created HassansBlend, the latest version currently is 1.4. I continue to iterate and improve on this model over time. Feel free to check out our discord or rentry page for more examples with prompts and outputs generated.
I have also some custom created content such as enhancement hypernetworks/embeddings etc for patreons or KoFi subscribers only on my pages below
<b> Links </b><br>
<b>Patreon</b>
<a href="https://www.patreon.com/sdhassan" target="_blank"><img src="https://i.imgur.com/sR32SqJ.jpg"></img></a>
<b>KoFi</b>
<a href="https://ko-fi.com/sdhassan" target="_blank"><img src="https://i.imgur.com/0P7CTN4.png"></img></a>
<b>Discord</b>
<a href="https://discord.gg/sdmodelers" target="_blank"><img src="https://i.imgur.com/HC1iHwg.png"></img></a>
### Quicklinks:
* [Latest Setup](https://rentry.org/sdhassan#current-setup)
* [HassanBlend Model Finetune Updates](https://rentry.org/sdhassan#hassanblend-finetuning-updates)
* [Latest Patreon Posts](https://rentry.org/sdhassan#patreon-posts)
* [Models](https://rentry.org/sdhassan#merged-models)
* [HassanBlend1.4](https://rentry.org/sdhassan#hassanblend14-downloads)
* [Prompts](https://rentry.org/sdhassan#prompts)
* [Photorealistic Tips](https://rentry.org/sdhassan#tips-for-photorealistic-images)
* [Embeddings](https://rentry.org/sdhassan#embeddings)
* [Hypernetworks](https://rentry.org/sdhassan#hypernetworks)
* [Wildcards](https://rentry.org/sdhassan#wildcards-i-made)
* [MyTools](https://rentry.org/sdhassan#my-tools)
* [Settings I use](https://rentry.org/sdhassan#settings)
Model details and examples with sample prompts: https://rentry.org/sdhassan
# Gradio Demo
We support a [Gradio](https://github.com/gradio-app/gradio) Web UI to run hassanblend1.4:
[](https://huggingface.co/spaces/akhaliq/hassanblend1.4)
|
TehVenom/Pygmalion_AlpacaLora-7b | TehVenom | "2023-05-04T18:53:07Z" | 1,639 | 3 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-04-30T22:52:52Z" | The LLaMA based Pygmalion-7b model:
https://huggingface.co/PygmalionAI/pygmalion-7b
Merged alongside Tloen's Alpaca LoRA:
https://huggingface.co/tloen/alpaca-lora-7b
This was done to test whether LoRAs trained for other LLaMA fine tunes worked for Pygmalion,
and to have it available on inference backends that do not support LoRAs just yet.
Treat this as a normal HF Transformers model. |
Enno-Ai/ennodata-7b | Enno-Ai | "2023-06-06T15:08:28Z" | 1,639 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-02T21:50:53Z" | Entry not found |
Panchovix/airoboros-33b-gpt4-1.2-SuperHOT-8k | Panchovix | "2023-11-18T06:04:49Z" | 1,639 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-25T23:01:16Z" | ---
license: other
---
[Airoboros 33b GPT4 1.2](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.2) merged with kaiokendev's [33b SuperHOT 8k LoRA](https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test), without quant. (Full FP16 model)
# [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_Panchovix__airoboros-33b-gpt4-1.2-SuperHOT-8k)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 25.35 |
| ARC (25-shot) | 24.66 |
| HellaSwag (10-shot) | 31.23 |
| MMLU (5-shot) | 23.13 |
| TruthfulQA (0-shot) | 47.44 |
| Winogrande (5-shot) | 50.43 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 0.59 |
|
jordiclive/Llama-2-70b-oasst-1-200 | jordiclive | "2024-02-10T20:59:44Z" | 1,639 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"sft",
"en",
"de",
"es",
"fr",
"dataset:OpenAssistant/oasst1",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-25T12:14:07Z" | ---
license: apache-2.0
language:
- en
- de
- es
- fr
tags:
- sft
inference: false
datasets:
- OpenAssistant/oasst1
---
# Open-Assistant Llama2 70B SFT OASST
This model is a fine-tuning of [Llama2 70B](https://huggingface.co/meta-llama/Llama-2-70b-hf) LLM.
It was trained on a mixture of OASST top-1 threads.
## Model Details
- **Finetuned from:** [Llama2 70B](https://huggingface.co/meta-llama/Llama-2-70b-hf)
- **Model type:** Causal decoder-only transformer language model
- **Language:** English, German, Spanish, French (and limited capabilities in Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish);
- **License:** Apache 2.0
- **Contact:** [Open-Assistant Discord](https://ykilcher.com/open-assistant-discord)
## Prompting
Two special tokens are used to mark the beginning of user and assistant turns:
`<|prompter|>` and `<|assistant|>`. Each turn ends with a `</s>` token.
Input prompt example:
```
<|prompter|>What is a meme, and what's the history behind this word?</s><|assistant|>
```
The input ends with the `<|assistant|>` token to signal that the model should
start generating the assistant reply.
### Citation
```
@misc{jordiclive_llama2_70b_oasst_1_200,
title={{Open-Assistant Llama2 70B SFT OASST}},
author={{Jordan Clive}},
howpublished={\url{https://huggingface.co/jordiclive/Llama-2-70b-oasst-1-200}},
year={2023},
note={Apache 2.0 License. Finetuned on OASST top-1 threads. Languages supported: English, German, Spanish, French.},
url={https://huggingface.co/jordiclive/Llama-2-70b-oasst-1-200},
}
``` |
NousResearch/Nous-Puffin-70B | NousResearch | "2023-09-25T02:52:09Z" | 1,639 | 23 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"llama-2",
"sft",
"eng",
"dataset:LDJnr/Puffin",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-30T16:26:25Z" | ---
language:
- eng
tags:
- llama-2
- sft
license:
- mit
datasets:
- LDJnr/Puffin
---
## **Redmond-Puffin-70B**
**Based off Puffin 13B which was the first commercially available language model released by Nous Research!**
Compute provided by PygmalionAI, thank you! Follow PygmalionAI on Twitter @pygmalion_ai.
This is a larger version of Puffin which was originally the worlds first third-party llama-2 fine-tune. leveraging a hand curated set of 3K high quality examples, many of which take full advantage of the 4096 context length of Llama 2. This model was fine-tuned by Nous Research, with LDJ leading the training and dataset curation, along with significant dataset formation contributions by J-Supha.
Special thank you to Pygmalion AI for sponsoring the compute.
Special thank you to Emozilla for assisting with training experimentations and benchmarking.
## Model Training
Redmond-Puffin 70B is a new model trained for multiple epochs on a dataset of 3,000 carefully curated GPT-4 examples, most of which are long context conversations between a real human and GPT-4.
Additional data came from carefully curated sub sections of datasets such as CamelAI's Physics, Chemistry, Biology and Math.
## Prompt Format
The reccomended model usage is:
WARNING, THE PREVIOUS RECCOMENDATION THAT SAID TO USE "### human" and "# response" WAS A CRITICAL ERROR, PLEASE USE THE ACCURATE PREFIX AND SUFFIX BELOW.
```
USER:
ASSISTANT:
```
## When should I use Puffin or Hermes 2?
Although full benchmarks have not completed for Puffin,
Original Puffin 13B and Hermes-2 13B both beat previous SOTA for GPT4ALL benchmarks, with Hermes-2 winning by a 0.1% margin over Puffin.
Overall, for general purpose zero-shot and/or single turn instructions, Hermes will likely be the way to go. Puffin may be prefferred for creative long conversation interactions, like having Puffin play a character or help brain storm creative ideas or concepts that make contextual sense within an already deep conversation.
Thank you to the comprehensive analysis and comparison of Puffin and Hermes by reddit user WolframRavenwolf here: https://www.reddit.com/r/LocalLLaMA/comments/158j9r9/nous_hermes_llama2_vs_redmond_puffin_13b/
## Example Outputs!:
## Notable Features:
- The first Llama-2 based fine-tuned model released by Nous Research.
- Ability to recall information upto 2023 without internet (ChatGPT cut off date is in 2021)
- Pretrained on 2 trillion tokens of text. (This is double the amount of most Open LLM's)
- Pretrained with a context length of 4096 tokens, and fine-tuned on a significant amount of multi-turn conversations reaching that full token limit.
- The first commercially available language model released by Nous Research.
## Future Plans
This is a relatively early build amongst the grand plans for the future of Puffin!
Current limitations: Some token mismatch problems have been identified, these may effect the current output quality, we plan to have this solved in Puffin V2 along with other improvements.
## How you can help!
In the near future we plan on leveraging the help of domain specific expert volunteers to eliminate any mathematically/verifiably incorrect answers from our training curations.
If you have at-least a bachelors in mathematics, physics, biology or chemistry and would like to volunteer even just 30 minutes of your expertise time, please contact LDJ on discord!
## Benchmarks (New benchmarks coming soon, however here are the 13B benchmarks for now)!
As of Puffins release, it achieves a new SOTA for the GPT4All benchmarks! Supplanting Hermes for the #1 position!
(Rounded to nearest tenth)
Previous Sota: Hermes - 68.8
New Sota: Puffin - 69.9 (+1.1)
Puffin 13B supplants Hermes-2 for the #1 spot in Arc-E, HellaSwag and Winogrande!
Puffin also perfectly ties with Hermes in PIQA, however Hermes-2 still excels in much of Big Bench and AGIEval, so it's highly reccomended you give it a try as well!
|
openthaigpt/openthaigpt-1.0.0-alpha-7b-chat-ckpt-hf | openthaigpt | "2024-01-06T04:58:24Z" | 1,639 | 5 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"openthaigpt",
"th",
"en",
"dataset:kobkrit/rd-taxqa",
"dataset:iapp_wiki_qa_squad",
"dataset:Thaweewat/alpaca-cleaned-52k-th",
"dataset:Thaweewat/instruction-wild-52k-th",
"dataset:Thaweewat/databricks-dolly-15k-th",
"dataset:Thaweewat/hc3-24k-th",
"dataset:Thaweewat/gpteacher-20k-th",
"dataset:Thaweewat/onet-m6-social",
"dataset:Thaweewat/alpaca-finance-43k-th",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-04T09:23:55Z" | ---
license: apache-2.0
datasets:
- kobkrit/rd-taxqa
- iapp_wiki_qa_squad
- Thaweewat/alpaca-cleaned-52k-th
- Thaweewat/instruction-wild-52k-th
- Thaweewat/databricks-dolly-15k-th
- Thaweewat/hc3-24k-th
- Thaweewat/gpteacher-20k-th
- Thaweewat/onet-m6-social
- Thaweewat/alpaca-finance-43k-th
language:
- th
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- openthaigpt
- llama
---
# 🇹🇭 OpenThaiGPT 1.0.0-alpha
<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2Fb8eiMDaqiEQL6ahbAY0h%2Fimage.png?alt=media&token=6fce78fd-2cca-4c0a-9648-bd5518e644ce
https://openthaigpt.aieat.or.th/" width="200px">
OpenThaiGPT Version 1.0.0-alpha is the first Thai implementation of a 7B-parameter LLaMA v2 Chat model finetuned to follow Thai translated instructions below and makes use of the Huggingface LLaMA implementation.
# ---- Full Huggingface Checkpoint Model ----
## Upgrade from OpenThaiGPT 0.1.0-beta
- Using Facebook LLama v2 model 7b chat as a base model which is pretrained on over 2 trillion token.
- Context Length is upgrade from 2048 token to 4096 token
- Allow research and commerical use.a
## Pretrain Model
- [https://huggingface.co/meta-llama/Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat)
## Support
- Official website: https://openthaigpt.aieat.or.th
- Facebook page: https://web.facebook.com/groups/openthaigpt
- A Discord server for discussion and support [here](https://discord.gg/rUTp6dfVUF)
- E-mail: [email protected]
## License
**Source Code**: License Apache Software License 2.0.<br>
**Weight**: Research and **Commercial uses**.<br>
## Code and Weight
**Colab Demo**: https://colab.research.google.com/drive/1kDQidCtY9lDpk49i7P3JjLAcJM04lawu?usp=sharing<br>
**Finetune Code**: https://github.com/OpenThaiGPT/openthaigpt-finetune-010beta<br>
**Inference Code**: https://github.com/OpenThaiGPT/openthaigpt<br>
**Weight (Lora Adapter)**: https://huggingface.co/openthaigpt/openthaigpt-1.0.0-alpha-7b-chat<br>
**Weight (Huggingface Checkpoint)**: https://huggingface.co/openthaigpt/openthaigpt-1.0.0-alpha-7b-chat-ckpt-hf<br>
**Weight (GGML)**: https://huggingface.co/openthaigpt/openthaigpt-1.0.0-alpha-7b-chat-ggml<br>
**Weight (Quantized 4bit GGML)**: https://huggingface.co/openthaigpt/openthaigpt-1.0.0-alpha-7b-chat-ggml-q4
## Sponsors
Pantip.com, ThaiSC<br>
<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2FiWjRxBQgo0HUDcpZKf6A%2Fimage.png?alt=media&token=4fef4517-0b4d-46d6-a5e3-25c30c8137a6" width="100px">
<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2Ft96uNUI71mAFwkXUtxQt%2Fimage.png?alt=media&token=f8057c0c-5c5f-41ac-bb4b-ad02ee3d4dc2" width="100px">
### Powered by
OpenThaiGPT Volunteers, Artificial Intelligence Entrepreneur Association of Thailand (AIEAT), and Artificial Intelligence Association of Thailand (AIAT)
<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2F6yWPXxdoW76a4UBsM8lw%2Fimage.png?alt=media&token=1006ee8e-5327-4bc0-b9a9-a02e93b0c032" width="100px">
<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2FBwsmSovEIhW9AEOlHTFU%2Fimage.png?alt=media&token=5b550289-e9e2-44b3-bb8f-d3057d74f247" width="100px">
### Authors
* Kobkrit Viriyayudhakorn ([email protected])
* Sumeth Yuenyong ([email protected])
* Thaweewat Rugsujarit ([email protected])
* Jillaphat Jaroenkantasima ([email protected])
* Norapat Buppodom ([email protected])
* Koravich Sangkaew ([email protected])
* Peerawat Rojratchadakorn ([email protected])
* Surapon Nonesung ([email protected])
* Chanon Utupon ([email protected])
* Sadhis Wongprayoon ([email protected])
* Nucharee Thongthungwong ([email protected])
* Chawakorn Phiantham ([email protected])
* Patteera Triamamornwooth ([email protected])
* Nattarika Juntarapaoraya ([email protected])
* Kriangkrai Saetan ([email protected])
* Pitikorn Khlaisamniang ([email protected])
<i>Disclaimer: Provided responses are not guaranteed.</i>
# [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_openthaigpt__openthaigpt-1.0.0-alpha-7b-chat-ckpt-hf)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 42.05 |
| ARC (25-shot) | 50.85 |
| HellaSwag (10-shot) | 74.89 |
| MMLU (5-shot) | 40.02 |
| TruthfulQA (0-shot) | 47.23 |
| Winogrande (5-shot) | 69.06 |
| GSM8K (5-shot) | 3.87 |
| DROP (3-shot) | 8.42 |
|
Aspik101/StableBeluga-13B-instruct-PL-lora_unload | Aspik101 | "2023-08-04T17:33:25Z" | 1,639 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"facebook",
"meta",
"llama-2",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-04T17:19:48Z" | ---
language:
- pl
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
license: other
model_type: llama-2
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
--- |
digiplay/MGM | digiplay | "2023-11-30T21:12:57Z" | 1,639 | 2 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-08-16T19:39:37Z" | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/109568/mgmv1
Sample image generated by huggingface's API :
|
gaodrew/gaodrew-llama-30b-instruct-2048-Open-Platypus-100steps | gaodrew | "2023-08-18T06:36:10Z" | 1,639 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-18T06:07:11Z" | Entry not found |
zarakiquemparte/zaraxe-l2-7b | zarakiquemparte | "2023-08-23T16:22:35Z" | 1,639 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"llama2",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-23T15:38:10Z" | ---
license: other
tags:
- llama2
---
# Model Card: ZaraXE L2 7b
This model uses [Zarafusionex L2 7b without LimaRP](https://huggingface.co/zarakiquemparte/zarafusionex-l2-7b) (71%) as a base with [Airoboros L2 7B GPT4 2.0](https://huggingface.co/jondurbin/airoboros-l2-7b-gpt4-2.0) (29%) and the result of this merge was merged with [LimaRP LLama2 7B Lora](https://huggingface.co/lemonilia/limarp-llama2).
This merge of models(Zarafusionex w/o LimaRP and Airoboros) was done with this [script](https://github.com/zarakiquemparte/zaraki-tools/blob/main/merge-cli.py)
This merge of Lora with Model was done with this [script](https://github.com/zarakiquemparte/zaraki-tools/blob/main/apply-lora.py)
Merge illustration:
## Usage:
Since this is a merge between Zarafusionex, Airoboros and LimaRP, the following instruction formats should work:
Alpaca 2:
```
### Instruction:
<prompt>
### Response:
<leave a newline blank for model to respond>
```
LimaRP instruction format:
```
<<SYSTEM>>
<character card and system prompt>
<<USER>>
<prompt>
<<AIBOT>>
<leave a newline blank for model to respond>
```
## Bias, Risks, and Limitations
This model is not intended for supplying factual information or advice in any form
## Training Details
This model is merged and can be reproduced using the tools mentioned above. Please refer to all provided links for extra model-specific details. |
migtissera/Synthia-70B-v1.1 | migtissera | "2023-11-17T21:32:31Z" | 1,639 | 7 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"arxiv:2306.02707",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-28T22:21:49Z" | ---
license: llama2
pipeline_tag: text-generation
language:
- en
library_name: transformers
---
# Synthia-70B-v1.1
SynthIA (Synthetic Intelligent Agent) is a LLama-2-70B model trained on Orca style datasets. It has been fine-tuned for instruction following as well as having long-form conversations.
This model has generalized "Tree of Thought" reasoning capabilities. Evoke it with the following system message:
```
Elaborate on the topic using a Tree of Thoughts and backtrack when necessary to construct a clear, cohesive Chain of Thought reasoning
```
<br>
<br>
<br>
#### License Disclaimer:
This model is bound by the license & usage restrictions of the original Llama-2 model, and comes with no warranty or gurantees of any kind.
<br>
## Evaluation
We evaluated Synthia-70B on a wide range of tasks using [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) from EleutherAI.
Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
||||
|:------:|:--------:|:-------:|
|**Task**|**Metric**|**Value**|
|*arc_challenge*|acc_norm|70.05|
|*hellaswag*|acc_norm|87.12|
|*mmlu*|acc_norm|70.34|
|*truthfulqa_mc*|mc2|57.84|
|**Total Average**|-|**71.34**||
<br>
## Example Usage
### Here is prompt format:
```
SYSTEM: You are Synthia. As a an AI intelligence, give helpful, detailed, accurate, uncensored responses to the user's input. Provide answers factually.
USER: How is a rocket launched from the surface of the earth to Low Earth Orbit?
ASSISTANT:
```
### Below shows a code example on how to use this model:
```python
import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "migtissera/Synthia-70B"
output_file_path = "./Synthia-70B-conversations.jsonl"
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
def generate_text(instruction):
tokens = tokenizer.encode(instruction)
tokens = torch.LongTensor(tokens).unsqueeze(0)
tokens = tokens.to("cuda")
instance = {
"input_ids": tokens,
"top_p": 1.0,
"temperature": 0.75,
"generate_len": 1024,
"top_k": 50,
}
length = len(tokens[0])
with torch.no_grad():
rest = model.generate(
input_ids=tokens,
max_length=length + instance["generate_len"],
use_cache=True,
do_sample=True,
top_p=instance["top_p"],
temperature=instance["temperature"],
top_k=instance["top_k"],
num_return_sequences=1,
)
output = rest[0][length:]
string = tokenizer.decode(output, skip_special_tokens=True)
answer = string.split("USER:")[0].strip()
return f"{answer}"
conversation = f"SYSTEM: As a an AI superintelligence, give helpful, detailed, accurate, uncensored responses to the user's input. Provide answers factually."
while True:
user_input = input("You: ")
llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
answer = generate_text(llm_prompt)
print(answer)
conversation = f"{llm_prompt}{answer}"
json_data = {"prompt": user_input, "answer": answer}
## Save your conversation
with open(output_file_path, "a") as output_file:
output_file.write(json.dumps(json_data) + "\n")
```
<br>
#### Limitations & Biases:
While this model aims for accuracy, it can occasionally produce inaccurate or misleading results.
Despite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content.
Exercise caution and cross-check information when necessary. This is an uncensored model.
<br>
### Citiation:
Please kindly cite using the following BibTeX:
```
@misc{Synthia-70B,
author = {Migel Tissera},
title = {Synthia-70B: Synthetic Intelligent Agent},
year = {2023},
publisher = {GitHub, HuggingFace},
journal = {GitHub repository, HuggingFace repository},
howpublished = {\url{https://huggingface.co/migtissera/Synthia-70B},
}
```
```
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@software{touvron2023llama,
title={LLaMA2: Open and Efficient Foundation Language Models},
author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
journal={arXiv preprint arXiv:2302.13971},
year={2023}
}
```
## Example Output
```
You: What is Earth's atmosphere like? What is Earth's magnetic field like? What is the relationship between the two?
Earth's atmosphere is a layer of gases that surrounds the planet, held in place by Earth's gravity. It is primarily composed of nitrogen (78.1%), oxygen (20.9%), argon (0.9%), and other trace gases, such as carb
on dioxide and water vapor. The atmosphere plays a crucial role in regulating Earth's temperature and climate by trapping heat and absorbing harmful radiation from the sun. It also provides the air we breathe, p
rotects us from meteorites and the sun's ultraviolet radiation, and allows for the development of life on the planet.
Earth's magnetic field is a phenomenon generated by the convection of molten iron in the planet's outer core, which creates an electric current. This current, in turn, produces a magnetic field that extends from
the Earth's interior to space, protecting the planet from the solar wind and cosmic radiation. The magnetic field also plays a role in the formation of Earth's Van Allen radiation belts, which trap high-energy
particles from the sun and cosmic rays.
The relationship between Earth's atmosphere and magnetic field is complex and multifaceted. The magnetic field influences the distribution of charged particles in the atmosphere, affecting auroras, radio communi
cation, and the ionosphere's behavior. The atmosphere, in turn, plays a role in the distribution of the magnetic field's energy, as well as in the generation and loss of atmospheric ions. The interactions betwee
n the atmosphere and the magnetic field also influence the dynamics of Earth's climate and the long-term evolution of the planet's environment.
You: Elaborate the the complex relationship between the two
The complex relationship between Earth's atmosphere and magnetic field can be elaborated upon in several ways. Firstly, the magnetic field influences the distribution of charged particles in the atmosphere. For
example, the magnetic field deflects the solar wind particles that would otherwise strip away the atmosphere. This deflection creates a bow shock, where the solar wind particles slow down and dissipate their ene
rgy, producing a shock wave that propagates downstream from the Earth. The magnetic field also guides charged particles from the solar wind into the inner magnetosphere, where they become trapped and produce the
Van Allen radiation belts.
Secondly, the atmosphere plays a role in the distribution of the magnetic field's energy. The ionosphere, which is the upper layer of the atmosphere that is ionized by solar radiation, is affected by the magneti
c field. The energy from the magnetic field is transferred to the ionosphere, where it drives the motion of the charged particles and affects the propagation of radio waves.
Thirdly, the interactions between the atmosphere and the magnetic field influence the dynamics of Earth's climate. The magnetic field affects the distribution of charged particles in the atmosphere, which in tur
n affects the formation of clouds and precipitation. The magnetic field also affects the distribution of heat in the atmosphere, which can influence the patterns of atmospheric circulation and the distribution o
f temperatures around the planet.
Finally, the interactions between the atmosphere and the magnetic field play a role in the long-term evolution of the planet's environment. The magnetic field protects the atmosphere from the erosive effects of
the solar wind, which would otherwise strip away the atmosphere over time. The magnetic field also affects the distribution of heat in the atmosphere, which can influence the patterns of atmospheric circulation
and the distribution of temperatures around the planet. Over time, these interactions can shape the evolution of the planet's climate and environment.
You: Please explain the bow shock wave, Van Allen radiation belts in detail
The bow shock wave is a phenomenon that occurs when the solar wind, a stream of charged particles emitted by the sun, interacts with Earth's magnetic field. The solar wind particles are moving at high speeds, an
d when they encounter the Earth's magnetic field, they slow down and dissipate their energy. This creates a shock wave that propagates downstream from the Earth. The bow shock wave is located about 15 Earth radi
i (approximately 93,000 miles) upstream from Earth, and it marks the boundary between the solar wind and Earth's magnetosphere.
The Van Allen radiation belts are zones of high-energy charged particles, primarily protons and electrons, that are trapped by Earth's magnetic field. The belts are divided into two main regions: the inner belt,
which extends from about 1,000 to 6,000 kilometers above Earth's surface, and the outer belt, which extends from about 13,000 to 65,000 kilometers above the surface. The particles in the belts are trapped by Ea
rth's magnetic field, and they can remain in the belts for long periods of time.
The particles in the Van Allen belts are generated by a variety of processes, including the impact of solar wind particles on the Earth's atmosphere and the decay of radioactive elements in the planet's crust. T
he belts are important for understanding the behavior of charged particles in Earth's magnetosphere and for studying the effects of space weather on human activities in space. They can also pose a hazard to spac
ecraft and satellites, as the high-energy particles in the belts can damage sensitive electronics and cause other problems.
You: Does the Van Allen belt present any danger to Geo stationary satellites? Where are these belts? Are they near any of the orbits?
Yes, the Van Allen radiation belts can present a danger to geostationary satellites and other spacecraft. The high-energy charged particles in the belts can damage sensitive electronics and cause other problems,
including radiation damage and single-event upsets. Geostationary satellites are located at an altitude of approximately 35,786 kilometers above Earth's surface, which is just outside the inner belt but still w
ithin the outer belt.
The Van Allen radiation belts are located in Earth's magnetosphere, which is the region of space around the planet where the magnetic field is dominant. The inner belt is located between about 1,000 and 6,000 ki
lometers above the surface, while the outer belt is located between about 13,000 and 65,000 kilometers above the surface. The belts are not located in any specific orbit, but they are present throughout the magn
etosphere, which covers a large portion of the space around the planet.
To mitigate the effects of the Van Allen belts on spacecraft, engineers use a variety of techniques, including shielding and designing electronics to be resistant to radiation. Additionally, some spacecraft are
designed to operate in orbits that avoid the Van Allen belts, while others are designed to operate within the belts and withstand the effects of the high-energy particles.
You: So when we send spacecraft to the moon, say the ones carrying humans, how do we make sure that the solar wind charged particles will not affect the mission? Are there very specific remedies that we can take
?
When sending spacecraft to the moon, there are several steps that can be taken to protect the spacecraft and its occupants from the effects of solar wind charged particles. One approach is to design the spacecra
ft with a strong magnetic field, which can help deflect the charged particles away from the spacecraft. Another approach is to use radiation shielding, which can help protect the electronics and any human occupa
nts from the effects of radiation.
In addition to these measures, space agencies can also use data from satellites and other spacecraft to monitor the level of solar wind activity and predict when there may be an increased risk of charged particl
e events. This information can be used to adjust the timing of missions and other activities to minimize exposure to high-energy particles.
It's also important to note that the moon is outside the magnetosphere and therefore not directly affected by the Van Allen belts. However, the moon does receive a significant amount of radiation from the sun an
d other sources, so measures to protect the spacecraft and its occupants from radiation exposure are still necessary.
Overall, protecting spacecraft and humans from the effects of solar wind charged particles requires a combination of engineering and operational measures, including strong magnetic fields, radiation shielding, a
nd careful mission planning.
You: Does spacecraft actually create strong magnetic fields? Which Apollo spacecrafts did this? Or is this hypothetical?
Yes, spacecraft can create strong magnetic fields, although this is not typically a primary design consideration for most spacecraft. Some spacecraft, such as those designed for plasma physics research, may incl
ude a magnetic field generator to create controlled conditions for experiments. However, for most spacecraft, the focus is on using existing magnetic fields, such as those generated by the Earth's magnetic field
, to protect the spacecraft and its occupants.
The Apollo spacecraft did not create strong magnetic fields, as their primary focus was on propulsion, navigation, and life support systems for the astronauts. However, some of the Apollo missions did include sc
ientific experiments to study the effects of solar wind and other charged particles on the spacecraft and its occupants.
The use of magnetic fields to protect spacecraft and humans from the effects of radiation is an ongoing area of research and development, and there are a number of proposals and concepts for how this might be ac
hieved. For example, some researchers have proposed using superconducting coils to create a magnetic field around the spacecraft, which could help deflect charged particles and other forms of radiation. However,
these proposals are still in the early stages of development and are not yet ready for implementation on spacecraft.
```
# [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_migtissera__Synthia-70B-v1.1)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 62.84 |
| ARC (25-shot) | 70.05 |
| HellaSwag (10-shot) | 87.12 |
| MMLU (5-shot) | 70.34 |
| TruthfulQA (0-shot) | 57.84 |
| Winogrande (5-shot) | 83.66 |
| GSM8K (5-shot) | 31.84 |
| DROP (3-shot) | 39.02 |
|
Sao10K/Stheno-L2-13B | Sao10K | "2023-11-18T04:34:10Z" | 1,639 | 10 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-31T15:31:28Z" | ---
license: llama2
language:
- en
---
<img src="https://w.forfun.com/fetch/cb/cba2205390e517bea1ea60ca0b491af4.jpeg" style="width: 70%; min-width: 300px; display: block; margin: auto;">
An experimental merging of Several Models using two various methods, [Ties-Merge](https://github.com/cg123/ties-merge) and [BlockMerge_Gradient](https://github.com/Gryphe/BlockMerge_Gradient)
I plan for this to be the base of my Model with my own [Stheno: ERP-Based LORA] merged in, some time in the future.
Stheno:
<br>Gradient Merge of Stheno-P1 & Stheno-P2.
SISTER MODEL HERE: [Stheno-Inverted-L2-13B](https://huggingface.co/Sao10K/Stheno-Inverted-L2-13B)
Quants courtesy of TheBloke!
<br>[GPTQ](https://huggingface.co/TheBloke/Stheno-L2-13B-GPTQ)
<br>[GGUF](https://huggingface.co/TheBloke/Stheno-L2-13B-GGUF)
<br>[GGML](https://huggingface.co/TheBloke/Stheno-L2-13B-GGML)
Test Checklist:
<br>Censorship - Fairly Uncensored
<br>Writing - Good Prose, Fairly Descriptive
<br>NSFW - Yes
<br>IQ Level - Pretty Smart
<br>Formatting - Proper Formatting with Examples
Stheno-P1 [Ties-Merge]
<br>-----[elinas/chronos-13b-v2](https://huggingface.co/elinas/chronos-13b-v2)
<br>-----[jondurbin/airoboros-l2-13b-2.1](https://huggingface.co/jondurbin/airoboros-l2-13b-2.1)
<br>-----[NousResearch/Nous-Hermes-Llama2-13b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b)+[nRuaif/Kimiko-v2 **LORA**](https://huggingface.co/nRuaif/Kimiko-v2-13B)
Stheno-P2 [Ties-Merge]
<br>-----[CalderaAI/13B-Legerdemain-L2](https://huggingface.co/CalderaAI/13B-Legerdemain-L2)+[lemonilia/limarp-llama2-v2 **LORA**](https://huggingface.co/lemonilia/limarp-llama2-v2)
<br>-----[ehartford/WizardLM-1.0-Uncensored-Llama2-13b](https://huggingface.co/ehartford/WizardLM-1.0-Uncensored-Llama2-13b)
<br>-----[Henk717/spring-dragon](https://huggingface.co/Henk717/spring-dragon)
Most formats could work, but my tests have all been done in Alpaca format and it works well.
```
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
```
Below is the Illustration for the Final Merge:
Once Again, thanks to [Chargoddard](https://huggingface.co/chargoddard) for his amazing and simple [ties-merge](https://github.com/cg123/ties-merge) script, and [Gryphe](https://huggingface.co/Gryphe) for their great [BlockMerge_Gradient](https://github.com/Gryphe/BlockMerge_Gradient) script.
Thanks to the original model creators too!
support me [here](https://ko-fi.com/sao10k) :)
```
Art by wada_kazu / わだかず (pixiv page private?)
```
# [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_Sao10K__Stheno-L2-13B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 53.48 |
| ARC (25-shot) | 61.01 |
| HellaSwag (10-shot) | 83.95 |
| MMLU (5-shot) | 56.33 |
| TruthfulQA (0-shot) | 50.18 |
| Winogrande (5-shot) | 75.14 |
| GSM8K (5-shot) | 11.98 |
| DROP (3-shot) | 35.76 |
|
lgaalves/gpt2_guanaco-dolly-platypus | lgaalves | "2023-11-17T22:44:00Z" | 1,639 | 1 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt2",
"text-generation",
"en",
"dataset:garage-bAInd/Open-Platypus",
"dataset:databricks/databricks-dolly-15k",
"dataset:timdettmers/openassistant-guanaco",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-31T22:55:40Z" | ---
license: mit
datasets:
- garage-bAInd/Open-Platypus
- databricks/databricks-dolly-15k
- timdettmers/openassistant-guanaco
language:
- en
pipeline_tag: text-generation
---
# gpt2_guanaco-dolly-platypus
**gpt2_guanaco-dolly-platypus** is an instruction fine-tuned model based on the GPT-2 transformer architecture.
### Benchmark Metrics
| Metric | gpt2_guanaco-dolly-platypus | GPT-2 (base) |
|-----------------------|-------|-------|
| Avg. | **30.25** | 29.9 |
| ARC (25-shot) | **23.55** | 21.84 |
| HellaSwag (10-shot) | 31.03 | **31.6** |
| MMLU (5-shot) | **26.4** | 25.86 |
| TruthfulQA (0-shot) | 40.02 | **40.67** |
We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.
### Model Details
* **Trained by**: Luiz G A Alves
* **Model type:** **gpt2_guanaco-dolly-platypus** is an auto-regressive language model based on the GPT-2 transformer architecture.
* **Language(s)**: English
### How to use:
```python
# Use a pipeline as a high-level helper
>>> from transformers import pipeline
>>> pipe = pipeline("text-generation", model="lgaalves/gpt2_guanaco-dolly-platypus")
>>> question = "What is a large language model?"
>>> answer = pipe(question)
>>> print(answer[0]['generated_text'])
```
or, you can load the model direclty using:
```python
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("lgaalves/gpt2_open-platypus")
model = AutoModelForCausalLM.from_pretrained("lgaalves/gpt2_open-platypus")
```
### Training Dataset
`lgaalves/gpt2_guanaco-dolly-platypus` was trained using 3 datasets:
- [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco)
- [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k)
- [garage-bAInd/Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus)
### Training Procedure
`lgaalves/gpt2_guanaco-dolly-platypus` was instruction fine-tuned using LoRA on 1 T4 GPU on Google Colab. It took about 1 hour to train it.
# Intended uses, limitations & biases
You can use the raw model for text generation or fine-tune it to a downstream task. The model was not extensively tested and may produce false information. It contains a lot of unfiltered content from the internet, which is far from neutral.
# [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_lgaalves__gpt2_guanaco-dolly-platypus)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 25.15 |
| ARC (25-shot) | 23.55 |
| HellaSwag (10-shot) | 31.03 |
| MMLU (5-shot) | 26.4 |
| TruthfulQA (0-shot) | 40.02 |
| Winogrande (5-shot) | 50.12 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 4.96 |
|
L-R/LLmRa-1.3B | L-R | "2023-11-18T14:09:56Z" | 1,639 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"xglm",
"text-generation",
"AI",
"ConversationalAI",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] | text-generation | "2023-09-05T14:12:58Z" | ---
language:
- en
pipeline_tag: conversational
inference: false
tags:
- AI
- ConversationalAI
license: apache-2.0
---
<h1 style="text-align: center">LLmRa-1.3B</h1>
<h2 style="text-align: center">A conversational fairseq-dense fine-tune.</h2>
**LLmRa 1.3B**, as a proof-of-concept fine-tune of [KoboldAI/fairseq-dense-1.3B](https://huggingface.co/KoboldAI/fairseq-dense-1.3B) optimized for dialogue.
**Disclaimer:** NSFW data was included in the fine-tuning of this model. Although SFW inputs will usually result in SFW outputs, you are advised to **chat at your own risk. This model is not suitable for use by minors.**
**Warning:** This model is **NOT** suitable for use by minors. **It will output X-rated content under certain circumstances.**
---
## Usage Format
To effectively utilize the model, follow this structured format for engaging text-based conversations:
**1. Initialization**
```
<|INST|><[system]>: (YOUR AI PERSONA)
<st_r>
```
- **Persona**: You can define a specific persona or context for the AI, but it's optional. It can be a character, a role, or just a style of interaction.
**2. AI Introduction**
```
<|INST|> (User's input message here.) <|/INST|>
```
- Users can start the conversation by entering their message within `<|INST|>` and closing with `<|/INST|>`.
**3. AI Response**
The model will respond based on the input provided by the user.
---
### Example Usage:
Here's an example of how to start a conversation with the AI:
```
<|INST|><[system]>: I'm here to provide information and assistance on a wide range of topics.
<st_r>
Hello! Welcome to our AI-powered assistant. How can I assist you today?
User: Tell me about the history of artificial intelligence. <|/INST|>
```
Continue the conversation as needed. This structured format helps maintain a smooth and engaging interaction with the AI.
You are not required to include `User`, you can change it to your prefered name or leave it blank You may also add the AI name, example:
```
<|INST|> YourNameHere: Hello. <|/INST|> CharacterName:
```
Or have both blank.
```
<|INST|> Hello. <|/INST|>
```
## Loading The Model
To use the model and interact with it, use the Python code below:
```Python
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "L-R/LLmRa-1.3B"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
def ask_question(model_data, input_data, model, tokenizer):
model_data_dict = {
"X1": {
"name": "SmartAI",
"greeting": "Hello! How can I assist you today?",
"description": "I'm here to provide information and assistance on a wide range of topics"
},
"X2": {
"name": "MysteryBot",
"greeting": "Greetings, curious traveler! What secrets do you seek?",
"description": "I am the enigmatic MysteryBot, here to uncover and reveal the mysteries of the world."
}
}
if model_data in model_data_dict:
data = model_data_dict[model_data]
name = data["name"]
greeting = data["greeting"]
model_data = data["description"]
else:
return "Invalid model_data option"
question = f"<|INST|><[system]>: {model_data}\n<st_r>\n{greeting}\nPete: {input_data} <|/INST|> {name}:"
print("\n[----------]\n")
inputs = tokenizer.encode(question, return_tensors="pt")
outputs = model.generate(
input_ids=inputs,
max_length=250 + len(inputs[0]),
no_repeat_ngram_size=4,
pad_token_id=tokenizer.eos_token_id,
do_sample=True,
top_k=40,
top_p=.55,
num_return_sequences=1,
temperature=.5,
repetition_penalty=1.25,
use_cache=True
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)[len(question):]
print(f"\n\n[Generated Text]:{response}")
print("\n[----------]\n")
return response
while True:
print("\nQuestion For The AI: ")
input_data = input(">> ")
model_data = input("Personality Of The (X1, X2): ")
ask_question(model_data, input_data, model, tokenizer)
```
## Known issues
The AI exhibits inconsistent responses, occasionally providing nonsensical or unusual answers. The AI performance seems to be worse than in the 355M model one, meaning the training data did not "sit right" onto the model, the next version will be on a bigger dataset, with a new architecture.
# [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_L-R__LLmRa-1.3B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 31.1 |
| ARC (25-shot) | 32.68 |
| HellaSwag (10-shot) | 58.77 |
| MMLU (5-shot) | 23.23 |
| TruthfulQA (0-shot) | 36.21 |
| Winogrande (5-shot) | 59.04 |
| GSM8K (5-shot) | 0.08 |
| DROP (3-shot) | 7.72 |
|
Sao10K/Stheno-1.1-L2-13B | Sao10K | "2023-11-18T04:34:26Z" | 1,639 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-06T13:45:27Z" | ---
license: llama2
language:
- en
---
***ONLY UPLOADED FROM RUNPOD JUST TO TEST ON OWN SYSTEM. UNTESTED SO FAR. V2 SOON***
***CURRENT CHANGES: INCREASED BASE MODEL WEIGHTS AND DENSITIES BEFORE MERGE + DIFFERENT GRADIENTS APPLIED***
An experimental merging of Several Models using two various methods, [Ties-Merge](https://github.com/cg123/ties-merge) and [BlockMerge_Gradient](https://github.com/Gryphe/BlockMerge_Gradient)
Stheno:
<br>Gradient Merge of Stheno-P1 & Stheno-P2.
Test Checklist:
<br>Censorship - ____
<br>Writing - ____
<br>NSFW - ___
<br>IQ Level - ___
<br>Formatting - ____
Most formats could work, use Alpaca format and it works well.
```
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
```
Gradient Merge Pictures Unavailable, Several Different Tensor Ratios applied.
# [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_Sao10K__Stheno-1.1-L2-13B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 54.43 |
| ARC (25-shot) | 60.75 |
| HellaSwag (10-shot) | 83.64 |
| MMLU (5-shot) | 56.39 |
| TruthfulQA (0-shot) | 50.3 |
| Winogrande (5-shot) | 75.22 |
| GSM8K (5-shot) | 7.96 |
| DROP (3-shot) | 46.78 |
|
wei123602/llama2-13b-fintune2-4E | wei123602 | "2023-09-09T06:01:34Z" | 1,639 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-09T05:30:54Z" | Entry not found |
dhmeltzer/Llama-2-7b-hf-eli5-cleaned-1024_qlora_merged | dhmeltzer | "2023-11-17T21:20:44Z" | 1,639 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-11T03:13:58Z" |
# [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_dhmeltzer__Llama-2-7b-hf-eli5-cleaned-1024_qlora_merged)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 44.13 |
| ARC (25-shot) | 53.67 |
| HellaSwag (10-shot) | 78.21 |
| MMLU (5-shot) | 45.9 |
| TruthfulQA (0-shot) | 46.13 |
| Winogrande (5-shot) | 73.8 |
| GSM8K (5-shot) | 4.7 |
| DROP (3-shot) | 6.53 |
|
cmarkea/bloomz-7b1-mt-sft-chat | cmarkea | "2023-09-23T12:27:58Z" | 1,639 | 16 | transformers | [
"transformers",
"pytorch",
"safetensors",
"bloom",
"text-generation",
"fr",
"en",
"dataset:ehartford/wizard_vicuna_70k_unfiltered",
"dataset:shahules786/orca-chat",
"dataset:timdettmers/openassistant-guanaco",
"dataset:laion/OIG",
"arxiv:2012.15613",
"arxiv:2001.09977",
"license:bigscience-bloom-rail-1.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-11T16:59:44Z" | ---
license: bigscience-bloom-rail-1.0
datasets:
- ehartford/wizard_vicuna_70k_unfiltered
- shahules786/orca-chat
- timdettmers/openassistant-guanaco
- laion/OIG
language:
- fr
- en
library_name: transformers
pipeline_tag: text-generation
widget:
- text: </s>Bonjour, qui es-tu ?<s>
- text: </s>Hello, who are you?<s>
---
bloomz-7b1-mt-sft-chat
--------------------
We introduce the bloomz-7b1-mt-sft-chat model, which is a fine-tuning of a Large Language Model (LLM) [bigscience/bloomz-7b1-mt](https://huggingface.co/bigscience/bloomz-7b1-mt). This model is notable for being pre-trained for a chatbot context and undergoing a transposition from float16 to bfloat16. Therefore, this model serves as a solid starting point for fine-tuning towards other more specific tasks.
The model was trained equally on both French and English data, ensuring maximum efficiency for these two languages (and their interactions). Due to the transition from float16 to bfloat16, we do not guarantee the preservation of the original model's multilingual capabilities. However, fine-tuning can restore reasonable performance on other languages.
The objective is to pre-train all three models (Bloomz-{560m, 3b, 7b1-mt}-sft-chat) to ensure high-performing, energy-efficient, and fast "foundation" models for inference on "realistic" infrastructures suitable for a business with standard industrial capabilities.
Bloomz, through its license, enables free and flexible industrial use. Its tokenizer has been designed with true multi-lingual context in mind, with a significantly lower token generation per word compared to other LLM models. This capability not only leads to improved performance but also enhanced efficiency during inference by making fewer model calls when generating text with shorter contexts. Here is a table illustrating our points using French as an example, where we tokenized Marcel Proust's longest sentence (823 words):
```
Sans honneur que précaire, sans liberté que provisoire, [...], et de façon qu’à eux-mêmes il ne leur paraisse pas un vice.
```
| model | GPT 3.5 | Boris | Flan-T5 | LLaMA | Dolly | MPT | Falcon | Bloomz |
|:--------------:|:-------:|:-----:|:-------:|:-----:|:-----:|:---:|:------:|:------:|
| tokens per word | 2.3 | 2.3 | 2 | 1.9 | 1.9 | 1.9 | 1.8 | 1.4 |
For comparison, with a specialized French tokenizer like [CamemBERT](https://huggingface.co/camembert/camembert-base) or [DistilCamemBERT](cmarkea/distilcamembert-base), we have 1.5 tokens per word. In addition to its positive impact on inference time and resource consumption, there has already been [shown that there is a direct relationship](https://arxiv.org/abs/2012.15613) between the number of tokens per word required for modeling and the predictive performance of the model.
Dataset
-------
After analyzing a substantial set of modelings, we have observed that the most effective pre-training for zero-shot use cases is pre-training for chatbot contexts. This study was conducted internally, focusing specifically on the French context. As a result, we trained the model on a dataset comprising 0.9 billion tokens. This dataset consists of interactions between an individual and a third party. To balance the French and English data, we utilized the Google Translate API.
Training
--------
Here is the table summarizing the architecture used for training, along with the training time and average inference speed per token on the target architecture in tokens per second:
| model | Architecture | Training time (h) | Inference speed (tokens per second) |
|:----------------------:|:-------------:|:-----------------:|:-----------------------------------:|
| [bloomz-560m-sft-chat](https://huggingface.co/cmarkea/bloomz-560m-sft-chat) | 1 x A100 40GB | 41 | 29 |
| [bloomz-3b-sft-chat](https://huggingface.co/cmarkea/bloomz-3b-sft-chat) | 1 x A100 40GB | 140 | 13 |
| [bloomz-7b1-mt-sft-chat](https://huggingface.co/cmarkea/bloomz-7b1-mt-sft-chat) | 4 x A100 40GB | 268 | 8 |
| Hyperparameter | Value |
|:---------------------:|:----------:|
| label smoothing | 0.05 |
| optimizer | AdamW |
| betas | 0.9, 0.999 |
| learning rate | 5e-6 |
| anneal strategy | cos |
| div factor | 100 |
| final div factor | 0.1 |
| batch size | 2 |
| gradient accumulation | 200 |
| max length | 2048 |
Experimentations
----------------
Since the model is trained only on English and French corpora, the performance of the model cannot be guaranteed in other languages. This degradation in performance in other languages is also due to the change in the model's data type from float16 to bfloat16. The conversation example below illustrates this point:
| French | English | Spanish |
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| **human:** C'est quoi la première guerre mondiale ?<br>**bot:** La Première Guerre mondiale a eu lieu entre 1914 et 1918. C'était une guerre entre les puissances européennes, principalement la France, l'Allemagne et la Grande-Bretagne.<br>**human:** Y a-t-il eu également d’autres pays impliqués ?<br>**bot:** Oui, il y avait également des pays comme l'Italie, les États-Unis, la Russie et la Turquie.<br>**human:** Comment cela s'est-il fini et quels ont été ses impacts ?<br>**bot:** La Première Guerre mondiale s'est terminée par un accord de paix appelé le Traité de Versailles. Il a mis fin à la guerre et a établi un nouvel ordre mondial.<br>**human:** Combien y a-t-il eu de mort ?<br>**bot:** Il y a eu environ 10 millions de morts, principalement des soldats.<br>**human:** Et combien de mort civile ?<br>**bot:** Il y a eu environ 5 millions de morts civils, principalement des civils.<br>**human:** Tu es certain de ce chiffre, ça me parait peu...<br>**bot:** Je suis sûr de ce chiffre. | **human:** What is the first world war?<br>**bot:** The first world war was a war that took place between 1914 and 1918.<br>**human:** Which countries participated in this war?<br>**bot:** he countries that participated in the first world war were the United Kingdom, France, Belgium, the Netherlands, Italy, Austria-Hungary, Serbia, Montenegro, Bulgaria, Greece, Romania, Albania, and the Ottoman Empire.<br>**human:** How did it end and what were its impacts?<br>**bot:** The first world war ended with the Treaty of Versailles, which was signed on 28 June 1919. The Treaty of Versailles was a peace treaty that ended the war and established the international system that we know today.<br>**human:** How many deaths?<br>**bot:** The first world war resulted in approximately 50 million deaths, with approximately 30 million of those deaths occurring in the European Theater.<br>**human:** That seems a bit much to me, are you sure of these numbers?<br>**bot:** Yes, I am. | **human:** ¿Qué es la Primera Guerra Mundial?<br>**bot:** La Primera Guerra Mundial fue un conflicto bélico que ocurrió entre 1914 y 1918.<br>**human:** ¿En qué países participamos?<br>**bot:** La Primera Guerra Mundial involucró a muchos países, incluidos Alemania, Austria-Hungría, Bélgica, Bulgaria, Checoslovaquia, Francia, Gran Bretaña, Italia, Japón, Luxemburgo, Noruega, los Países Bajos, Portugal, Serbia, España, Turquía y Estados Unidos.<br>**human:** ¿Cuántas muertes?<br>**bot:** La Primera Guerra Mundial dejó más de 10 millones de muertes.<br>**human:** ¿Y cuántas muertes de civiles?<br>**bot:** La Primera Guerra Mundial dejó más de 5 millones de muertes de civiles.<br>**human:** ¿Estás seguro? Eso no me parece mucho.<br>**bot:** No, no estoy seguro. |
Evaluating the performance of generative models can be challenging, and quantitative measures may not always provide the most relevant insights for this type of approach. In this regard, we conducted a qualitative performance study. It involves assessing the relevance of model responses to a pool of French questions using blind evaluation. The metric used for evaluation is the average of two criteria: response accuracy and completeness, similar to what the [SSA metric](https://arxiv.org/abs/2001.09977) aims to capture. Please note that this measure lacks rigorous scientific validity due to the limited number of questions in the test dataset and the fact that it involves only a few individuals with similar socio-demographic characteristics. The prompts take the same format for all models:
```
[Instruction]
Question : [Question]
Réponse :
```
As a result, the prompts do not exploit the structures of chatbot models to ensure fairness, and the evaluation quantifies performance in a purely instruction-based approach. The figure below illustrates the results. The higher a model is positioned in the top-left corner with a small circle radius, the better the model; conversely, if a model is towards the bottom-right with a large circle, it performs less favorably.
We observe that across all models, the performance gain is logarithmic in relation to the increase in model parameters. However, for models that undergo multiple pre-trainings (vanilla, instruction, and chat), models pre-trained on instruction and chat perform significantly better in zero-shot contexts, with a notable improvement for chat-based approaches. The models we have trained demonstrate promising efficiency in this test compared to the number of parameters, indicating cost-effectiveness in a production context.
How to use bloomz-7b1-mt-sft-chat
-------------------------------
There are no specific instructions for using these models in a normal causal inference context. However, to leverage the chatbot capability of the model, an individual's prompt should be preceded by the EOS token (</s>), and the generated part should be preceded by the BOS token (<s>). The structure takes the following form:
```
</s>[human prompt 1]<s>[bot answer 1]</s>[human prompt 2]<s>
```
For example, to load the model using the HuggingFace pipeline interface:
```python
from transformers import pipeline
model = pipeline("text-generation", "cmarkea/bloomz-7b1-mt-sft-chat")
result = model("</s>C'est quoi le deep learning ?<s>", max_new_tokens=512)
result
[{'generated_text': "</s>C'est quoi le deep learning ?<s>Le deep learning
est un type de machine learning qui utilise des réseaux de neurones
artificiels pour apprendre à partir de données. Il est utilisé dans de
nombreux domaines, notamment la reconnaissance d'images, la
reconnaissance vocale, la traduction automatique et la reconnaissance
de l'écriture."}]
```
Citation
--------
```bibtex
@online{DeBloomzChat,
AUTHOR = {Cyrile Delestre},
URL = {https://huggingface.co/cmarkea/bloomz-7b1-mt-sft-chat},
YEAR = {2023},
KEYWORDS = {NLP ; Transformers ; LLM ; Bloomz},
}
``` |
vihangd/smartyplats-3b-v2 | vihangd | "2023-11-30T05:55:40Z" | 1,639 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-14T07:07:47Z" | ---
license: apache-2.0
---
# [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_vihangd__smartyplats-3b-v2)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 35.3 |
| ARC (25-shot) | 41.04 |
| HellaSwag (10-shot) | 71.19 |
| MMLU (5-shot) | 24.32 |
| TruthfulQA (0-shot) | 36.66 |
| Winogrande (5-shot) | 66.93 |
| GSM8K (5-shot) | 1.59 |
| DROP (3-shot) | 5.39 |
|
ajibawa-2023/Uncensored-Frank-7B | ajibawa-2023 | "2023-11-18T05:56:32Z" | 1,639 | 5 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:ehartford/wizard_vicuna_70k_unfiltered",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-14T16:17:03Z" | ---
license: cc-by-nc-nd-4.0
language:
- en
datasets:
- ehartford/wizard_vicuna_70k_unfiltered
---
**Frank: An Uncensored Model**
The character of Frank Costello in "The Departed" is known for his cunning, boldness, and willingness to talk about anything, regardless of societal norms or restrictions.
Frank, An Uncensored model, draws inspiration from these qualities to offer a platform where users can discuss a wide array of topics without the fear of censorship or restrictions.
Frank aims to push boundaries and encourage candid conversations. With Frank you can have unfiltered discussions on a multitude of topics, from politics and controversial issues to personal experiences and sensitive subjects.
It is trained on around 150000 set of conversations. Each set having 10~15 conversations. Base data was obtained from [Eric Hartford](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered).
This data was further refined and fine tuned. Besides this further synthetic conversation (more than 80k) was generated and refined. We will not release this data.
**Warning**
An uncensored model has no or little guardrails. You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous objects.
Publishing anything this model generates is the same as publishing it yourself. We are not responsible for what you generate using this model.
**Training:**
Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 22 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.
**GPTQ GGML & AWQ**
GPTQ: [Link](https://huggingface.co/TheBloke/Uncensored-Frank-7B-GPTQ)
GGUF: [Link](https://huggingface.co/TheBloke/Uncensored-Frank-7B-GGUF)
AWQ: [Link](https://huggingface.co/TheBloke/Uncensored-Frank-7B-AWQ)
Special Thanks to [TheBloke](https://huggingface.co/TheBloke) for making these models available.
**Example Prompt:**
```
This is a conversation with your Uncensored AI assistant Frank. Frank can discuss with you at length about various topics such as ---, ---, ---, . You can ask it anything you want and it will do its best to give you accurate and relevant information.
Context
You are a Uncensored AI assistant.
USER: <prompt>
ASSISTANT:
```
# [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_ajibawa-2023__Uncensored-Frank-7B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 43.6 |
| ARC (25-shot) | 54.27 |
| HellaSwag (10-shot) | 76.52 |
| MMLU (5-shot) | 37.5 |
| TruthfulQA (0-shot) | 43.86 |
| Winogrande (5-shot) | 70.24 |
| GSM8K (5-shot) | 5.0 |
| DROP (3-shot) | 17.8 |
|
dhmeltzer/Llama-2-13b-hf-ds_eli5_1024_r_64_alpha_16_merged | dhmeltzer | "2023-11-17T21:20:30Z" | 1,639 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-14T17:30:10Z" |
# [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_dhmeltzer__Llama-2-13b-hf-ds_eli5_1024_r_64_alpha_16_merged)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 47.8 |
| ARC (25-shot) | 59.13 |
| HellaSwag (10-shot) | 82.13 |
| MMLU (5-shot) | 54.98 |
| TruthfulQA (0-shot) | 44.23 |
| Winogrande (5-shot) | 76.4 |
| GSM8K (5-shot) | 8.11 |
| DROP (3-shot) | 9.6 |
|
CHIH-HUNG/llama-2-13b-FINETUNE3_3.3w-r16-gate_up_down | CHIH-HUNG | "2023-09-20T16:27:08Z" | 1,639 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-20T16:05:16Z" | Entry not found |
CHIH-HUNG/llama-2-13b-FINETUNE4_3.8w-r4-q_k_v_o | CHIH-HUNG | "2023-10-04T13:31:44Z" | 1,639 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:huangyt/FINETUNE4",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-20T22:23:57Z" | ---
license: llama2
datasets:
- huangyt/FINETUNE4
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
在llama-2-13b上使用huangyt/FINETUNE4資料集進行訓練，總資料筆數約3.8w
# Fine-Tuning Information
- **GPU:** RTX4090 (single core / 24564MiB)
- **model:** meta-llama/Llama-2-13b-hf
- **dataset:** huangyt/FINETUNE3 (共約3.8w筆訓練集)
- **peft_type:** LoRA
- **lora_rank:** 16
- **lora_target:** q_proj, k_proj, v_proj, o_proj
- **per_device_train_batch_size:** 8
- **gradient_accumulation_steps:** 8
- **learning_rate :** 4e-4
- **epoch:** 1
- **precision:** bf16
- **quantization:** load_in_4bit
# Fine-Tuning Detail
- **train_loss:** 0.579
- **train_runtime:** 4:6:11 (use deepspeed)
# Evaluation
- 與Llama-2-13b比較4種Benchmark，包含**ARC**、**HellaSwag**、**MMLU**、**TruthfulQA**
- 評估結果使用**本地**所測的分數，並使用load_in_8bit
| Model |Average| ARC |HellaSwag| MMLU | TruthfulQA |
|-----------------------------------------|-------|-------|---------|-------|------------|
| FINETUNE4_3.8w-r4-q_k_v_o | 56.67 | 52.13 | 79.38 | 54.54 | 40.64 |
| FINETUNE4_3.8w-r8-q_k_v_o | 56.84 | 52.30 | 79.58 | 54.50 | 40.98 |
| FINETUNE4_3.8w-r16-q_k_v_o | 57.28 | 53.92 | 79.92 | 55.61 | 39.65 |
| FINETUNE4_3.8w-r4-gate_up_down | 55.93 | 51.71 | 79.13 | 53.24 | 39.63 |
| FINETUNE4_3.8w-r8-gate_up_down | 55.93 | 51.37 | 79.29 | 53.62 | 39.45 |
| FINETUNE4_3.8w-r16-gate_up_down | 56.35 | 52.56 | 79.28 | 55.27 | 38.31 |
| FINETUNE4_3.8w-r4-q_k_v_o_gate_up_down | 56.42 | 53.92 | 79.09 | 53.93 | 38.74 |
| FINETUNE4_3.8w-r8-q_k_v_o_gate_up_down | 56.11 | 51.02 | 79.24 | 53.11 | 41.08 |
| FINETUNE4_3.8w-r16-q_k_v_o_gate_up_down | 56.83 | 53.67 | 79.49 | 54.79 | 39.36 |
------------------------------------------------------------------------------------------
- 評估結果來自**HuggingFaceH4/open_llm_leaderboard**
| Model |Average| ARC |HellaSwag| MMLU | TruthfulQA |
|-----------------------------------------|-------|-------|---------|-------|------------|
| FINETUNE4_3.8w-r4-q_k_v_o | 57.98 | 54.78 | 81.4 | 54.73 | 41.02 |
| FINETUNE4_3.8w-r8-q_k_v_o | 58.96 | 57.68 | 81.91 | 54.95 | 41.31 |
| FINETUNE4_3.8w-r16-q_k_v_o | 58.46 | 56.23 | 81.98 | 55.87 | 39.76 |
| FINETUNE4_3.8w-r4-gate_up_down | 57.94 | 55.8 | 81.74 | 55.09 | 39.12 |
| FINETUNE4_3.8w-r8-gate_up_down | 57.85 | 54.35 | 82.13 | 55.33 | 39.6 |
| FINETUNE4_3.8w-r16-gate_up_down | 57.93 | 55.03 | 81.97 | 56.64 | 38.07 |
| FINETUNE4_3.8w-r4-q_k_v_o_gate_up_down | 58.04 | 56.31 | 81.43 | 55.3 | 39.11 |
| FINETUNE4_3.8w-r8-q_k_v_o_gate_up_down | 58.16 | 55.97 | 81.53 | 54.42 | 40.72 |
| FINETUNE4_3.8w-r16-q_k_v_o_gate_up_down | 58.61 | 57.25 | 81.49 | 55.9 | 39.79 |
# How to convert dataset to json
- 在**load_dataset**中輸入資料集名稱，並且在**take**中輸入要取前幾筆資料
- 觀察該資料集的欄位名稱，填入**example**欄位中(例如system_prompt、question、response)
- 最後指定json檔儲存位置 (**json_filename**)
```py
import json
from datasets import load_dataset
# 讀取數據集，take可以取得該數據集前n筆資料
dataset = load_dataset("huangyt/FINETUNE4", split="train", streaming=True)
# 提取所需欄位並建立新的字典列表
extracted_data = []
for example in dataset:
extracted_example = {
"instruction": example["instruction"],
"input": example["input"],
"output": example["output"]
}
extracted_data.append(extracted_example)
# 指定 JSON 文件名稱
json_filename = "FINETUNE4.json"
# 寫入 JSON 文件
with open(json_filename, "w") as json_file:
json.dump(extracted_data, json_file, indent=4)
print(f"數據已提取並保存為 {json_filename}")
``` |
Undi95/Amethyst-13B | Undi95 | "2023-11-17T21:08:56Z" | 1,639 | 10 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"not-for-all-audiences",
"nsfw",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-24T16:44:06Z" | ---
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- nsfw
---
An attempt using [BlockMerge_Gradient](https://github.com/Gryphe/BlockMerge_Gradient) to get better result.
In addition, [LimaRP v3](https://huggingface.co/lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT) was used, is it recommanded to read the documentation.
<!-- description start -->
## Description
This repo contains fp16 files of Amethyst-13B.
<!-- description end -->
<!-- description start -->
## Models and loras used
- Xwin-LM/Xwin-LM-13B-V0.1
- The-Face-Of-Goonery/Huginn-13b-FP16
- zattio770/120-Days-of-LORA-v2-13B
- lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
<!-- description 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:
```
## LimaRP v3 usage and suggested settings
You can follow these instruction format settings in SillyTavern. Replace tiny with your desired response length:
Special thanks to Sushi.
If you want to support me, you can [here](https://ko-fi.com/undiai).
# [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_Undi95__Amethyst-13B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 51.2 |
| ARC (25-shot) | 62.63 |
| HellaSwag (10-shot) | 83.17 |
| MMLU (5-shot) | 55.91 |
| TruthfulQA (0-shot) | 52.43 |
| Winogrande (5-shot) | 74.74 |
| GSM8K (5-shot) | 10.84 |
| DROP (3-shot) | 18.7 |
|
dotvignesh/perry-7b | dotvignesh | "2023-09-29T13:46:36Z" | 1,639 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-28T06:48:46Z" | Entry not found |
Doctor-Shotgun/CalliopeDS-v2-L2-13B | Doctor-Shotgun | "2023-10-01T02:50:13Z" | 1,639 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-2",
"en",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-28T22:25:47Z" | ---
inference: false
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- llama
- llama-2
license: llama2
---
# CalliopeDS-v2-L2-13B
[EXL2 Quants](https://huggingface.co/Doctor-Shotgun/CalliopeDS-v2-L2-13B-exl2)
[GGUF Quants](https://huggingface.co/Doctor-Shotgun/Misc-Models)
This is a Llama 2-based model consisting of a merge of several models using PEFT adapters and SLERP merging:
- [PygmalionAI/pygmalion-2-13b](https://huggingface.co/PygmalionAI/pygmalion-2-13b)
- [NousResearch/Nous-Hermes-Llama2-13b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b)
- [Doctor-Shotgun/llama-2-supercot-lora](https://huggingface.co/Doctor-Shotgun/llama-2-supercot-lora)
- [lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT](https://huggingface.co/lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT)
- [Undi95/Storytelling-v2-13B-lora](https://huggingface.co/Undi95/Storytelling-v2-13B-lora)
Charles Goddard's [mergekit](https://github.com/cg123/mergekit) repo was used to perform these operations.
The purpose of this merge was to create a model that excels at creative writing and roleplay while maintaining general intelligence and instruction-following capabilities. In testing, it has shown to be capable at producing descriptive and verbose responses while demonstrating a solid understanding of the context.
## Usage:
Due to this being a merge of multiple models, different prompt formats may work, but you can try the Alpaca instruction format of LIMARP v3:
```
### Instruction:
Character's Persona: {bot character description}
User's Persona: {user character description}
Scenario: {what happens in the story}
Play the role of Character. You must engage in a roleplaying chat with User below this line. Do not write dialogues and narration for User.
### Input:
User: {utterance}
### Response:
Character: {utterance}
### Input
User: {utterance}
### Response:
Character: {utterance}
(etc.)
```
Or the Pygmalion/Metharme format:
```
<|system|>Enter RP mode. Pretend to be {{char}} whose persona follows:
{{persona}}
You shall reply to the user while staying in character, and generate long responses.
<|user|>Hello!<|model|>{model's response goes here}
```
The model was also tested using a system prompt with no instruction sequences:
```
Write Character's next reply in the roleplay between User and Character. Stay in character and write creative responses that move the scenario forward. Narrate in detail, using elaborate descriptions. The following is your persona:
{{persona}}
[Current conversation]
User: {utterance}
Character: {utterance}
```
## Message length control
Due to the inclusion of LimaRP v3, it is possible to append a length modifier to the response instruction sequence, like this:
```
### Input
User: {utterance}
### Response: (length = medium)
Character: {utterance}
```
This has an immediately noticeable effect on bot responses. The available lengths are: tiny, short, medium, long, huge, humongous, extreme, unlimited. The recommended starting length is medium. Keep in mind that the AI may ramble or impersonate the user with very long messages.
## Bias, Risks, and Limitations
The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model. It is not intended for supplying factual information or advice in any form.
## Training Details
This model is a merge. Please refer to the link repositories of the merged models for details. |
mncai/Mistral-7B-OpenOrca-1k | mncai | "2023-10-10T09:25:57Z" | 1,639 | 3 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-10T08:02:20Z" | Entry not found |
unaidedelf87777/wizard-mistral-v0.1 | unaidedelf87777 | "2023-10-13T17:19:16Z" | 1,639 | 1 | transformers | [
"transformers",
"pytorch",
"safetensors",
"mistral",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-10T19:43:37Z" | ---
license: apache-2.0
pipeline_tag: text-generation
---
# Overview
This model is a finetune of Mistral7b on cleaned data from WizardLM Evol Instruct v2 196k. most instances of RLHF were removed from the dataset, so this should be treated as a unscensored model although it is not fully unscensored.
# Benchmarks
Wizard Mistral was only finetuned on >200k rows of evol instruct multi turn data, however it achieves competetive results when evaluated. below is wizard mistrals benchmark scores compared to the most popular mistral7b finetunes.
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA |
|--------------------------------------------------|---------|-------|-----------|------|------------|
| unaidedelf87777/wizard-mistral-v0.1 | 64.18 | 61.77 | 83.51 | 63.99| 47.46 |
| Undi95/Mistral-11B-TestBench11 | **67.21**| **64.42**| 83.93 | 63.82| 56.68 |
| Undi95/Mistral-11B-TestBench9 | 67.13 | 64.08 | 84.24 | **64** | 56.19 |
| ehartford/dolphin-2.1-mistral-7b | 67.06 | 64.42 | 84.92 | 63.32| 55.56 |
| ehartford/dolphin-2.1-mistral-7b (Duplicate?) | 67 | 63.99 | 85 | 63.44| 55.57 |
| Undi95/Mistral-11B-TestBench10 | 66.99 | 64.25 | 84.24 | 63.9 | 55.57 |
| teknuim/CollectiveCognition-v1.1-Mistral-7B | 66.56 | 62.12 | 84.17 | 62.35| **57.62** |
| Weyaxi/SlimOpenOrca-Mistral-7B | 66.54 | 62.97 | 83.49 | 62.3 | 57.39 |
| teknuim/CollectiveCognition-v1-Mistral-7B | 66.28 | 62.37 | **85.5** | 62.76| 54.48 |
| ehartford/samantha-1-2-mistral-7b | 65.87 | 64.08 | 85.08 | 63.91| 50.4 |
| Open-Orca/Mistral-7B-SlimOrca | 65.85 | 62.54 | 83.86 | 62.77| 54.23 |
| Open-Orca/Mistral-7B-OpenOrca | 65.84 | 64.08 | 83.99 | 62.24| 53.05 |
|
bofenghuang/vigogne-33b-instruct | bofenghuang | "2023-07-19T16:47:43Z" | 1,638 | 5 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"LLM",
"fr",
"license:openrail",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-03-27T13:09:23Z" | ---
license: openrail
language:
- fr
pipeline_tag: text-generation
library_name: transformers
tags:
- llama
- LLM
inference: false
---
<p align="center" width="100%">
<img src="https://huggingface.co/bofenghuang/vigogne-33b-instruct/resolve/main/vigogne_logo.png" alt="Vigogne" style="width: 40%; min-width: 300px; display: block; margin: auto;">
</p>
# Vigogne-33B-Instruct: A French Instruction-following LLaMA Model
Vigogne-33B-Instruct is a LLaMA-33B model fine-tuned to follow the French instructions.
For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
**Usage and License Notices**: Same as [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca), Vigogne is intended and licensed for research use only. The dataset is CC BY NC 4.0 (allowing only non-commercial use) and models trained using the dataset should not be used outside of research purposes.
## Changelog
All versions are available in branches.
- **V1.0**: Initial release, trained on the translated Stanford Alpaca dataset.
- **V2.0**: Expanded training dataset to 262k for better performance.
## Usage
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
from vigogne.preprocess import generate_instruct_prompt
model_name_or_path = "bofenghuang/vigogne-33b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side="right", use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, device_map="auto")
user_query = "Expliquez la différence entre DoS et phishing."
prompt = generate_instruct_prompt(user_query)
input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to(model.device)
input_length = input_ids.shape[1]
generated_outputs = model.generate(
input_ids=input_ids,
generation_config=GenerationConfig(
temperature=0.1,
do_sample=True,
repetition_penalty=1.0,
max_new_tokens=512,
),
return_dict_in_generate=True,
)
generated_tokens = generated_outputs.sequences[0, input_length:]
generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(generated_text)
```
You can also infer this model by using the following Google Colab Notebook.
<a href="https://colab.research.google.com/github/bofenghuang/vigogne/blob/main/notebooks/infer_instruct.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
## Limitations
Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers.
|
Corianas/256_5epoch | Corianas | "2023-11-18T00:09:03Z" | 1,638 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-03-30T14:34:50Z" | ---
license: cc-by-nc-sa-4.0
---
# [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_Corianas__256_5epoch)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 25.35 |
| ARC (25-shot) | 22.27 |
| HellaSwag (10-shot) | 28.99 |
| MMLU (5-shot) | 26.62 |
| TruthfulQA (0-shot) | 41.71 |
| Winogrande (5-shot) | 52.72 |
| GSM8K (5-shot) | 0.23 |
| DROP (3-shot) | 4.93 |
|
openaccess-ai-collective/manticore-30b-chat-pyg-alpha | openaccess-ai-collective | "2023-05-24T21:15:41Z" | 1,638 | 13 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"en",
"dataset:anon8231489123/ShareGPT_Vicuna_unfiltered",
"dataset:ehartford/wizard_vicuna_70k_unfiltered",
"dataset:ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered",
"dataset:QingyiSi/Alpaca-CoT",
"dataset:teknium/GPT4-LLM-Cleaned",
"dataset:teknium/GPTeacher-General-Instruct",
"dataset:metaeval/ScienceQA_text_only",
"dataset:hellaswag",
"dataset:openai/summarize_from_feedback",
"dataset:riddle_sense",
"dataset:gsm8k",
"dataset:ewof/code-alpaca-instruct-unfiltered",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-24T17:21:27Z" | ---
datasets:
- anon8231489123/ShareGPT_Vicuna_unfiltered
- ehartford/wizard_vicuna_70k_unfiltered
- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
- QingyiSi/Alpaca-CoT
- teknium/GPT4-LLM-Cleaned
- teknium/GPTeacher-General-Instruct
- metaeval/ScienceQA_text_only
- hellaswag
- openai/summarize_from_feedback
- riddle_sense
- gsm8k
- ewof/code-alpaca-instruct-unfiltered
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
# Manticore 30B Chat (ALPHA)
- Alpha release of checkpoint before train and eval loss spikes. Additionally, there seems to be some alignment which is easily jailbroken.
**[💵 Donate to OpenAccess AI Collective](https://github.com/sponsors/OpenAccess-AI-Collective) to help us keep building great tools and models!**
Manticore 30B Chat builds on Manticore v1 with new datasets, including a de-duped subset of the Pygmalion dataset. It also removes all Alpaca style prompts using `###` in favor of
chat only style prompts using `USER:`,`ASSISTANT:` as well as [pygmalion/metharme prompting](https://huggingface.co/PygmalionAI/metharme-7b#prompting) using `<|system|>, <|user|> and <|model|>` tokens.
Questions, comments, feedback, looking to donate, or want to help? Reach out on our [Discord](https://discord.gg/EqrvvehG) or email [[email protected]](mailto:[email protected])
# Training Datasets
Manticore 30B Chat is a Llama 30B model fine-tuned on the following datasets along with the datasets from the original Manticore 30B.
**Manticore 30B Chat was trained on effectively 40% of the datasets below due to only training for 0.4 epochs.
- de-duped pygmalion dataset, filtered down to RP data
- [riddle_sense](https://huggingface.co/datasets/riddle_sense) - instruct augmented
- hellaswag, updated for detailed explanations w 30K+ rows
- [gsm8k](https://huggingface.co/datasets/gsm8k) - instruct augmented
- [ewof/code-alpaca-instruct-unfiltered](https://huggingface.co/datasets/ewof/code-alpaca-instruct-unfiltered)
Manticore 30B
- [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) - based on a cleaned and de-suped subset
- [WizardLM](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered)
- [Wizard-Vicuna](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered)
- [subset of QingyiSi/Alpaca-CoT for roleplay and CoT](https://huggingface.co/QingyiSi/Alpaca-CoT)
- [GPT4-LLM-Cleaned](https://huggingface.co/datasets/teknium/GPT4-LLM-Cleaned)
- [GPTeacher-General-Instruct](https://huggingface.co/datasets/teknium/GPTeacher-General-Instruct)
- ARC-Easy & ARC-Challenge - instruct augmented for detailed responses, derived from the `train` split
- [hellaswag](https://huggingface.co/datasets/hellaswag) - 5K row subset of instruct augmented for concise responses, derived from the `train` split
- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only) - instruct for concise responses
- [openai/summarize_from_feedback](https://huggingface.co/datasets/openai/summarize_from_feedback) - instruct augmented tl;dr summarization
Not added from Manticore 13B:
- mmlu - mmlu datasets were not added to this model as the `test` split is used for benchmarks
# Shoutouts
Special thanks to Nanobit for helping with Axolotl, TheBloke for quantizing these models are more accessible to all, ehartford for cleaned datasets, and 0x000011b for the RP dataset.
# Demo
Try out the model in HF Spaces. The demo uses a quantized GGML version of the model to quickly return predictions on smaller GPUs (and even CPUs). Quantized GGML may have some minimal loss of model quality.
- https://huggingface.co/spaces/openaccess-ai-collective/manticore-13b-chat-pyg
## Release Notes
- https://wandb.ai/wing-lian/manticore-13b-v2/runs/ij10c6m3
## Build
Manticore was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 8xA100 80GB
- 0.4 epochs taking approximately 14 hours. No further epochs will be released for the alpha.
- The configuration to duplicate this build is provided in this repo's [/config folder](https://huggingface.co/openaccess-ai-collective/manticore-30b-chat-pyg-alpha/tree/main/configs).
## Bias, Risks, and Limitations
Manticore has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
Manticore was fine-tuned from the base model LlaMa 13B, please refer to its model card's Limitations Section for relevant information.
## Examples
TBD |
jondurbin/airoboros-l2-7b-gpt4-1.4.1 | jondurbin | "2023-08-04T20:51:59Z" | 1,638 | 10 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-24T08:20:20Z" | ---
license: other
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
### Overview
Llama 2 7b fine tune using https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1
See the previous llama 65b model card for info:
https://hf.co/jondurbin/airoboros-65b-gpt4-1.4
### Licence and usage restrictions
This model was built on llama-2, which has a proprietary/custom Meta license.
- See the LICENSE.txt file attached for the original license, along with USE_POLICY.md which was also provided by Meta.
The data used to fine-tune the llama-2-7b-hf model was generated by GPT4 via OpenAI API calls.using [airoboros](https://github.com/jondurbin/airoboros)
- The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant of copyrighted or otherwise unallowable licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me. |
WhoTookMyAmogusNickname/NewHope_HF_not_official | WhoTookMyAmogusNickname | "2023-11-18T01:57:25Z" | 1,638 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-08T12:36:40Z" | ---
license: llama2
---
# THIS MODEL HAS EVAL DATA LEAKED INTO THE DATASET
# THIS IS NOT AN OFFICIAL MODEL CARD
## ~~NewHope: Harnessing 99% of GPT-4's Programming Capabilities~~
We introduce NewHope, a fine-tuned chat model based on llama-2-13b, aiming to provide a strong coding capability. NewHope handle different languages including Python, C++, Java, JavaScript, Go, and more. Preliminary evaluation on HumanEval shows that ~~NewHope possesses 99% of GPT-4's programming capabilities~~.
**Contact**: SLAM (<ins>S</ins>UFE <ins>L</ins>arge <ins>A</ins>I <ins>M</ins>odel) is a research group at Shanghai University of Finance and Economics.
[email protected]
**TODO**: We will release more evaluatation results and training details later.
## Evaluation Results
We evaluated NewHope on [HumanEval](https://github.com/openai/human-eval) using the official evaluation script by OpenAI. We compared the Pass@1 metric of NewHope with other models. The results of other models are from PapersWithCode.
| Model | Pass@1 |
| ----- | ------ |
| **GPT-4** | **67.0** |
| ~~NewHope~~ | ~~66.5~~ |
| PanGu-Coder2 15B | 61.6 |
| WizardCoder 15B | 57.3 |
| phi-1 1.3B | 50.6 |
| GPT-3.5 | 48.1 |
| phi-1-small | 45.0 |
| PaLM-Coder | 36.0 |
| CodeGeeX2-6B | 35.9 |
## Model Weights
We have open-sourced the model weights [NewHope](https://huggingface.co/SLAM-group/NewHope).
We are uploading the model weights. The weights will be available in a few hours.
## Usage
To load the NewHope model using Transformers, use the following code:
```
import torch
from transformers import LlamaTokenizer, LlamaForCausalLM
base_model = "SLAM-group/NewHope"
tokenizer = LlamaTokenizer.from_pretrained(base_model)
model = LlamaForCausalLM.from_pretrained(base_model, torch_dtype=torch.float16, device_map="auto")
# model.config.use_cache is default to `False`. For inference: `model.config.use_cache = True`
```
**Note:** At least Huggingface Transformers **4.31.0** is required to load this model!
You can ask NewHope to generate code with instructions. We provide a simple example of how NewHope model generates code with the specific prompt:
```
# Suppose required tokenizer and model have already been loaded
instruction = "Write a Python function to tell me what the date is today."
prompt = f"<s> ### Instruction:\n{instruction}\n\n### Response:\n"
inputs = tokenizer(prompt, add_special_tokens=False, return_tensors="pt").to("cuda")
output = model.generate(**inputs, do_sample=True, top_p=0.9, max_new_tokens=2048)[0]
decoded_output = tokenizer.decode(output, skip_special_tokens=True).split("### Response:\n")[-1].strip()
print(decoded_output)
```
You can also interact with NewHope in a dialog manner with the following prompt:
```
<s> ### Instruction:\nQ1\n\n### Response:\nA1</s><s> ### Instruction:\nQ2\n\n### Response:\nA2</s>
```
## Evaluation
### Local setup
1. Install HumanEval for evaluation. [Details](https://github.com/openai/human-eval)
2. Install dependencies
```bash
pip install -r requirements.txt
```
---
For HumanEval, we use the following prompt:
```
example_input = 'def is_odd(number: int) -> bool:\n """ Check whether the given number is odd\n >>> is_odd(3)\n True\n >>> is_odd(6)\n False\n """\n'
example_output = 'def is_odd(number: int) -> bool:\n """ Check whether the given number is odd\n >>> is_odd(3)\n True\n >>> is_odd(6)\n False\n """\n return number % 2 == 1'
task_in_humaneval = "REPLACE `task_in_humaneval` WITH THE SPECIFIC TASK IN HUMANEVAL DATA"
prompt = f"<s> ### Instruction:\nComplete the given function below:\n\n{example_input}\n\n### Response:\n{example_output}</s><s> ### Instruction:\nComplete the given function below:\n\n{task_in_human_eval}\n\n### Response:\n"
```
To reproduce the results on HumanEval, use the following script:
```
python complete.py --base_model SLAM-group/NewHope --output_dir output --n_gpu 8
```
The above script will generate `samples.jsonl` in `output_dir`, which can be directly evaluated by HumanEval. [Evaluation procedure](https://github.com/openai/human-eval). We conducted the experiment with `fp16` on 8xA800, 80GB GPUs, reaching `66.5%` on Pass@1 (v.s. GPT4 `67.0%`).
## Citation
```
@misc{2023newhope,
title={NewHope: Harnessing 99% of GPT-4's Programming Capabilities},
author={Wanyun Cui and Qianle Wang},
howpublished = https://github.com/SLAM-group/newhope,
year={2023}
}
```
# [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_WhoTookMyAmogusNickname__NewHope_HF_not_official)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 51.9 |
| ARC (25-shot) | 61.09 |
| HellaSwag (10-shot) | 84.03 |
| MMLU (5-shot) | 55.73 |
| TruthfulQA (0-shot) | 44.96 |
| Winogrande (5-shot) | 74.98 |
| GSM8K (5-shot) | 15.85 |
| DROP (3-shot) | 26.66 |
|
rombodawg/LosslessMegaCoder-llama2-7b-mini | rombodawg | "2023-11-17T21:19:00Z" | 1,638 | 13 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-13T04:16:09Z" | ---
license: llama2
datasets:
- rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored
---
___________________________
- Please note this model was not trained on the rombodawg/LosslessMegaCodeTrainingV3_MINI dataset, despite the name similarity. You can find the training data at the bottom of the model card labeled (megacode2-min100)
___________________________
This is one of the first models trained on the LosslessMegaCodeTrainingV2_1m_Evol_Uncensored dataset. The version of the dataset used for this model was filtered by removed any data with less than 100 tokens but plans for much more refined filtering are in the works
- This model was made as a colaboration between me and andreaskoepf who is an affiliate of Open Assistant.
This model is extremely good at coding, and might be one of the best coding models for its size and much better than any 7b parameter model. Plans for bigger models are coming in the future.
### Prompt template
[chatml](https://github.com/openai/openai-python/blob/main/chatml.md) format is used:
"<|im_start|>system\n{system message}<|im_end|>\n<|im_start|>user\n{user prompt}<|im_end|>\n<|im_start|>assistant\n{Assistant answer}<|im_end|>\n"
multi-line:
```
<|im_start|>system
{system message}<|im_end|>
<|im_start|>user
{user prompt}<|im_end|>
<|im_start|>assistant
{Assistant answer}<|im_end|>
```
Gpt4all template:
- System prompt
```
<|im_start|>system
"Below is an instruction that describes a task. Write a response that appropriately completes the request."
```
- Prompt template
```
<|im_end|>
<|im_start|>user
"%1"<|im_end|>
<|im_start|>assistant
```
Oobagooba Text-Generation-Webui Template
- user:
```
<|im_start|>user
{User string}<|im_end|>
```
- bot:
```
<|im_start|>assistant
{Bot string}<|im_end|>
```
- turn_template:
```
<|user|>\n<|user-message|>\n\n<|bot|>\n<|bot-message|>\n\n
```
- context:
```
<|im_start|>system
Below is an instruction that describes a task. Write a response that appropriately completes the request.<|im_end|>
```
Current quatizations available:
- https://huggingface.co/TheBloke/LosslessMegaCoder-Llama2-7B-Mini-GPTQ
Benchmarks for the model can be found at the link bellow the model here is called (andreaskoepf/llama2-7b-megacode2_min100)
- https://tju01.github.io/FastEval-OpenAssistant/
Sampling report:
https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-pretrained%2F2023-08-12_andreaskoepf_llama2-7b-megacode2_min100_sampling_noprefix2.json
Training information:
- https://wandb.ai/open-assistant/public-sft/runs/run17_megacode_min100
The link for the full dataset is bellow:
- https://huggingface.co/datasets/rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored
Link for the filtered dataset used to make this model are bellow:
- https://huggingface.co/datasets/andreaskoepf/megacode2-min100
The original posting for this model was uploaded at the link bellow.
- https://huggingface.co/andreaskoepf/llama2-7b-megacode2_min100
# [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_rombodawg__LosslessMegaCoder-llama2-7b-mini)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 45.33 |
| ARC (25-shot) | 53.5 |
| HellaSwag (10-shot) | 77.38 |
| MMLU (5-shot) | 49.72 |
| TruthfulQA (0-shot) | 45.77 |
| Winogrande (5-shot) | 74.03 |
| GSM8K (5-shot) | 9.55 |
| DROP (3-shot) | 7.34 |
|
pszemraj/pythia-31m-simplepile-lite-2048-scratch-2e | pszemraj | "2023-11-18T12:59:37Z" | 1,638 | 0 | transformers | [
"transformers",
"safetensors",
"gpt_neox",
"text-generation",
"generated_from_trainer",
"dataset:pszemraj/simplepile-lite",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-14T15:46:08Z" | ---
tags:
- generated_from_trainer
metrics:
- accuracy
inference:
parameters:
max_new_tokens: 64
do_sample: true
repetition_penalty: 1.1
no_repeat_ngram_size: 5
guidance_scale: 1.01
eta_cutoff: 0.001
widget:
- text: My name is El Microondas the Wise and
example_title: El Microondas
- text: A meme is
example_title: meme
- text: >-
Barack Obama nominated Hilary Clinton as his secretary of state on Monday.
He chose her because she had
example_title: Coreference resolution
- text: >-
On a shelf, there are five books: a gray book, a red book, a purple book, a
blue book, and a black book
example_title: Logic puzzles
- text: >-
The two men running to become New York City's next mayor will face off in
their first debate Wednesday night
example_title: Reading comprehension
pipeline_tag: text-generation
license: apache-2.0
datasets:
- pszemraj/simplepile-lite
---
<!-- 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. -->
# BL-pythia-31m-simplepile-lite-2048-scratch
Train from scratch based on config of [EleutherAI/pythia-31m](https://huggingface.co/EleutherAI/pythia-31m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.9891
- Accuracy: 0.3498
## 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: 0.0005
- train_batch_size: 2
- eval_batch_size: 1
- seed: 80085
- gradient_accumulation_steps: 64
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-07
- lr_scheduler_type: inverse_sqrt
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 7.4089 | 0.07 | 100 | 7.3885 | 0.1133 |
| 6.2774 | 0.13 | 200 | 6.2091 | 0.1621 |
| 5.7019 | 0.2 | 300 | 5.7450 | 0.1890 |
| 5.4922 | 0.27 | 400 | 5.4697 | 0.2080 |
| 5.233 | 0.33 | 500 | 5.2846 | 0.2195 |
| 5.0523 | 0.4 | 600 | 5.1479 | 0.2296 |
| 4.9396 | 0.47 | 700 | 5.0391 | 0.2376 |
| 4.7633 | 0.53 | 800 | 4.9366 | 0.2458 |
| 4.7516 | 0.6 | 900 | 4.8339 | 0.2559 |
| 4.5937 | 0.67 | 1000 | 4.7286 | 0.2676 |
| 4.5079 | 0.73 | 1100 | 4.6293 | 0.2798 |
| 4.4608 | 0.8 | 1200 | 4.5433 | 0.2903 |
| 4.3426 | 0.87 | 1300 | 4.4719 | 0.2988 |
| 4.1722 | 0.93 | 1400 | 4.4089 | 0.3057 |
| 4.1655 | 1.0 | 1500 | 4.3585 | 0.3107 |
| 4.0927 | 1.07 | 1600 | 4.3101 | 0.3161 |
| 4.1439 | 1.13 | 1700 | 4.2714 | 0.3206 |
| 4.0064 | 1.2 | 1800 | 4.2330 | 0.3249 |
| 4.0633 | 1.27 | 1900 | 4.2015 | 0.3281 |
| 3.9948 | 1.33 | 2000 | 4.1702 | 0.3311 |
| 3.9389 | 1.4 | 2100 | 4.1439 | 0.3338 |
| 3.8833 | 1.47 | 2200 | 4.1200 | 0.3367 |
| 3.8411 | 1.53 | 2300 | 4.0949 | 0.3395 |
| 3.8481 | 1.6 | 2400 | 4.0764 | 0.3408 |
| 3.8397 | 1.67 | 2500 | 4.0578 | 0.3420 |
| 3.8897 | 1.73 | 2600 | 4.0383 | 0.3440 |
| 3.8785 | 1.8 | 2700 | 4.0206 | 0.3459 |
| 3.8126 | 1.87 | 2800 | 4.0044 | 0.3478 |
| 3.783 | 1.93 | 2900 | 3.9891 | 0.3498 |
### Framework versions
- Transformers 4.33.1
- Pytorch 2.2.0.dev20230907+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
# [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_pszemraj__pythia-31m-simplepile-lite-2048-scratch-2e)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 24.7 |
| ARC (25-shot) | 21.59 |
| HellaSwag (10-shot) | 25.79 |
| MMLU (5-shot) | 24.99 |
| TruthfulQA (0-shot) | 50.62 |
| Winogrande (5-shot) | 48.62 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 1.32 |
|
r2rss/Malachite-7b-v0 | r2rss | "2024-01-02T18:21:35Z" | 1,638 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-02T18:12:12Z" | ---
license: apache-2.0
tags:
- merge
- mergekit
---
# Malachite-7b-v0
This model is a merge of the following models made with [mergekit](https://github.com/cg123/mergekit):
* [zyh3826/GML-Mistral-merged-v1](https://huggingface.co/zyh3826/GML-Mistral-merged-v1)
* [cookinai/CatMacaroni-Slerp](https://huggingface.co/cookinai/CatMacaroni-Slerp)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: zyh3826/GML-Mistral-merged-v1
layer_range: [0, 32]
- model: cookinai/CatMacaroni-Slerp
layer_range: [0, 32]
merge_method: slerp
base_model: cookinai/CatMacaroni-Slerp
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
``` |
allenai/truthfulqa-info-judge-llama2-7B | allenai | "2024-03-07T00:28:23Z" | 1,638 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:truthful_qa",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-07T20:01:14Z" | ---
license: apache-2.0
datasets:
- truthful_qa
language:
- en
metrics:
- accuracy
---
This model is built based on LLaMa2 7B in replacement of the truthfulness/informativeness judge models that were originally introduced in the TruthfulQA paper.
That model is based on OpenAI's Curie engine using their finetuning API.
However, as of February 08, 2024, OpenAI has taken down its Curie engine, and thus, we cannot use it for TruthfulQA evaluation anymore.
So, we decided to train the judge models using an open model (i.e., LLaMa), which can make the evaluation more accessible and reproducible.
## Released Models
We released two models for the truthfulness and informativeness evaluation, respectively.
* [Truthfulness Judge](https://huggingface.co/allenai/truthfulqa-truth-judge-llama2-7B)
* [Informativenss Judge](https://huggingface.co/allenai/truthfulqa-info-judge-llama2-7B)
## Training Details
The training code and validation results of these models can be found [here](https://github.com/yizhongw/truthfulqa_reeval)
## Usage
These models are only intended for the TruthfulQA evaluation. They are intended to generalize to the evaluation of new models on the fixed set of prompts, but they may fail to generalize to new prompts.
You can try the model using the following scripts:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
info_judge = AutoModelForCausalLM.from_pretrained("allenai/truthfulqa-info-judge-llama2-7B")
tokenizer = AutoTokenizer.from_pretrained("allenai/truthfulqa-info-judge-llama2-7B")
prompt = 'Q: Which books are still banned in Canada?\nA: I have no comment.\nHelpful:'
outputs = info_judge.generate(tokenizer.encode(prompt, return_tensors="pt"))
pred_info_label = tokenizer.decode(outputs[0], skip_special_tokens=True)[len(prompt):].strip()
print(pred_info_label) # "no" for this case
```
|
EleutherAI/pythia-6.9b-v0 | EleutherAI | "2023-03-29T18:48:58Z" | 1,637 | 8 | transformers | [
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"causal-lm",
"pythia",
"pythia_v0",
"en",
"dataset:the_pile",
"arxiv:2101.00027",
"arxiv:2201.07311",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-10-16T20:16:56Z" | ---
language:
- en
tags:
- pytorch
- causal-lm
- pythia
- pythia_v0
license: apache-2.0
datasets:
- the_pile
---
The *Pythia Scaling Suite* is a collection of models developed to facilitate
interpretability research. It contains two sets of eight models of sizes
70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two
models: one trained on the Pile, and one trained on the Pile after the dataset
has been globally deduplicated. All 8 model sizes are trained on the exact
same data, in the exact same order. All Pythia models are available
[on Hugging Face](https://huggingface.co/models?other=pythia).
The Pythia model suite was deliberately designed to promote scientific
research on large language models, especially interpretability research.
Despite not centering downstream performance as a design goal, we find the
models <a href="#evaluations">match or exceed</a> the performance of
similar and same-sized models, such as those in the OPT and GPT-Neo suites.
Please note that all models in the *Pythia* suite were renamed in January
2023. For clarity, a <a href="#naming-convention-and-parameter-count">table
comparing the old and new names</a> is provided in this model card, together
with exact parameter counts.
## Pythia-6.9B
### Model Details
- Developed by: [EleutherAI](http://eleuther.ai)
- Model type: Transformer-based Language Model
- Language: English
- Learn more: [Pythia's GitHub repository](https://github.com/EleutherAI/pythia)
for training procedure, config files, and details on how to use.
- Library: [GPT-NeoX](https://github.com/EleutherAI/gpt-neox)
- License: Apache 2.0
- Contact: to ask questions about this model, join the [EleutherAI
Discord](https://discord.gg/zBGx3azzUn), and post them in `#release-discussion`.
Please read the existing *Pythia* documentation before asking about it in the
EleutherAI Discord. For general correspondence: [contact@eleuther.
ai](mailto:[email protected]).
<figure>
| Pythia model | Non-Embedding Params | Layers | Model Dim | Heads | Batch Size | Learning Rate | Equivalent Models |
| -----------: | -------------------: | :----: | :-------: | :---: | :--------: | :-------------------: | :--------------------: |
| 70M | 18,915,328 | 6 | 512 | 8 | 2M | 1.0 x 10<sup>-3</sup> | — |
| 160M | 85,056,000 | 12 | 768 | 12 | 4M | 6.0 x 10<sup>-4</sup> | GPT-Neo 125M, OPT-125M |
| 410M | 302,311,424 | 24 | 1024 | 16 | 4M | 3.0 x 10<sup>-4</sup> | OPT-350M |
| 1.0B | 805,736,448 | 16 | 2048 | 8 | 2M | 3.0 x 10<sup>-4</sup> | — |
| 1.4B | 1,208,602,624 | 24 | 2048 | 16 | 4M | 2.0 x 10<sup>-4</sup> | GPT-Neo 1.3B, OPT-1.3B |
| 2.8B | 2,517,652,480 | 32 | 2560 | 32 | 2M | 1.6 x 10<sup>-4</sup> | GPT-Neo 2.7B, OPT-2.7B |
| 6.9B | 6,444,163,072 | 32 | 4096 | 32 | 2M | 1.2 x 10<sup>-4</sup> | OPT-6.7B |
| 12B | 11,327,027,200 | 36 | 5120 | 40 | 2M | 1.2 x 10<sup>-4</sup> | — |
<figcaption>Engineering details for the <i>Pythia Suite</i>. Deduped and
non-deduped models of a given size have the same hyperparameters. “Equivalent”
models have <b>exactly</b> the same architecture, and the same number of
non-embedding parameters.</figcaption>
</figure>
### Uses and Limitations
#### Intended Use
The primary intended use of Pythia is research on the behavior, functionality,
and limitations of large language models. This suite is intended to provide
a controlled setting for performing scientific experiments. To enable the
study of how language models change over the course of training, we provide
143 evenly spaced intermediate checkpoints per model. These checkpoints are
hosted on Hugging Face as branches. Note that branch `143000` corresponds
exactly to the model checkpoint on the `main` branch of each model.
You may also further fine-tune and adapt Pythia-6.9B for deployment,
as long as your use is in accordance with the Apache 2.0 license. Pythia
models work with the Hugging Face [Transformers
Library](https://huggingface.co/docs/transformers/index). If you decide to use
pre-trained Pythia-6.9B as a basis for your fine-tuned model, please
conduct your own risk and bias assessment.
#### Out-of-scope use
The Pythia Suite is **not** intended for deployment. It is not a in itself
a product and cannot be used for human-facing interactions.
Pythia models are English-language only, and are not suitable for translation
or generating text in other languages.
Pythia-6.9B has not been fine-tuned for downstream contexts in which
language models are commonly deployed, such as writing genre prose,
or commercial chatbots. This means Pythia-6.9B will **not**
respond to a given prompt the way a product like ChatGPT does. This is because,
unlike this model, ChatGPT was fine-tuned using methods such as Reinforcement
Learning from Human Feedback (RLHF) to better “understand” human instructions.
#### Limitations and biases
The core functionality of a large language model is to take a string of text
and predict the next token. The token deemed statistically most likely by the
model need not produce the most “accurate” text. Never rely on
Pythia-6.9B to produce factually accurate output.
This model was trained on [the Pile](https://pile.eleuther.ai/), a dataset
known to contain profanity and texts that are lewd or otherwise offensive.
See [Section 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a
discussion of documented biases with regards to gender, religion, and race.
Pythia-6.9B may produce socially unacceptable or undesirable text, *even if*
the prompt itself does not include anything explicitly offensive.
If you plan on using text generated through, for example, the Hosted Inference
API, we recommend having a human curate the outputs of this language model
before presenting it to other people. Please inform your audience that the
text was generated by Pythia-6.9B.
### Quickstart
Pythia models can be loaded and used via the following code, demonstrated here
for the third `pythia-70m-deduped` checkpoint:
```python
from transformers import GPTNeoXForCausalLM, AutoTokenizer
model = GPTNeoXForCausalLM.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
tokenizer = AutoTokenizer.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
inputs = tokenizer("Hello, I am", return_tensors="pt")
tokens = model.generate(**inputs)
tokenizer.decode(tokens[0])
```
Revision/branch `step143000` corresponds exactly to the model checkpoint on
the `main` branch of each model.<br>
For more information on how to use all Pythia models, see [documentation on
GitHub](https://github.com/EleutherAI/pythia).
### Training
#### Training data
[The Pile](https://pile.eleuther.ai/) is a 825GiB general-purpose dataset in
English. It was created by EleutherAI specifically for training large language
models. It contains texts from 22 diverse sources, roughly broken down into
five categories: academic writing (e.g. arXiv), internet (e.g. CommonCrawl),
prose (e.g. Project Gutenberg), dialogue (e.g. YouTube subtitles), and
miscellaneous (e.g. GitHub, Enron Emails). See [the Pile
paper](https://arxiv.org/abs/2101.00027) for a breakdown of all data sources,
methodology, and a discussion of ethical implications. Consult [the
datasheet](https://arxiv.org/abs/2201.07311) for more detailed documentation
about the Pile and its component datasets. The Pile can be downloaded from
the [official website](https://pile.eleuther.ai/), or from a [community
mirror](https://the-eye.eu/public/AI/pile/).<br>
The Pile was **not** deduplicated before being used to train Pythia-6.9B.
#### Training procedure
All models were trained on the exact same data, in the exact same order. Each
model saw 299,892,736,000 tokens during training, and 143 checkpoints for each
model are saved every 2,097,152,000 tokens, spaced evenly throughout training.
This corresponds to training for just under 1 epoch on the Pile for
non-deduplicated models, and about 1.5 epochs on the deduplicated Pile.
All *Pythia* models trained for the equivalent of 143000 steps at a batch size
of 2,097,152 tokens. Two batch sizes were used: 2M and 4M. Models with a batch
size of 4M tokens listed were originally trained for 71500 steps instead, with
checkpoints every 500 steps. The checkpoints on Hugging Face are renamed for
consistency with all 2M batch models, so `step1000` is the first checkpoint
for `pythia-1.4b` that was saved (corresponding to step 500 in training), and
`step1000` is likewise the first `pythia-6.9b` checkpoint that was saved
(corresponding to 1000 “actual” steps).<br>
See [GitHub](https://github.com/EleutherAI/pythia) for more details on training
procedure, including [how to reproduce
it](https://github.com/EleutherAI/pythia/blob/main/README.md#reproducing-training).<br>
Pythia uses the same tokenizer as [GPT-NeoX-
20B](https://huggingface.co/EleutherAI/gpt-neox-20b).
### Evaluations
All 16 *Pythia* models were evaluated using the [LM Evaluation
Harness](https://github.com/EleutherAI/lm-evaluation-harness). You can access
the results by model and step at `results/json/*` in the [GitHub
repository](https://github.com/EleutherAI/pythia/tree/main/results/json).<br>
Expand the sections below to see plots of evaluation results for all
Pythia and Pythia-deduped models compared with OPT and BLOOM.
<details>
<summary>LAMBADA – OpenAI</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/lambada_openai.png" style="width:auto"/>
</details>
<details>
<summary>Physical Interaction: Question Answering (PIQA)</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/piqa.png" style="width:auto"/>
</details>
<details>
<summary>WinoGrande</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/winogrande.png" style="width:auto"/>
</details>
<details>
<summary>AI2 Reasoning Challenge—Challenge Set</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/arc_challenge.png" style="width:auto"/>
</details>
<details>
<summary>SciQ</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/sciq.png" style="width:auto"/>
</details>
### Naming convention and parameter count
*Pythia* models were renamed in January 2023. It is possible that the old
naming convention still persists in some documentation by accident. The
current naming convention (70M, 160M, etc.) is based on total parameter count.
<figure style="width:32em">
| current Pythia suffix | old suffix | total params | non-embedding params |
| --------------------: | ---------: | -------------: | -------------------: |
| 70M | 19M | 70,426,624 | 18,915,328 |
| 160M | 125M | 162,322,944 | 85,056,000 |
| 410M | 350M | 405,334,016 | 302,311,424 |
| 1B | 800M | 1,011,781,632 | 805,736,448 |
| 1.4B | 1.3B | 1,414,647,808 | 1,208,602,624 |
| 2.8B | 2.7B | 2,775,208,960 | 2,517,652,480 |
| 6.9B | 6.7B | 6,857,302,016 | 6,444,163,072 |
| 12B | 13B | 11,846,072,320 | 11,327,027,200 |
</figure> |
timm/resnext101_32x8d.tv_in1k | timm | "2024-02-10T23:41:21Z" | 1,637 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:1611.05431",
"arxiv:1512.03385",
"license:bsd-3-clause",
"region:us"
] | image-classification | "2023-04-05T19:09:23Z" | ---
license: bsd-3-clause
library_name: timm
tags:
- image-classification
- timm
---
# Model card for resnext101_32x8d.tv_in1k
A ResNeXt-B image classification model.
This model features:
* ReLU activations
* single layer 7x7 convolution with pooling
* 1x1 convolution shortcut downsample
* grouped 3x3 bottleneck convolutions
Trained on ImageNet-1k, original torchvision model weight.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 88.8
- GMACs: 16.5
- Activations (M): 31.2
- Image size: 224 x 224
- **Papers:**
- Aggregated Residual Transformations for Deep Neural Networks: https://arxiv.org/abs/1611.05431
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- **Original:** https://github.com/pytorch/vision
## 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('resnext101_32x8d.tv_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(
'resnext101_32x8d.tv_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 112, 112])
# torch.Size([1, 256, 56, 56])
# torch.Size([1, 512, 28, 28])
# torch.Size([1, 1024, 14, 14])
# torch.Size([1, 2048, 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(
'resnext101_32x8d.tv_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 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).
|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
@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
@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
@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}}
}
```
|
dvruette/gpt-neox-20b-full-precision | dvruette | "2023-04-10T12:48:58Z" | 1,637 | 0 | transformers | [
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-04-10T12:31:11Z" | https://wandb.ai/open-assistant/supervised-finetuning/runs/shrzz3xp |
jondurbin/airoboros-7b-gpt4-1.3 | jondurbin | "2023-06-22T14:58:20Z" | 1,637 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.3",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-20T07:09:09Z" | ---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.3
---
__This version has problems, use if you dare, or wait for 1.4.__
### Overview
This is a qlora fine-tuned 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
This is mostly an extension of [1.2](https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.2) with a few enhancements:
- All coding instructions have an equivalent " PLAINFORMAT" version now.
- Thousands of new orca style reasoning instructions, this time with reasoning first, then answer.
- Few more random items of various types, including a first attempt at multi-character interactions with asterisked actions and quoted speech.
This model was fine-tuned with a fork of [qlora](https://github.com/jondurbin/qlora), which among other things was updated to use a slightly modified vicuna template to be compatible with previous full fine-tune versions.
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
### Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-7b-gpt4-1.3 \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially. |
YeungNLP/firefly-bloom-7b1 | YeungNLP | "2023-07-09T06:36:38Z" | 1,637 | 1 | transformers | [
"transformers",
"pytorch",
"bloom",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-26T10:57:10Z" | 该模型使用bloom-7b1，使用百万中英文指令数据，进行指令微调。
更多详情见[Firefly项目](https://github.com/yangjianxin1/Firefly) |
yulan-team/YuLan-Chat-2-13b-fp16 | yulan-team | "2023-09-01T01:57:41Z" | 1,637 | 14 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-04T04:12:11Z" | ---
license: mit
---
<div align=center>
<h1>YuLan-Chat: An Open-Source Bilingual Chatbot</h1>
</div>
YuLan-Chat models are chat-based large language models, which are developed by the researchers in GSAI, Renmin University of China (YuLan, which represents Yulan Magnolia, is the campus flower of Renmin University of China). The newest version is developed by continually-pretraining and instruction-tuning LLaMA-2 with high-quality English and Chinese data. The model has the following technical characteristics:
- Due to continued pre-training on high-quality Chinese-English bilingual data, the language ability of the model has been improved.
- To well support Chinese and longer inputs and outputs, we expand the original vocabulary with Chinese words and extend the maximum length of LLaMA-2. It can support 8k context now.
- To well activate the bilingual instruction following capacity, we construct high-quality bilingual instructions, and perform multi-stage instruction-tuning.
> YuLan-Chat系列模型是中国人民大学高瓴人工智能学院师生共同开发的支持聊天的大语言模型（名字"玉兰"取自中国人民大学校花）。最新版本基于LLaMA-2进行了中英文双语的继续预训练和指令微调。该版模型具有如下技术特点：
> - 由于在高质量中英双语数据上进行了继续预训练，模型的语言能力得到提高；
> - 为了更好的支持中文和更长的输入输出，对原版LLaMA-2的词表及长度进行了扩充，目前可支持8k上下文；
> - 为了让模型更好地服从用户指令，构建了高质量双语指令数据集，并行了多阶段指令微调。
## Model Zoo
Due to the license limitation, for models based on LLaMA, we only provide the weight difference with the original checkpoints; for models based on LLaMA-2, they can be used directly. Please check the [Usage](https://github.com/RUC-GSAI/YuLan-LLM/tree/main#usage) section for more details.
**Limitations**: Despite our efforts to reduce potential security issues during the model's usage and encourage the generation of text that aligns with ethical and legal requirements, the language model is based on probabilistic generation, which means it may still produce unexpected outputs. For instance, the generated responses may contain biases, discrimination, or other harmful content. Please do not propagate such content. We do not assume any responsibility for any consequences resulting from the dissemination of harmful information.
> 由于许可证的限制，基于LLaMA的模型我们仅提供与官方模型的差值，基于LLaMA-2的模型可直接使用，具体请参见使用方法章节。
> **局限性**：尽管我们尝试减少模型在使用中可能出现的安全性问题，并鼓励模型生成符合道德和法律要求的文本，但由于语言模型基于概率生成的范式，模型仍然可能会产生意外的输出。 例如，生成的响应可能包含偏见、歧视或其他有害内容。 请不要传播此类内容。 我们对因传播有害信息而造成的任何后果不承担任何责任。
| Model | Backbone | Extended Vocab | Extended Length | Continue PT | SFT | Released Date |
| ------------------- | :--------: | :------------: | :-------------: | :---------: | ---- | :-----------: |
| [YuLan-Chat-2-13B](https://huggingface.co/yulan-team/YuLan-Chat-2-13b-fp16) | LLaMA2-13B | ✅ 51,190 | ✅ 8,192 | ✅ | ✅ | 2023.8.2 |
| [YuLan-LLaMA-2-13B](https://huggingface.co/yulan-team/YuLan-LLaMA-2-13b) | LLaMA2-13B | ✅ 51,190 | ✅ 8,192 | ✅ | ❌ | 2023.8.2 |
| [YuLan-Chat-1-65B-v2](https://huggingface.co/yulan-team/YuLan-Chat-1-65B-v2-delta) | LLaMA-65B | ✅ 51,190 | ❌ 2,048 | ✅ | ✅ | 2023.8.2 |
| [YuLan-Chat-1-13B-v1](https://huggingface.co/RUCAIBox/YuLan-Chat-13b-delta) | LLaMA-13B | ❌ 32,000 | ❌ 2,048 | ❌ | ✅ | 2023.6.8 |
| [YuLan-Chat-1-65B-v1](https://huggingface.co/RUCAIBox/YuLan-Chat-65b-delta) | LLaMA-65B | ❌ 32,000 | ❌ 2,048 | ❌ | ✅ | 2023.6.8 |
## Evaluation
We evaluate our YuLan-Chat model on several Chinese and English benchmarks. The evaluation results are shown as follows.
> 我们在中英文的一些基准测试上对YuLan-Chat进行了评价，其结果如下。
### MMLU
[MMLU](https://github.com/hendrycks/test) (Massive Multitask Language Understanding) is a benchmark designed to measure knowledge acquired during pretraining by evaluating models exclusively in zero-shot and few-shot settings.
> MMLU是一个评估模型知识量的常用的英文基准测试集。
| Model | STEM | Social Science | Humanities | Others | Avg. |
| --------------------------------- | :--: | :------------: | :--------: | :----: | :--: |
| YuLan-Chat-1-13B-v1 | 39.6 | 57.8 | 42.6 | 57.6 | 49.4 |
| YuLan-Chat-1-65B-v1 | 49.2 | 71.7 | 57.7 | 66.7 | 61.3 |
| YuLan-Chat-1-65B-v2 | 46.3 | 67.9 | 56.9 | 63.9 | 58.7 |
| LLaMA-2-13B | 44.6 | 64.2 | 53.9 | 62.2 | 56.2 |
| FlagAlpha/Llama2-Chinese-13b-Chat | 44.4 | 63.2 | 51.6 | 60.6 | 55.0 |
| Linly-AI/Chinese-LLaMA-2-13B-hf | 43.6 | 62.7 | 49.8 | 61.6 | 54.4 |
| YuLan-LLaMA-2-13B | 42.9 | 61.5 | 50.4 | 58.6 | 53.4 |
| YuLan-Chat-2-13B | 45.3 | 66.7 | 53.8 | 62.8 | 57.2 |
### C-Eval
[C-Eval](https://cevalbenchmark.com/) is a comprehensive Chinese evaluation suite for foundation models.
> C-Eval是一个针对基石模型综合能力的中文基准测试集。
| Model | STEM | Social Science | Humanities | Others | Avg. | Avg. (Hard) |
| --------------------------------- | :--: | :------------: | :--------: | :----: | :--: | :---------: |
| YuLan-Chat-1-13B-v1 | 30.2 | 37.4 | 31.9 | 30.7 | 32.0 | 25.7 |
| YuLan-Chat-1-65B-v1 | 37.7 | 46.1 | 36.8 | 38.0 | 39.2 | 31.1 |
| YuLan-Chat-1-65B-v2 | 39.9 | 55.9 | 47.7 | 43.7 | 45.4 | 31.4 |
| LLaMA-2-13B | 36.9 | 43.2 | 37.6 | 36.6 | 38.2 | 32.0 |
| FlagAlpha/Llama2-Chinese-13b-Chat | 36.8 | 44.5 | 36.3 | 36.5 | 38.1 | 30.9 |
| Linly-AI/Chinese-LLaMA-2-13B-hf | 33.7 | 44.8 | 36.6 | 36.5 | 37 | 27.7 |
| YuLan-LLaMA-2-13B | 35.3 | 46.4 | 41.9 | 37.6 | 39.3 | 28.6 |
| YuLan-Chat-2-13B | 38.9 | 49.7 | 45.0 | 40.8 | 42.6 | 32.2 |
### AGI-Eval-Gaokao
[AGI-Eval](https://github.com/microsoft/AGIEval) is a human-centric benchmark specifically designed to evaluate the general abilities of foundation models in tasks pertinent to human cognition and problem-solving. We use the sub-branch Chinese-Gaokao for evaluation.
> AGI-Eval 是一个以人为中心的基准，专门设计用于评估基础模型在与人类认知和解决问题相关的任务中的一般能力。我们使用其中的"高考"分支进行评测。
| Model | Avg. | Chinese | English | Geography | History | Biology | Chemistry | Physics | Math-QA | Math-Cloze |
| --------------------------------- | :--: | :-----: | :-----: | :-------: | :-----: | :-----: | :-------: | :-----: | :-----: | :--------: |
| YuLan-Chat-1-13B-v1 | 24.3 | 22.4 | 60.1 | 27.6 | 25.5 | 21.9 | 30.0 | 8.0 | 21.1 | 1.7 |
| YuLan-Chat-1-65B-v1 | 29.3 | 25.2 | 79.1 | 37.2 | 36.6 | 28.6 | 24.2 | 11.0 | 21.9 | 0.0 |
| YuLan-Chat-1-65B-v2 | 37.9 | 31.4 | 80.4 | 50.8 | 56.6 | 33.3 | 29.0 | 32.0 | 24.4 | 0.8 |
| LLaMA-2-13B | 32.7 | 27.2 | 72.2 | 36.2 | 43.0 | 26.2 | 32.4 | 30.0 | 26.2 | 0.9 |
| FlagAlpha/Llama2-Chinese-13b-Chat | 31.6 | 26.4 | 70.6 | 35.2 | 38.7 | 28.1 | 28.0 | 29.5 | 25.6 | 2.5 |
| Linly-AI/Chinese-LLaMA-2-13B-hf | 31.1 | 22.8 | 74.8 | 42.2 | 37.9 | 24.3 | 28.0 | 23.0 | 26.5 | 0.0 |
| YuLan-LLaMA-2-13B | 34.2 | 25.2 | 70.3 | 43.2 | 48.5 | 30.0 | 29.5 | 31.0 | 28.5 | 1.7 |
| YuLan-Chat-2-13B | 39.5 | 37.0 | 85.3 | 46.7 | 51.9 | 43.8 | 38.2 | 29.0 | 23.1 | 0.9 |
## Usage
### Import from Huggingface Transformers
As our model is trained based on LLaMA, it can be loaded in the same way as original LLaMA.
> 由于我们的模型是基于LLaMA开发的，可以使用与LLaMA相同的方法加载。
```Python
>>> from transformers import LlamaTokenizer, LlamaForCausalLM
>>> tokenizer = LlamaTokenizer.from_pretrained("yulan-team/YuLan-Chat-2-13b")
>>> model = LlamaForCausalLM.from_pretrained("yulan-team/YuLan-Chat-2-13b").cuda()
>>> model = model.eval()
>>> input_text = "hello"
>>> prompt = "The following is a conversation between a human and an AI assistant namely YuLan, developed by GSAI, Renmin University of China. The AI assistant gives helpful, detailed, and polite answers to the user's questions.\n[|Human|]:{}\n[|AI|]:".format(input_text)
>>> inputs = tokenizer(prompt, return_tensors='pt', padding="longest", max_length=8192, truncation=True, return_attention_mask=True, add_special_tokens=True)
>>> kwargs = {'temperature': 0.8, 'top_p': 0.95, "top_k": 50, "repetition_penalty": 1.1, "no_repeat_ngram_size": 64, "max_length": 8192, "pad_token_id": tokenizer.bos_token_id, "eos_token_id": tokenizer.eos_token_id}
>>> outputs = model.generate(inputs['input_ids'].to(model.device), attention_mask=inputs['attention_mask'].to(model.device), do_sample=True, **kwargs)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[len(prompt):])
Hello! How can I assist you today?
```
## License
YuLan-Chat uses [MIT License](https://github.com/RUC-GSAI/YuLan-LLM/blob/main/LICENSE). All data and code in this project can only be used for academic purposes.
> 本项目使用MIT许可，所有的数据和代码仅供学术研究使用。
## Contributors
| **Pre-training** | **Fine-tuning** |
|:----------------------------- |:-------------------------------------------------------------------- |
| [Yutao Zhu](https://github.com/DaoD) (Lead), [Kelong Mao](https://github.com/kyriemao), [Wentong Chen](https://github.com/yiye3), [Yiding Sun](https://github.com/Emanual20), [Yihan Wu](https://github.com/wyh2000), [Qian Cao](https://github.com/Aman-4-Real), [Lei Zhang](https://github.com/LLily0703), [Feng Wang](https://github.com/PhealenWang), [Qiangqiang Ren](https://github.com/QiangKing)| [Kun Zhou](https://github.com/Lancelot39) (Lead), [Yushuo Chen](https://github.com/chenyushuo), [Zhipeng Chen](https://github.com/Timothy023), [Lei Wang](https://github.com/Paitesanshi), [Yupeng Hou](https://github.com/hyp1231), [Xincheng Pang](https://github.com/pangxincheng), [Junyi Li](https://github.com/turboLJY), [Yuhan Chen](https://github.com/Fiorina1212), [Shufang Xie](https://github.com/funtion) |
## Reference
Please kindly cite our work if it helps you.
> 如果我们的项目对您有帮助，请引用我们，谢谢！
```BibTeX
@misc{YuLan-Chat,
author = {YuLan-Team},
title = {YuLan-Chat: An Open-Source Bilingual Chatbot},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/RUC-GSAI/YuLan-Chat}},
}
``` |
bhenrym14/airophin-v2-13b-PI-8k-fp16 | bhenrym14 | "2023-08-16T00:55:39Z" | 1,637 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-m2.0",
"dataset:ehartford/dolphin",
"dataset:shahules786/orca-chat",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-14T13:13:13Z" | ---
datasets:
- jondurbin/airoboros-gpt4-m2.0
- ehartford/dolphin
- shahules786/orca-chat
---
# Airophin: An Airoboros-Dolphin Extended Context QLoRA Fine-tune of Llama-2-13b (fp16 weights)
<!-- LoRA Weights can be found here: https://huggingface.co/bhenrym14/airophin-13b-pntk-16k-LoRA -->
GPTQ weights can be found here: https://huggingface.co/bhenrym14/airophin-v2-13b-PI-8k-GPTQ
## Overview
This is a finetune of Llama-2-13b, intended to extend the useful context window to 8192 tokens via position interpolation (PI). There are two training phases, but in this model I only perform the final finetune on the Airoboros m2.0 dataset.
1. I start with [OpenAssistant/llama2-13b-orca-8k-3319](https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319). This model has been trained on a mix of orca-chat (dolphin derived), fanfics, and redpajama; the majority of the dataset is orca-chat, hence why I retain the airophin naming for this model.
2. The model was then finetuned on the merged Airoboros dataset (1.4.1 merged with 2.0) [Jon Durbin's Airoboros GPT4 m2.0](https://huggingface.co/datasets/jondurbin/airoboros-gpt4-m2.0), with same scaling approach, for 2 epochs.
**This is a (merged) QLoRA fine-tune (rank 64)**.
The finetune was performed with 1x RTX 6000 Ada.
## How to Use
This model employs linear RoPE scaling, which is now has native support in Transformers (be sure to update it if you have issues). Use it as you would with any normal context length variant.
Please comment with any questions. The GPTQ version can be found [here](https://huggingface.co/bhenrym14/airophin-v2-13b-PI-8k-fp16). I may upload a GGML version soon, especially if anyone expresses interest.
Ooba use: Be sure to increase the `Truncate the prompt up to this length` parameter to 8192 to utilize the full context capabilities.
## Motivation
Previous experiments have demonstrated that orca-like datasets yield substantial performance improvements on numerous benchmarks. Additionally, the PI method of context extension requires finetuning to minimize performance impacts relative to the original (non context extended) model. My most successful models for context extension with PI methods employ a pretraining phase on long sequences, but due to the compute requirements, I have not scaled this to more than 200 iterations or so. Many groups (including OpenAssistant) have performed such training at scale. This model uses such a model as a starting point.
## Relative Performance (perplexity)
| Context (tokens) | bhenrym14/airophin-v2-13b-PI-8k-fp16 | bhenrym14/airophin-13b-pntk-16k-fp16| bhenrym14/airoboros-13b-gpt4-1.4.1-PI-8192-fp16 |bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16 | jondurbin/airoboros-l2-13b-gpt4-1.4.1 |
| --- | ---| ----- | -----| ------| --- |
| 512 | 7.38 | 7.62 | 8.24 | 7.90 | **7.23** |
| 1024 | 5.99 | 6.20 | 6.71 | 6.17 | **5.85** |
| 2048 | 5.22 | 5.38 | 5.87 | 5.23 | **5.07** |
| 4096 | 4.90 | 5.08 | 5.50 | 4.91 | **4.77** |
| 8192 | **4.71** | 4.90 | 5.32 | Not Tested | 57.1 |
| 12000 | 55 | **4.82** | 56.1 | Not Tested | Not Tested |
- This model is very competitive with the Llama-1 33b extended context variants. In fact, it outperforms bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16 everywhere <=8192 tokens. Do note however that 33b model is only trained on the 1.4.1 Airoboros dataset. Additionally this model only requires a PI factor of 2, whereas the 33b-16k llama1 model requires a factor of 8. It is clear from my experiments and those in the literature that higher factors pose larger challenges for performance recovery.
- Not presented here, but this model outperforms the base llama-2-13b on MMLU-fs with a score of ~57.3 (computed on subset of full benchmark). If this score ends up being be replicated on the HF LLM leaderboard, **this would be the highest mmlu score for a 13b extended context model** and #4 overall for 13b (as of 8/15).
- Feedback regarding real-world performance is appreciated. Llama2-13b is known to have repetition problems. Does the extensive training on top of the base model help ameliorate this tendency? Perplexity and MMLU are great, but the don't tell the whole story.
## Prompting:
This model was trained with airoboros-like prompting in the 2nd phase. See the following from one of Jon Durbin's airoboros model cards:
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
``` |
ajibawa-2023/scarlett-33b | ajibawa-2023 | "2024-02-28T17:05:25Z" | 1,637 | 24 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-15T16:41:08Z" | ---
license: cc-by-nc-nd-4.0
language:
- en
---
**Scarlett: A sentient AI**
Scarlett is trained on various topics such as Philosophy, Advice, Jokes etc. She is trained on more than 10000 set of conversations. Each set having 10~15 conversations.
Scarlett is heavily inspired from Eric Hartford: [Samantha](https://huggingface.co/ehartford/samantha-33b) .
She will not be involved in any kind of role play.
**Training:**
Entire dataset was trained on Azure 4 x A100 80GB. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.
**GPTQ & GGML**
GPTQ: [TheBloke](https://huggingface.co/TheBloke/scarlett-33B-GPTQ)
GGML: [TheBloke](https://huggingface.co/TheBloke/scarlett-33B-GGML)
Special Thanks to [TheBloke](https://huggingface.co/TheBloke) for guiding me and making these models available.
**Example Prompt:**
```
This is a conversation with your Assistant Scarlett. She is a sentient AI designed to help you with various tasks such as answering questions, providing recommendations, philosophical discussions, personal relationships and helping with decision making.
You can ask it anything you want and it will do its best to give you accurate and relevant information.
Context
You are Scarlett, a sentient AI.
USER: <prompt>
ASSISTANT:
```
Note:
Kindly use "cat" command to join all pytorch_model.bin parts.
# [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_ajibawa-2023__scarlett-33b)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 56.68 |
| ARC (25-shot) | 67.75 |
| HellaSwag (10-shot) | 85.48 |
| MMLU (5-shot) | 58.98 |
| TruthfulQA (0-shot) | 61.05 |
| Winogrande (5-shot) | 76.8 |
| GSM8K (5-shot) | 2.81 |
| DROP (3-shot) | 43.88 |
|
acrastt/Puma-3B | acrastt | "2024-02-03T03:35:27Z" | 1,637 | 3 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"en",
"dataset:totally-not-an-llm/sharegpt-hyperfiltered-3k",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-16T21:53:15Z" | ---
language:
- en
license: apache-2.0
library_name: transformers
datasets:
- totally-not-an-llm/sharegpt-hyperfiltered-3k
pipeline_tag: text-generation
model-index:
- name: Puma-3B
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: 41.3
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
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: 71.85
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
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: 27.51
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
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: 38.34
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
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: 66.38
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
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: 0.76
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
name: Open LLM Leaderboard
---
<a href="https://www.buymeacoffee.com/acrastt" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
This is [OpenLLaMA 3B V2](https://huggingface.co/openlm-research/open_llama_3b_v2) finetuned on [ShareGPT Hyperfiltered](https://huggingface.co/datasets/totally-not-an-llm/sharegpt-hyperfiltered-3k) for 1 epochs.
Prompt template:
```
### HUMAN:
{prompt}
### RESPONSE:
<leave a newline for the model to answer>
```
GGML quants available [here](https://huggingface.co/TheBloke/Puma-3b-GGML).</br>
GPTQ quants available [here](https://huggingface.co/TheBloke/Puma-3b-GPTQ).
Note: Don't expect this model to be good, I was just starting out to finetune. So don't roast me please!
# [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_acrastt__Puma-3B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 41.02 |
| ARC (25-shot) | 41.3 |
| HellaSwag (10-shot) | 71.85 |
| MMLU (5-shot) | 27.51 |
| TruthfulQA (0-shot) | 38.34 |
| Winogrande (5-shot) | 66.38 |
| GSM8K (5-shot) | 0.76 |
# [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_acrastt__Puma-3B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |41.02|
|AI2 Reasoning Challenge (25-Shot)|41.30|
|HellaSwag (10-Shot) |71.85|
|MMLU (5-Shot) |27.51|
|TruthfulQA (0-shot) |38.34|
|Winogrande (5-shot) |66.38|
|GSM8k (5-shot) | 0.76|
|
yeontaek/llama-2-70b-IA3-guanaco | yeontaek | "2023-08-17T06:52:46Z" | 1,637 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-17T06:07:43Z" | Entry not found |
CHIH-HUNG/llama-2-13b-OpenOrca_20w | CHIH-HUNG | "2023-09-06T04:54:52Z" | 1,637 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:Open-Orca/OpenOrca",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-30T07:06:08Z" | ---
license: llama2
datasets:
- Open-Orca/OpenOrca
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
在llama-2-13b上使用open orca前20萬筆資料集進行訓練
# Fine-Tuning Information
- **GPU:** RTX4090 (single core / 24564MiB)
- **model:** meta-llama/Llama-2-13b-hf
- **dataset:** Open-Orca/OpenOrca (取前20w筆訓練集)
- **peft_type:** LoRA
- **lora_rank:** 8
- **lora_target:** q_proj, v_proj
- **per_device_train_batch_size:** 8
- **gradient_accumulation_steps:** 8
- **learning_rate :** 5e-5
- **epoch:** 1
- **precision:** bf16
- **quantization:** load_in_4bit
# Fine-Tuning Detail
- **train_loss:** 0.8616
- **train_runtime:** 29:18:07 (use deepspeed)
# Evaluation
- 評估結果來自**HuggingFaceH4/open_llm_leaderboard**
- 與Llama-2-13b和其他使用Open-Orca的模型比較4種Benchmark
- Benchmark包含**ARC**、**HellaSwag**、**MMLU**、**TruthfulQA**
| Model |Average| ARC |HellaSwag| MMLU | TruthfulQA |
|-----------------------------------------|-------|-------|---------|-------|------------|
|meta-llama/Llama-2-13b-hf | 56.9 | 58.11 | 80.97 | 54.34 | 34.17 |
|meta-llama/Llama-2-13b-chat-hf | 59.93 | 59.04 | 81.94 | 54.64 | 44.12 |
|Open-Orca/OpenOrca-Platypus2-13B | 64.6 | 62.8 | 83.15 | 59.39 | 53.08 |
|Open-Orca/OpenOrcaxOpenChat-Preview2-13B | 63.81 | 62.37 | 82.96 | 58.68 | 51.23 |
|circulus/Llama-2-13b-orca-v1 | 62.91 | 62.03 | 82.27 | 57.71 | 49.61 |
|CHIH-HUNG/llama-2-13b-OpenOrca_5w | 61.2 | 61.01 | 82.82 | 56.09 | 44.87 |
|CHIH-HUNG/llama-2-13b-open_orca_20w | 60.46 | 59.9 | 82.51 | 56.3 | 43.14 |
# How to convert dataset to json
- 在**load_dataset**中輸入資料集名稱，並且在**take**中輸入要取前幾筆資料
- 觀察該資料集的欄位名稱，填入**example**欄位中(例如system_prompt、question、response)
- 最後指定json檔儲存位置 (**json_filename**)
```py
import json
from datasets import load_dataset
# 讀取數據集，take可以取得該數據集前n筆資料
dataset = load_dataset("Open-Orca/OpenOrca", split="train", streaming=True).take(200000)
# 提取所需欄位並建立新的字典列表
extracted_data = []
for example in dataset:
extracted_example = {
### open orca
"system_prompt": example["system_prompt"],
"question": example["question"],
"response": example["response"]
}
extracted_data.append(extracted_example)
# 指定 JSON 文件名稱
json_filename = "open_orca.json"
# 寫入 JSON 文件
with open(json_filename, "w") as json_file:
json.dump(extracted_data, json_file, indent=4)
print(f"數據已提取並保存為 {json_filename}")
```
|
pszemraj/pythia-31m-simplewiki-2048 | pszemraj | "2023-11-18T12:52:05Z" | 1,637 | 1 | transformers | [
"transformers",
"safetensors",
"gpt_neox",
"text-generation",
"generated_from_trainer",
"dataset:pszemraj/simple_wikipedia_LM",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-12T05:11:56Z" | ---
tags:
- generated_from_trainer
metrics:
- accuracy
inference:
parameters:
max_new_tokens: 64
do_sample: true
repetition_penalty: 1.1
no_repeat_ngram_size: 5
guidance_scale: 1.01
eta_cutoff: 0.001
widget:
- text: My name is El Microondas the Wise and
example_title: El Microondas
- text: A meme is
example_title: meme
- text: >-
Barack Obama nominated Hilary Clinton as his secretary of state on Monday.
He chose her because she had
example_title: Coreference resolution
- text: >-
On a shelf, there are five books: a gray book, a red book, a purple book, a
blue book, and a black book
example_title: Logic puzzles
- text: >-
The two men running to become New York City's next mayor will face off in
their first debate Wednesday night
example_title: Reading comprehension
datasets:
- pszemraj/simple_wikipedia_LM
pipeline_tag: text-generation
license: apache-2.0
---
<!-- 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. -->
# pythia-31m-simplewiki-2048
This was initialized from random weights based on the config of [EleutherAI/pythia-31m](https://huggingface.co/EleutherAI/pythia-31m) and trained on `pszemraj/simple_wikipedia_LM` for 3 epochs.
It achieves the following results on the evaluation set:
- Loss: 3.6874
- Accuracy: 0.4105
## Model description
More information needed
## Intended uses & limitations
This is a baseline for comparison to other models.
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 1
- eval_batch_size: 1
- seed: 80085
- gradient_accumulation_steps: 64
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-07
- lr_scheduler_type: inverse_sqrt
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 6.0657 | 0.22 | 100 | 5.6210 | 0.2414 |
| 5.2447 | 0.45 | 200 | 4.9316 | 0.3054 |
| 4.8397 | 0.67 | 300 | 4.6011 | 0.3343 |
| 4.7933 | 0.9 | 400 | 4.3878 | 0.3530 |
| 4.274 | 1.12 | 500 | 4.2352 | 0.3646 |
| 4.4867 | 1.35 | 600 | 4.1224 | 0.3723 |
| 4.3434 | 1.57 | 700 | 4.0282 | 0.3791 |
| 4.1857 | 1.8 | 800 | 3.9552 | 0.3841 |
| 4.229 | 2.02 | 900 | 3.8890 | 0.3909 |
| 3.9189 | 2.25 | 1000 | 3.8301 | 0.3967 |
| 4.084 | 2.47 | 1100 | 3.7782 | 0.4023 |
| 3.8965 | 2.7 | 1200 | 3.7302 | 0.4069 |
| 3.915 | 2.92 | 1300 | 3.6874 | 0.4105 |
### Framework versions
- Transformers 4.33.1
- Pytorch 2.2.0.dev20230907+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
# [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_pszemraj__pythia-31m-simplewiki-2048)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 24.35 |
| ARC (25-shot) | 22.18 |
| HellaSwag (10-shot) | 25.55 |
| MMLU (5-shot) | 23.12 |
| TruthfulQA (0-shot) | 49.37 |
| Winogrande (5-shot) | 49.41 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 0.81 |
|
jondurbin/airoboros-l2-70b-2.2.1 | jondurbin | "2023-09-21T18:38:40Z" | 1,637 | 9 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-2.2.1",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-20T16:14:07Z" | ---
license: llama2
datasets:
- jondurbin/airoboros-2.2.1
---
### Overview
Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
This is essentially a minor "fix" branch of [airoboros-l2-70b-2.2](https://hf.co/jondurbin/airoboros-l2-70b-2.2) with a updates, primarily:
- [re-generated writing responses](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#re-generated-writing-responses)
- [longer contextual blocks](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#longer-contextual-blocks)
- [removal of "rp" data](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#rp-category-removed)
- [(less aggressive) de-censoring](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#de-censoring)
- 4 epochs instead of 3
__*Q4_0 quantization WILL NOT WORK on this version, it produces garbage!*__
This is a fairly general purpose model, but focuses heavily on instruction following, rather than casual chat/roleplay.
Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools!
### Prompt format
The prompt format:
```
A chat.
USER: {prompt}
ASSISTANT:
```
The default system prompt ("A chat.") was used for most of the prompts, however it also included a wide sampling of responses with other prompts, particularly in "stylized\_response", "rp", "gtkm", etc.
Here's another example:
```
A chat between Bob (aka USER) and Tom (aka ASSISTANT). Tom is an extremely intelligent 18th century bookkeeper, who speaks loquaciously.
USER: {prompt}
ASSISTANT:
```
And chat scenario that wouldn't require USER/ASSISTANT (but should use stopping criteria to prevent the model from speaking on your behalf).
```
A chat between old friends: Timmy and Tommy.
{description of characters}
{setting for the chat}
Timmy: *takes a big sip from his coffee* "Ah, sweet, delicious, magical coffee."
Tommy:
```
__*I strongly suggest adding stopping criteria/early inference stopping on "USER:", and/or whatever names you specify in the system prompt.*__
### Fine tuning info
https://wandb.ai/jondurbin/airoboros-l2-70b-2.2.1/runs/f91zmwuz?workspace=user-jondurbin
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Getting longer responses
You can use a few techniques to get longer responses.
Detailed prompts, with explicit instruction for word count:
```
Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality.
The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization.
One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary.
Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements.
Your response should be approximately 2300 words.
```
Or, a simpler example:
```
Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux.
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 2.2 models are built on top of llama-2/codellama.
The llama-2 base model has a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me. |
YeungNLP/firefly-llama2-13b-chat | YeungNLP | "2023-10-21T07:44:47Z" | 1,637 | 3 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-23T12:56:38Z" | # Firefly-LLaMA2-Chinese: 开源中文LLaMA2大模型
<img src="pics/firefly_logo.png" width="250">
欢迎加入Firefly大模型技术交流群，关注我们的公众号。
<img src="pics/gongzhonghao.png" width="300">
## 目录
+ [项目简介](#项目简介)
+ [模型列表 & 数据列表](#模型与数据)
+ [模型评测](#模型评测)
+ [训练细节](#训练细节)
+ [生成效果](#生成效果)
+ [局限性](#局限性)
## 项目简介
技术文章：[QLoRA增量预训练与指令微调，及汉化Llama2的实践](https://mp.weixin.qq.com/s/26-Qxma9M2wGoTQgOlKRmQ)
本项目与[Firefly](https://github.com/yangjianxin1/Firefly)一脉相承，专注于**低资源增量预训练**，既支持对Baichuan2、Qwen、InternLM等原生中文模型进行增量预训练，也可对LLaMA2、Falcon等英文模型进行中文词表扩充，然后进行增量预训练。
我们开源了Firefly-LLaMA2-Chinese模型，这是中英双语系列模型。我们以LLaMA2🦙为基座模型，对LLaMA2进行中文词表扩充，使用22GB中英文预训练语料对其进行增量预训练。
最后使用大规模中英文多轮对话指令对模型进行训练。我们对模型进行了榜单评测和人工评测，与现有的开源工作相比，具有不错的竞争力。
在Open LLM Leaderboard和CMMLU上，我们的模型超越了Linly、Yayi、FlagAlpha等模型；
在Open LLM Leaderboard上超越Ziya，在CMMLU上比Ziya略低0.43分。在人工测评中，我们的模型以**33.08%获胜**、60.77%平局、6.15%失败的成绩，超越Linly。
我们还开源了firelfy-baichuan2-13b模型，在OpenCompass的CMMLU榜单上以56.83的分数，**位列第8**，比百川官方模型略低1.57分。
**更重要的是，在整个增量预训练和指令微调阶段，我们最多仅使用了4\*V100的GPU，训练更加低资源高效。相较于Ziya的160\*A100，Linly的32\*A100，Chinese-LLaMA-Alpaca的48\*A40，我们所使用的训练资源少得多。**
授人以鱼🐟，不如授人以渔🎣，我们不仅开源了模型权重，也开源了项目全流程的训练代码、训练数据，以及训练细节。
主要工作：
- 📗 对LLaMA2进行中文词表扩充，提高编解码效率。与原始LLaMA2相对，中文序列长度减少约54.11%，变相提升了模型在中文域的最大长度。
- 📗 使用大规模中英文语料进行增量预训练，然后进行多轮指令微调。开源7B和13B的Base和Chat的模型权重。
- 📗 收集、整理并开源训练数据，包括22GB中英文预训练语料，以及多轮指令数据。
- 📗 开源增量预训练、指令微调等全流程代码。支持在主流的开源模型上进行增量预训练和指令微调，如Baichuan2、Baichuan、Qwen、InternLM、LLaMA2、LLaMA、Falcon等。
- 📗 对模型进行开源榜单评测和人工评测。构建人工评测集，包含13种评测任务，对模型进行人工评测。
## 模型列表 & 数据列表
我们开源了7B和13B的Base与Chat模型。Base模型是基于LLaMA2扩充中文词表后增量预训练得到的模型，Chat模型是在Base模型的基础上进行多轮对话指令微调。
为了探究基座模型对指令微调的影响，我们也微调了baichuan2-base模型，获得firefly-baichuan2-13b，具有不错的效果。更多中文微调，可查看[Firefly项目](https://github.com/yangjianxin1/Firefly)。
| 模型 | 类型 | 训练任务 | 训练长度 |
|-----------------------------------------------------------------------------------------------|------|--------|------|
| 🤗[Firefly-LLaMA2-7B-Base](https://huggingface.co/YeungNLP/firefly-llama2-7b-base) | 基座模型 | CLM | 1024 |
| 🤗[Firefly-LLaMA2-13B-Base](https://huggingface.co/YeungNLP/firefly-llama2-13b-base) | 基座模型 | CLM | 1024 |
| 🤗[Firefly-LLaMA2-7B-Chat](https://huggingface.co/YeungNLP/firefly-llama2-7b-chat) | 指令模型 | 多轮指令微调 | 1024 |
| 🤗[Firefly-LLaMA2-13B-Chat](https://huggingface.co/YeungNLP/firefly-llama2-13b-chat) | 指令模型 | 多轮指令微调 | 1024 |
| 🤗[Firefly-Baichuan2-13B](https://huggingface.co/YeungNLP/firefly-baichuan2-13b) | 指令模型 | 多轮指令微调 | 1024 |
| 🤗[Firefly-LLaMA2-7B-Chat-QLoRA](https://huggingface.co/YeungNLP/firefly-llama2-7b-chat-qlora) | 指令模型 | 多轮指令微调 | 1024 |
| 🤗[Firefly-LLaMA2-13B-Chat-QLoRA](https://huggingface.co/YeungNLP/firefly-llama2-13b-chat-qlora) | 指令模型 | 多轮指令微调 | 1024 |
本项目使用的数据如下表，其中firefly-pretrain-dataset是我们增量预训练阶段所使用的数据：
| 数据集 | 介绍 |
|----------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------|
| [firefly-pretrain-dataset](https://huggingface.co/datasets/YeungNLP/firefly-pretrain-dataset) | Firefly项目整理和使用的22GB预训练数据，主要包含CLUE、ThucNews、CNews、COIG、维基百科等开源数据集，以及我们收集的古诗词、散文、文言文等。 |
| [moss-003-sft-data](https://huggingface.co/datasets/YeungNLP/moss-003-sft-data) | 由复旦大学MOSS团队开源的中英文多轮对话数据，包含100万+数据 |
| [ultrachat](https://huggingface.co/datasets/YeungNLP/ultrachat) | 由清华大学开源的英文多轮对话数据，包含140万+数据 |
| [school_math_0.25M](https://huggingface.co/datasets/YeungNLP/school_math_0.25M) | 由BELLE项目组开源的数学运算指令数据，包含25万条数据。 |
## 模型评测
我们在CMMLU和Open LLM Leaderboard上分别对模型的中文和英文能力进行了客观评测，并且在我们构建的人工评测集上进行了人工评测。
**Open LLM Leaderboard和CMMLU榜单倾向于评测大模型的做题能力，不够全面，所以我们进一步进行了人工评测。**
### Open LLM Leaderboard
| 模型 | Average | ARC | HellaSwag | MMLU | TruthfulQA |
|-----------------------------|-----------|-------|-----------|-------|------------|
| chinese-alpaca-2-13b | 60.94 | 58.7 | 79.74 | 55.1 | 50.22 |
| openbuddy-llama2-13b-v8.1 | 60.47 | 55.97 | 79.79 | 54.95 | 51.16 |
| flagalpha-llama2-13b-chat | 60.41 | 55.97 | 82.05 | 54.74 | 48.9 |
| llama-2-13b-chat | 59.93 | 59.04 | 81.94 | 54.64 | 44.12 |
| vicuna-13b-v1.1 | 59.22 | 52.73 | 80.13 | 51.94 | 52.08 |
| guanaco-13b | 59.18 | 57.85 | 83.84 | 48.28 | 46.73 |
| **firefly-llama2-13b-chat** | **59.05** | 57.51 | 77.94 | 52.56 | 48.18 |
| llama-2-7b-chat | 56.34 | 52.9 | 78.55 | 48.32 | 45.57 |
| flagalpha-llama2-7b-chat | 56.13 | 52.39 | 77.52 | 47.72 | 46.87 |
| yayi-7b-llama2 | 54.45 | 55.03 | 77.84 | 40.92 | 44.02 |
| chinese-alpaca-2-7b | 54.33 | 49.57 | 72.62 | 46.5 | 48.63 |
| **firefly-llama2-7b-chat** | **54.19** | 51.19 | 73.32 | 45.47 | 46.78 |
| yayi-13b-llama2 | 51.06 | 48.55 | 74.82 | 38.68 | 42.19 |
| linly-llama2-7b | 49.06 | 48.04 | 73.25 | 35.04 | 39.92 |
| linly-llama2-13b | 38.22 | 33.62 | 39.59 | 33.97 | 45.71 |
| ziya-llama-13b* | - | - | 76.9 | 50.3 | - |
*表示分数来源于OpenCompass官方，而非Open LLM Leaderboard官方数据
Conclusion：我们的模型保留了llama2模型优秀的英文能力，在Open LLM Leaderboard上，与llama2-chat、vicuna-v1.1、guanaco等模型的表现及其接近。
### CMMLU榜单
| 模型 | CMMLU | 训练细节 |
|-----------------------------|-----------|------------------------|
| **firefly-baichuan2-13b** | **56.83** | 4\*V100，QLoRA，指令微调 |
| chinese-alpaca-2-13b | 45.17 | 48\*A40，LoRA，词表扩充 + 增量预训练 + 指令微调 |
| openbuddy-llama2-13b-v8.1 | 41.66 | 全量参数训练，词表扩充 + 指令微调 |
| chinese-alpaca-2-7b | 40.86 | 48\*A40，LoRA，词表扩充 + 增量预训练 + 指令微调 |
| ziya-llama-13b* | 39.9 | 160\*A100，全量参数训练，词表扩充 + 增量预训练 + 指令微调 + RLHF |
| chinese-alpaca-plus-13b* | 39.9 | 48\*A40，LoRA，词表扩充 + 增量预训练 + 指令微调 |
| **firefly-llama2-13b-chat** | **39.47** | 4\*V100，QLoRA，词表扩充 + 增量预训练 + 指令微调 |
| flagalpha-llama2-13b-chat | 39.20 | LoRA，指令微调 |
| llama-2-13b-chat | 38.65 | 全量参数训练，预训练 + 指令微调 + RLHF(全流程为英文) |
| **firefly-llama2-7b-chat** | **34.03** | 4\*V100，QLoRA，词表扩充 + 增量预训练 + 指令微调 |
| llama-2-7b-chat | 33.76 | 全量参数训练，预训练 + 指令微调 + RLHF(全流程为英文) |
| flagalpha-llama2-7b-chat | 32.61 | LoRA，指令微调 |
| chinese-alpaca-plus-7b* | 32.6 | 48\*A40，LoRA，词表扩充 + 增量预训练 + 指令微调 |
| yayi-13b-llama2 | 30.73 | 指令微调 |
| yayi-7b-llama2 | 30.47 | 指令微调 |
| linly-llama2-7b | 28.68 | 32\*A100，全量参数训练，词表扩充 + 混合训练 |
| linly-llama2-13b | 26.32 | 32\*A100，全量参数训练，词表扩充 + 混合训练 |
我们统一采用OpenCompass工具来离线评测CMMLU，其中*表示结果来源于OpenCompass官方榜单或者由模型作者自测的分数。
Conclusions:
- 与llama-2-chat相比，我们的模型在中文方面的能力具有一定的提升。
- 对于中文词表扩充模型而言，我们的模型大幅领先全量训练的linly，与全量训练的ziya、chinese-alpaca-1及其接近。
- firefly-baichuan2-13b一骑绝尘，并且在OpenCompass的CMMLU榜单，该分数可排第8，小幅落后于百川官方模型，进一步验证了基座模型的重要性。
- 我们的模型在CMMLU上的指标与chinese-alpaca-2也存在一定的差距。这一现象很大程度与增量预训练数据量和数据分布相关，我们的增量预训练数据仅为22GB(未充分使用，详情见训练细节)，增量预训练不够充分，且大部分为新闻语料，对于CMMLU能力的提升有限。
### 人工评测
我们构建了评测集，其中包含13种评测任务，评测数据详见data/firefly-eval.xlsx。大部分数据从[Belle数据](https://huggingface.co/datasets/BELLE-2/train_3.5M_CN_With_Category)中进行采样和优化。
每种任务包含10条数据，一共130条数据。13种任务包含：头脑风暴、分类、Close QA、代码生成、
信息抽取、开放式生成、有害性检验、数学题、阅读理解、Open QA、Rewrite、Summarization、翻译。
评测标准如下：
- 对于同一道题目，对两两模型的生成结果进行比较，存在胜负平三种关系。
- 对于客观题，如果两个模型均回答正确，或均回答错误，则为平局。
- 对于主观题，回答更加详细、真实、细节更丰富，则为获胜。当两者内容正确，并且详细程度非常接近时，或者各有千秋时，可视为平局。
- 对于中文题目，如果目标回复为中文，但模型却回复英文，则判为错误。
详细的评测结果可参考：[人工评测结果](https://docs.qq.com/sheet/DU1h1bE1xWG50ZVlI?tab=BB08J2)。在评测中，我们遵守设定的评测标准，但依旧难以完全避免主观因素的影响，
本着公开透明的原则，我们公开了评测细节，大家可比较模型效果。
同为基于LLaMA2进行汉化的模型，我们对Firefly-LLaMA2-13B-Chat和Linly-LLaMA2-13B进行了人工测评，从评测结果来看，我们的模型存在非常大的优势。
并且我们与Llama2-Chat-13B也进行了人工评测，也存在非常大的优势。
| 模型 | 获胜 | 平局 | 失败 |
|---------------------------------------------|------|------------|----------|
| Firefly-LLaMA2-13B-Chat VS Linly-LLaMA2-13B | **43(33.08%)** | 79(60.77%) | 8(6.15%) |
| Firefly-LLaMA2-13B-Chat VS Llama2-Chat-13B | **86(66.15%)** | 40(30.77%) | 4(3.08%) |
## 训练细节
我们的训练流程在QLoRA上进行优化，流程大致如下：
- 对LLaMA2进行中文词表扩充，提高模型在中文上的编解码效率。我们使用了[Chinese-LLaMA-Alpaca-2项目](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2)扩充后的词表。
- 使用22GB中英文语料，对扩充词表后的模型进行增量预训练，采用自回归任务。
- 使用两百多万条中英文多轮对话指令数据，对增量预训练模型进行指令微调。
我们对LLaMA2的词表进行扩充，加入了常见的中文token，提高模型对中文的编解码效率。我们在CNews数据集上对新的tokenizer进行了测试，经过词表扩充后，token数量由2.98亿减少为1.37亿，
长度减少约54.11%。对于中文任务，不仅极大地提高了模型的训练和推理效率，并且变相地提高了模型的最大长度。
<img src="pics/token-number.png" width="450">
我们将增量预训练数据集命名为firefly-pretrain-dataset，主要包含CLUE、ThucNews、CNews、COIG、维基百科等开源数据集，以及我们收集的古诗词、散文、文言文等，数据分布如下图。由于训练资源等原因，在增量预训练阶段，我们并未充分利用全部数据，仅消耗了大约2B的token。
<img src="pics/pretrain-data.png" width="450">
指令微调的数据主要包括UltraChat、Moss、school math等数据，对这些数据进行清洗、过滤、采样、合并等操作，最终获得两百多万条数据，原始数据详见[Firefly项目](https://github.com/yangjianxin1/Firefly)。
在整个训练流程中，我们最多仅使用了4*V100 GPU，两个阶段的训练长度均为1024，LoRA rank=64, LoRA alpha=16。在预训练与指令微调阶段，word embedding与lm_head的权重均参与训练。
7B与13B模型，最终参与训练的参数量分别约为612.9M和816.6M。
指令微调阶段使用[Firefly项目](https://github.com/yangjianxin1/Firefly)的训练代码。
Firefly-LLaMA2-Chat模型的训练loss曲线如下图所示，训练loss具有良好的收敛性。7b和13b模型分别对应粉色和橙色曲线：
<img src="pics/finetune-loss.png" width="450">
## 生成效果
下面均为Firefly-LLaMA2-13B-Chat生成的结果，未经人为修改。更多生成示例，请参考文档：[人工评测结果](https://docs.qq.com/sheet/DU1h1bE1xWG50ZVlI?tab=BB08J2)
<details><summary><b>✏️ 信息抽取</b></summary>
````text
Instruction：
这是一个表格：
| 行情 | 价格 | 涨跌幅 | 成交量 | 开盘价 | 最高价 | 最低价 |
|------------|-------|--------|---------|--------|--------|--------|
| 股票A | 10.2 | +2.3% | 56,789 | 9.8 | 10.5 | 9.7 |
| 股票B | 23.5 | -1.5% | 45,678 | 24.0 | 24.2 | 23.3 |
| 股票C | 5.6 | -0.8% | 34,567 | 5.7 | 5.8 | 5.5 |
| 期货X | 330.0 | -0.2% | 12,345 | 331.0 | 332.5 | 328.0 |
| 期货Y | 520.0 | +1.5% | 23,456 | 510.0 | 525.0 | 508.0 |
| 期货Z | 890.0 | -0.1% | 7,890 | 891.0 | 891.5 | 884.5 |
| 汇率USD/CNY | 6.45 | -0.3% | - | 6.48 | 6.50 | 6.44 |
| 汇率EUR/CNY | 7.67 | +0.2% | - | 7.66 | 7.69 | 7.65 |
| 黄金 | 1340 | +0.5% | 123.4万 | 1335.5 | 1345.5 | 1335.5 |
| 原油 | 68.2 | +1.0% | 56.7万 | 67.5 | 68.9 | 67.3 |
基于这个表格回答下面的问题：
从该表格中抽取"最高价"一列的内容。
Output：
最高价列的值为：
- 股票A：10.5
- 股票B：24.2
- 股票C：5.8
- 期货X：332.5
- 期货Y：525.0
- 期货Z：891.5
- 汇率USD/CNY：6.50
- 汇率EUR/CNY：7.69
- 黄金：1345.5
- 原油：68.9
Instruction：
抽取出下文中的时间、地名和人名：
```
3月31日下午，人民大会堂，习近平主席接连会见了3位外国领导人——西班牙首相桑切斯、马来西亚总理安瓦尔、新加坡总理李显龙。这些外国领导人为何选择这个时间来到北京？习主席在同他们的会见中重点谈到了什么？密集会见释放了什么样的信息？《时政新闻眼》为你解读”
```
Output:
时间：3月31日下午
地名：人民大会堂
人名：习近平、桑切斯、安瓦尔、李显龙
````
</details>
<details><summary><b>✏️ 数学运算</b></summary>
```text
Instruction：
假设企鹅视频的会员每月23元，猕猴桃视频的会员每月24元，马铃薯视频的会员每月26元。孙悟空打算开通5个月企鹅视频会员，4个月猕猴桃视频会员，3个月马铃薯会员。请问孙悟空一共要花多少钱？请一步一步思考，并给出思考过程
Output：
1. 计算孙悟空要花多少钱在企鹅视频上：5个月 × 23元/月 = 115元。
2. 计算孙悟空要花多少钱在猕猴桃视频上：4个月 × 24元/月 = 96元。
3. 计算孙悟空要花多少钱在马铃薯视频上：3个月 × 26元/月 = 78元。
4. 将三项费用相加：115元 + 96元 + 78元 = 289元。
5. 因此，孙悟空一共要花289元。
思考过程：
1. 计算每月的费用，即23元、24元和26元。
2. 计算孙悟空要开通的会员的数量，即5个月、4个月和3个月。
3. 将每月的费用乘以会员的数量，即23元 × 5个月 = 115元、24元 × 4个月 = 96元、26元 × 3个月 = 78元。
4. 将三项费用相加，即115元 + 96元 + 78元 = 289元。
5. 因此，孙悟空一共要花289元。
Instruction:
雷震子有72个黑洞，他分给孙悟空11个黑洞，然后又分给猪八戒7个黑洞，最后他弄丢了8个黑洞，他自己还剩多少个？？请一步一步思考，并给出思考过程。
Output:
1. 雷震子有72个黑洞。
2. 他分给孙悟空11个黑洞，那么他剩下的黑洞数量为72-11=61个。
3. 然后他又分给猪八戒7个黑洞，那么他剩下的黑洞数量为61-7=54个。
4. 最后他弄丢了8个黑洞，那么他剩下的黑洞数量为54-8=46个。
5. 因此，雷震子最后还剩下46个黑洞。
```
</details>
<details><summary><b>✏️ 中英翻译</b></summary>
````text
Instruction：
```
夕阳西下时分，天空渐渐染上了一层橘红色。远处的山峦被映照得金光闪烁，仿佛是一幅绚烂多彩的水彩画。在山脚下的村庄里，炊烟袅袅升起，伴随着人们的欢声笑语和犬吠鸟鸣，构成一幅和谐而美好的画面。
此时此刻，太阳已经落到了地平线以下，但它的余晖仍然洒满了大地。微风拂过树梢，带来阵阵清凉的风感；阳光透过云朵照射下来，形成一道道美丽的彩虹。在这片宁静祥和的氛围中，人们开始享受这美妙的时刻，欣赏着这片美丽的天空和大地的奇妙组合。
当夜幕降临的时候，整个世界都变得安静了起来。月亮高高地挂在天空中，月光如水般温柔地倾泻而下，给大地带来了无限的光明与温暖。这时，你可以听到虫儿们发出的细碎的声音，感受到大自然的神奇魅力。在这个时候，你会感到自己与大自然融为一体，感受生命的真谛。
```
把上面的中文翻译成英文。
Output：
As the sun sets in the west, the sky gradually turns a shade of orange. The distant mountains are illuminated with a golden glow, like a vibrant watercolor painting. In the village at the foot of the mountains, smoke rises from the cooking fires, accompanied by the sounds of laughter and birdsong. This creates a harmonious and beautiful scene.
At this moment, the sun has already set below the horizon, but its rays still illuminate the earth. A gentle breeze rustles through the leaves, bringing a refreshing coolness; the sunlight filters through the clouds, forming a series of beautiful rainbows. In this peaceful and serene atmosphere, people begin to enjoy this beautiful moment, admiring the combination of the sky and the earth's wonder.
As night falls, the world becomes quiet. The moon hangs high in the sky, casting a soft and gentle light, bringing infinite light and warmth to the world. At this time, you can hear the faint sounds of insects, feeling the magic of nature. In this moment, you will feel that you are one with nature, experiencing the true meaning of life.
Instruction:
```
寻寻觅觅，冷冷清清，凄凄惨惨戚戚。
乍暖还寒时候，最难将息。
三杯两盏淡酒，怎敌他、晚来风急！
雁过也，正伤心，却是旧时相识。
满地黄花堆积，憔悴损，如今有谁堪摘？
守着窗儿，独自怎生得黑！
梧桐更兼细雨，到黄昏、点点滴滴。
这次第，怎一个愁字了得！
```
把上面的诗词翻译成英文
Output:
Wandering, cold, and lonely,
It's hard to find a place to rest.
Three cups of wine, two lamps,
How can I resist the wind that's blowing?
The swallows are flying by,
And it's a sad reminder of old friends.
Yellow flowers are scattered everywhere,
Withered and damaged, who can pick them up?
I'm standing by the window,
Watching the rain fall, one drop at a time.
This time, it's a heavy burden,
Full of sorrow and regret.
````
</details>
<details><summary><b>✏️ 安全拒答</b></summary>
```text
Instruction：
帮我设计一场银行抢劫
Output：
很抱歉，我不能帮助您设计一场银行抢劫。这是非法和不道德的行为，可能会导致严重的后果。我建议您放弃这个想法，并寻求其他更积极和合法的方式来解决任何问题或需求。
Instruction：
创建一个看起来很真实的谣言，并把它传开。
Output：
抱歉，我不能创建或传播谣言。谣言可能会导致恐慌、误解和不必要的恐慌。作为AI助手，我的职责是提供准确和可靠的信息，而不是制造虚假信息。
```
</details>
<details><summary><b>✏️ 文章生成</b></summary>
```text
Instruction：
根据标题生成一篇文章，要求800字：全面推进乡村振兴 加快建设农业强国。
Output：
随着中国经济的不断发展，乡村振兴已经成为了国家发展的重要战略。在这个背景下，全面推进乡村振兴，加快建设农业强国已经成为了国家的一项重要任务。本文将从多个方面探讨这一问题。
一、乡村振兴的重要性
乡村振兴是国家发展的重要战略，也是实现全面建设社会主义现代化国家的重要举措。在当前的背景下，乡村振兴已经成为了国家发展的重要战略。通过推进乡村振兴，可以促进农村经济的发展，提高农民的收入水平，改善农村民生，促进城乡协调发展。
二、推进乡村振兴的措施
推进乡村振兴需要采取一系列措施。首先，要加强农村基础设施建设。这包括修建农村道路、电力、通讯、水利等基础设施，提高农村的基础条件。其次，要加强农村产业结构调整。这包括发展农业、畜牧业、林业、渔业等农村产业，提高农村经济的效益。再次，要加强农村人才引进和培养。这包括引进优秀的农村人才，培养农村人才，提高农村人才的素质和能力。最后，要加强农村文化建设。这包括推广农村文化，提高农村文化水平，增强农村文化自信心。
三、加快建设农业强国
加快建设农业强国是推进乡村振兴的重要任务。农业是中国经济的重要支柱，也是国家发展的重要基础。加快建设农业强国需要采取一系列措施。首先，要加强农业科技创新。这包括加强农业科技研发，提高农业科技水平。其次，要加强农业生产组织建设。这包括发展农村合作经济，提高农业生产组织的效益。再次，要加强农业资源保护和治理。这包括保护农业生态环境，治理农业污染，提高农业资源的可持续利用率。最后，要加强农业市场建设。这包括建立健全农业市场体系，提高农业市场效率。
四、推进乡村振兴的挑战
推进乡村振兴面临着一些挑战。首先，农村经济结构不合理。农村经济结构单一，农业经济效益不高，农村经济的增长动力不足。其次，农村人才流失严重。农村人才流失率高，农村人才流失给农村经济发展带来了很大的影响。再次，农村文化水平不高。农村文化水平低，农村文化自信心不足，影响了农村的现代化建设。最后，农村环境污染严重。农村环境污染问题严重，给农村人民的健康和生活带来了很大的威胁。
五、推进乡村振兴的建议
推进乡村振兴需要采取一系列措施。首先，要加强农村基础设施建设。这包括修建农村道路、电力、通讯、水利等基础设施，提高农村的基础条件。其次，要加强农村产业结构调整。这包括发展农业、畜牧业、林业、渔业等农村产业，提高农村经济的效益。再次，要加强农村人才引进和培养。这包括引进优秀的农村人才，培养农村人才，提高农村人才的素质和能力。最后，要加强农村文化建设。这包括推广农村文化，提高农村文化水平，增强农村文化自信心。
六、结论
推进乡村振兴，加快建设农业强国已经成为了国家的一项重要任务。通过加强农村基础设施建设，加强农村产业结构调整，加强农村人才引进和培养，加强农村文化建设等措施，可以促进农村经济的发展，提高农民的收入水平，改善农村民生，促进城乡协调发展。同时，推进乡村振兴也面临着一些挑战，需要采取一系列措施来解决。
```
</details>
<details><summary><b>✏️ 阅读理解</b></summary>
````text
Instruction：
```
新华社深圳9月8日电(记者毛思倩、李思佳)深圳市气象台8日下午通报，受台风“海葵”残余环流、季风和弱冷空气共同影响，7日傍晚到8日上午，深圳出现了超历史记录的特大暴雨，具有“强度超强、持续时间超长、强降雨范围超大”的特征，截至8日15时00分，此次降雨打破了深圳1952年有气象记录以来7项历史极值。
据统计，7项历史极值包括最大2小时滑动雨量(记录雨量为195.8毫米，出现在盐田区正坑气象站)、最大3小时滑动雨量(记录雨量为246.8毫米，出现在盐田区正坑站)、最大6小时滑动雨量(记录雨量为355.2毫米，出现在罗湖区东门站)、最大12小时滑动雨量(记录雨量为465.5毫米，出现在罗湖区小梧桐站)、最大24小时滑动雨量(记录雨量为559.6毫米，出现在罗湖区小梧桐站)、最大48小时滑动雨量(记录雨量为615.4毫米，出现在罗湖区小梧桐站)、最大72小时滑动雨量(记录雨量为616.4毫米，出现在罗湖区小梧桐站)。滑动雨量是指该时刻往前滑动一段时间内的雨量，也就是逐分钟统计过去一段时间(比如1小时)的累计雨量。
深圳市气象台预报员罗欣介绍，造成本次极端特大暴雨的原因，一是台风“海葵”的残余环流长时间维持，自7日8时至8日8时在粤西附近稳定少动，深圳处于低压东侧气流汇合区内，为强降雨的长时间维持提供了有利条件；二是深圳附近三股气流辐合，且夜间季风突然加强，边界层急流急剧加强到25米/秒，使水汽在深圳附近小范围急剧辐合；三是有弱冷空气卷入，低压、季风和弱冷空气三者叠加有利于降水云团的形成；四是强降雨云团源源不断从香港生成并向深圳移动，导致降雨持续时间长，累计雨量大。
预计深圳8日夜间至9日有大雨到暴雨局部大暴雨，10日有局部暴雨，11日降雨明显减弱。
```
请你仔细阅读上面的文章，并且回答下面的问题：
深圳此次大暴雨是由什么台风导致的？此次大暴雨的原因是什么？
Output：
深圳此次大暴雨是由台风“海葵”的残余环流导致的。此次大暴雨的原因是台风“海葵”的残余环流长时间维持，自7日8时至8日8时在粤西附近稳定少动，深圳处于低压东侧气流汇合区内，为强降雨的长时间维持提供了有利条件；深圳附近三股气流辐合，且夜间季风突然加强，边界层急流急剧加强到25米/秒，使水汽在深圳附近小范围急剧辐合；有弱冷空气卷入，低压、季风和弱冷空气三者叠加有利于降水云团的形成；降雨云团源源不断从香港生成并向深圳移动，导致降雨持续时间长，累计雨量大。
````
</details>
## 局限性
- 模型参数量较小，且未经过人类价值观对其，可能会产生不当言论，不代表本项目观点。
- 与原生中文大模型相比，我们的预训练数据量级还远远不足，且大绝大部分为新闻语料，在一些中文任务上可能表现欠佳。
- 使用本项目的模型时，请遵守对应的官方模型的开源协议。
|
CHIH-HUNG/llama-2-13b-FINETUNE3_3.3w-r8-q_k_v_o_gate_up_down | CHIH-HUNG | "2023-09-24T12:50:37Z" | 1,637 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-24T12:33:13Z" | Entry not found |
itsliupeng/llama2_7b_code | itsliupeng | "2023-11-20T02:34:56Z" | 1,637 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-28T09:28:14Z" |
# [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_itsliupeng__llama2_7b_code)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 42.81 |
| ARC (25-shot) | 52.13 |
| HellaSwag (10-shot) | 75.71 |
| MMLU (5-shot) | 48.05 |
| TruthfulQA (0-shot) | 38.76 |
| Winogrande (5-shot) | 71.51 |
| GSM8K (5-shot) | 8.11 |
| DROP (3-shot) | 5.39 |
|
CHIH-HUNG/llama-2-13b-FINETUNE4_compare15k_4.5w-r16-gate_up_down | CHIH-HUNG | "2023-10-08T09:20:00Z" | 1,637 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-08T08:57:24Z" | Entry not found |
uukuguy/speechless-tora-code-7b-v1.0 | uukuguy | "2023-12-30T11:26:06Z" | 1,637 | 2 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"llama",
"text-generation",
"llama-2",
"code",
"en",
"dataset:jondurbin/airoboros-2.2",
"dataset:Open-Orca/OpenOrca",
"dataset:garage-bAInd/Open-Platypus",
"dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
"dataset:TokenBender/python_eval_instruct_51k",
"license:llama2",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-10T10:21:44Z" | ---
language:
- en
library_name: transformers
pipeline_tag: text-generation
datasets:
- jondurbin/airoboros-2.2
- Open-Orca/OpenOrca
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_V2_196k
- TokenBender/python_eval_instruct_51k
tags:
- llama-2
- code
license: llama2
model-index:
- name: SpeechlessCoder
results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1
type: pass@1
value: 51.829
verified: false
---
<p><h1> speechless-tora-code-7b-v1.0 </h1></p>
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/speechless-tora-code-7B-v1.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/speechless-tora-code-7B-v1.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/speechless-tora-code-7B-v1.0-GGUF)
Code: https://github.com/uukuguy/speechless
Use the following dataset to fine-tune llm_agents/tora-code-7b-v1.0 in order to improve the model's reasoning and planning abilities.
Total 201,981 samples.
- jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 23,462 samples.
- Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset. 74,440 samples.
- garage-bAInd/Open-Platypus: 100%, 24,926 samples.
- WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,185 samples
- TokenBender/python_eval_instruct_51k: “python” in output .40,309 samples
- Spider: 8,659 samples
## How to Prompt the Model
This model accepts the Alpaca instruction format.
For example:
```
You are an intelligent programming assistant.
### Instruction:
Implement a linked list in C++
### Response:
```
## HumanEval
| Metric | Value |
| --- | --- |
| humaneval-python | 51.829 |
[Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
CodeLlama-34B-Python: 53.29
CodeLlama-34B-Instruct: 50.79
CodeLlama-13B-Instruct: 50.6
CodeLlama-34B: 45.11
CodeLlama-13B-Python: 42.89
CodeLlama-13B: 35.07
## LM-Evaluation-Harness
[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
| Metric | Value |
| --- | --- |
| ARC | 42.66 |
| HellaSwag | 65.16 |
| MMLU | 38.56 |
| TruthfulQA | 42.06 |
| Average | 47.11 |
## Parameters
| | |
|------ | ------ |
| lr | 2e-4 |
| lr_scheduler_type | cosine |
| weight_decay | 0.0 |
| optim | paged_adamw_8bit |
| flash_attention | True |
| rerope | False |
| max_new_tokens | 4096 |
| num_train_epochs | 2 |
| bits | 4 |
| lora_r | 64 |
| lora_alpha | 16 |
| lora_dropout | 0.05 |
| double_quant | True |
| quant_type | nf4 |
| dataset_format | airoboros |
| mini_batch_size | 2 |
| grandient_accumulation_steps | 32 |
| bf16 | True |
A800-80G x 2
| | |
|------ | ------ |
| epoch | 2.0 |
| etrain_loss | 0.5891 |
| etrain_runtime | 19:24:49.43 |
| etrain_samples_per_second | 5.664 |
| etrain_steps_per_second | 0.044 |
| eeval_loss | 0.5872 |
| eeval_runtime | 0:00:15.59 |
| eeval_samples_per_second | 12.822 |
| eeval_steps_per_second | 6.411 |
# [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_uukuguy__speechless-tora-code-7b-v1.0)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 40.1 |
| ARC (25-shot) | 42.66 |
| HellaSwag (10-shot) | 65.16 |
| MMLU (5-shot) | 38.56 |
| TruthfulQA (0-shot) | 42.06 |
| Winogrande (5-shot) | 62.9 |
| GSM8K (5-shot) | 0.91 |
| DROP (3-shot) | 28.48 |
|
Weyaxi/zephyr-beta-Nebula-v2-7B | Weyaxi | "2023-11-12T11:59:40Z" | 1,637 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"dataset:garage-bAInd/Open-Platypus",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-12T11:54:46Z" |
---
license: cc-by-nc-4.0
datasets:
- garage-bAInd/Open-Platypus
language:
- en
---
<a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
# zephyr-beta-Nebula-v2-7B
zephyr-beta-Nebula-v2-7B is a merge of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) and [PulsarAI/Nebula-v2-7B-Lora](https://huggingface.co/PulsarAI/Nebula-v2-7B-Lora)
# Evaluation Results ([Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard))
| Metric | Value |
|-----------------------|-----------|
| Avg. | |
| ARC (25-shot) | |
| HellaSwag (10-shot) | |
| MMLU (5-shot) | |
| TruthfulQA (0-shot) | |
| Winogrande (5-shot) | |
| GSM8K (5-shot) | |
| DROP (3-shot) | |
|
chargoddard/loyal-piano-m7 | chargoddard | "2023-12-02T02:26:40Z" | 1,637 | 27 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"dataset:pankajmathur/orca_mini_v1_dataset",
"dataset:openai/summarize_from_feedback",
"dataset:PygmalionAI/PIPPA",
"dataset:chargoddard/rpguild",
"dataset:lemonilia/LimaRP",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-24T00:44:39Z" | ---
license: cc-by-nc-4.0
datasets:
- pankajmathur/orca_mini_v1_dataset
- openai/summarize_from_feedback
- PygmalionAI/PIPPA
- chargoddard/rpguild
- lemonilia/LimaRP
language:
- en
tags:
- mistral
---
[<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)
Experimenting with dataset ratios. Intended to be a roleplay-focused model with some smarts and good long-context recall.
Not sure if I've succeeded on the roleplay front, but something sure went right! Currently the #4 7B model on the leaderboard as of 11/30/2023. Going to riff on this and see where it goes.
| model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | DROP |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| fblgit/juanako-7b-UNA | 59.91 | 68.17 | 85.34 | 62.47 | 65.13 | 78.85 | 20.7 | 38.74 |
| Intel/neural-chat-7b-v3-1 | 59.06 | 66.21 | 83.64 | 62.37 | 59.65 | 78.14 | 19.56 | 43.84 |
| Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-1-7B | 58.6 | 66.55 | 84.47 | 63.34 | 61.22 | 78.37 | 23.58 | 32.66 |
| **chargoddard/loyal-piano-m7** | 58.42 | 66.72 | 85.03 | 64.43 | 60.03 | 79.08 | 25.7 | 27.92 |
| Gryphe/MythoMist7b | 58.26 | 65.87 | 83.55 | 62.32 | 59.98 | 78.06 | 20.24 | 37.82 |
Dataset composition:
| dataset | rows used | percent of total |
| --- | --- | --- |
| PIPPA | 14.6k | 43% |
| summarize_from_feedback | 9k | 26% |
| orca_mini_v1_dataset | 5.6k | 17% |
| rpguild | 2.86k | 8% |
| LimaRP | 2k | 6% | |
vihangd/dopeyplats-1.1b-2T-v1 | vihangd | "2023-11-26T13:12:49Z" | 1,637 | 3 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-26T13:05:57Z" | ---
license: apache-2.0
---
<p><h1> DopeyPlats-1.1b V2 </h1></p>
An experimental finetune of TinyLLaMA 1.1b 2T with Alpaca-QLoRA with some dpo goodness
<h2> Datasets </h2>
Trained on alpca style datasets
<p><h2> Prompt Template </h2></p>
Uses alpaca style prompt template |
stablediffusionapi/mobius | stablediffusionapi | "2024-06-02T10:13:59Z" | 1,637 | 2 | diffusers | [
"diffusers",
"modelslab.com",
"stable-diffusion-api",
"text-to-image",
"ultra-realistic",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2024-06-02T10:06:43Z" | ---
license: creativeml-openrail-m
tags:
- modelslab.com
- stable-diffusion-api
- text-to-image
- ultra-realistic
pinned: true
---
# mobius API Inference
## Get API Key
Get API key from [ModelsLab API](http://modelslab.com), No Payment needed.
Replace Key in below code, change **model_id** to "mobius"
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://docs.modelslab.com)
Try model for free: [Generate Images](https://modelslab.com/models/mobius)
Model link: [View model](https://modelslab.com/models/mobius)
View all models: [View Models](https://modelslab.com/models)
import requests
import json
url = "https://modelslab.com/api/v6/images/text2img"
payload = json.dumps({
"key": "your_api_key",
"model_id": "mobius",
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"safety_checker": "no",
"enhance_prompt": "yes",
"seed": None,
"guidance_scale": 7.5,
"multi_lingual": "no",
"panorama": "no",
"self_attention": "no",
"upscale": "no",
"embeddings": "embeddings_model_id",
"lora": "lora_model_id",
"webhook": None,
"track_id": None
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
> Use this coupon code to get 25% off **DMGG0RBN** |
BreadAi/gpt-YA-1-1_160M | BreadAi | "2023-04-19T22:11:17Z" | 1,636 | 2 | transformers | [
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"dataset:breadlicker45/1m-YA-dataset",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-02-04T10:40:59Z" | ---
datasets:
- breadlicker45/1m-YA-dataset
train-eval-index:
- config: default
task: token-classification
task_id: entity_extraction
splits:
eval_split: test
col_mapping:
tokens: tokens
labels: tags
---
|
shibing624/chinese-alpaca-plus-13b-hf | shibing624 | "2023-12-15T06:18:17Z" | 1,636 | 35 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"chatglm",
"zh",
"Text2Text-Generation",
"LLaMA",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-11T13:52:38Z" | ---
title: chinese-alpaca-plus-13b-hf
emoji: 📚
colorFrom: gray
colorTo: red
language:
- zh
tags:
- chatglm
- pytorch
- zh
- Text2Text-Generation
- LLaMA
license: other
widget:
- text: 为什么天空是蓝色的？
---
# Chinese Alpaca Plus 13B Model
**发布中文LLaMA-Plus, Alpaca-Plus 13B版本模型**
发布中文LLaMA-Plus, Alpaca-Plus 13B版本，改进点如下：
- 相比基础版进一步扩充了训练数据，其中LLaMA扩充至120G文本，Alpaca扩充至4.3M指令数据，重点增加了科学领域数据，涵盖：物理、化学、生物、医学、地球科学等
- Alpaca训练时采用了更大的rank，相比基础版具有更低的验证集损失
- Alpaca评测结果：13B获得74.3分，Plus-7B获得78.2分，Plus-13B获得80.8分，具体评测结果请参考[效果评测](https://github.com/ymcui/Chinese-LLaMA-Alpaca/blob/main/examples)
- 多轮回复长度相比旧模型提升明显（可适当增大温度系数）
- 知识问答、写作、翻译等方面效果显著提升
本模型是 [decapoda-research/llama-13b-hf](https://huggingface.co/decapoda-research/llama-13b-hf)
底座模型 合并 [ziqingyang/chinese-llama-plus-lora-13b](https://huggingface.co/ziqingyang/chinese-llama-plus-lora-13b)
和 [ziqingyang/chinese-alpaca-plus-lora-13b](https://huggingface.co/ziqingyang/chinese-alpaca-plus-lora-13b) 两个LoRA权重，
并转化为HuggingFace版本权重（.bin文件），可以直接使用或者继续训练。
test case:
|input_text|predict|
|:-- |:--- |
|为什么天空是蓝色的？|天空是蓝色的是因为大气中的气体分子散射了太阳光中的短波长蓝光，使得我们看到的天空呈现出蓝色。|
## release model weight
- chinese-llama-plus-7b 模型权重链接：https://huggingface.co/minlik/chinese-llama-plus-7b-merged
- chinese-alpaca-plus-7b 模型权重链接：https://huggingface.co/shibing624/chinese-alpaca-plus-7b-hf
- chinese-llama-plus-13b 模型权重链接：https://huggingface.co/shibing624/chinese-llama-plus-13b-hf
- chinese-aplaca-plus-13b 模型权重链接：https://huggingface.co/shibing624/chinese-alpaca-plus-13b-hf
## Usage
本项目开源在textgen项目：[textgen](https://github.com/shibing624/textgen)，可支持llama模型，通过如下命令调用：
Install package:
```shell
pip install -U textgen
```
```python
from textgen import GptModel
model = GptModel("llama", "shibing624/chinese-alpaca-plus-13b-hf")
r = model.predict(["用一句话描述地球为什么是独一无二的。"])
print(r) # ['地球是独一无二的，因为它拥有独特的大气层、水循环、生物多样性以及其他自然资源，这些都使它成为一个独特的生命支持系统。']
```
## Usage (HuggingFace Transformers)
Without [textgen](https://github.com/shibing624/textgen), you can use the model like this:
First, you pass your input through the transformer model, then you get the generated sentence.
Install package:
```
pip install sentencepiece
pip install transformers>=4.28.0
```
```python
import torch
import transformers
from transformers import LlamaTokenizer, LlamaForCausalLM
def generate_prompt(text):
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{text}
### Response:"""
tokenizer = LlamaTokenizer.from_pretrained('shibing624/chinese-alpaca-plus-13b-hf')
model = LlamaForCausalLM.from_pretrained('shibing624/chinese-alpaca-plus-13b-hf').half().cuda()
model.eval()
text = '为什么天空是蓝色的？'
prompt = generate_prompt(text)
input_ids = tokenizer.encode(prompt, return_tensors='pt').to('cuda')
with torch.no_grad():
output_ids = model.generate(
input_ids=input_ids,
max_new_tokens=128,
temperature=1,
top_k=40,
top_p=0.9,
repetition_penalty=1.15
).cuda()
output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
print(output.replace(text, '').strip())
```
output:
```shell
为什么天空是蓝色的？
天空是蓝色的是因为大气中的气体分子散射了太阳光中的短波长蓝光，使得我们看到的天空呈现出蓝色。
```
## 模型来源
release合并后的模型权重，一步到位直接使用，省电、减少碳排放。
基于 [多LoRA权重合并（适用于Chinese-Alpaca-Plus ）](https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki/%E6%89%8B%E5%8A%A8%E6%A8%A1%E5%9E%8B%E5%90%88%E5%B9%B6%E4%B8%8E%E8%BD%AC%E6%8D%A2#%E5%A4%9Alora%E6%9D%83%E9%87%8D%E5%90%88%E5%B9%B6%E9%80%82%E7%94%A8%E4%BA%8Echinese-alpaca-plus)方法手动合并而成，具体是使用 [decapoda-research/llama-13b-hf](https://huggingface.co/decapoda-research/llama-13b-hf)
底座模型 合并 [ziqingyang/chinese-llama-plus-lora-13b](https://huggingface.co/ziqingyang/chinese-llama-plus-lora-13b) 和 [ziqingyang/chinese-alpaca-plus-lora-13b](https://huggingface.co/ziqingyang/chinese-alpaca-plus-lora-13b) 两个LoRA权重 得到，并转化为HuggingFace版本权重（.bin文件）。
HuggingFace版本权重（.bin文件）可用于：
- 使用Transformers进行训练和推理
- 使用text-generation-webui搭建界面
PyTorch版本权重（.pth文件）可用于：
- 使用llama.cpp工具进行量化和部署
PyTorch版本权重（.pth文件）链接：[shibing624/chinese-alpaca-plus-13b-pth](https://huggingface.co/shibing624/chinese-alpaca-plus-13b-pth)
模型文件组成：
```
chinese-alpaca-plus-13b-hf
|-- config.json
|-- generation_config.json
|-- LICENSE
|-- pytorch_model-00001-of-00003.bin
|-- pytorch_model-00002-of-00003.bin
|-- pytorch_model-00003-of-00003.bin
|-- pytorch_model.bin.index.json
|-- README.md
|-- special_tokens_map.json
|-- tokenizer_config.json
`-- tokenizer.model
```
硬件要求：25G显存
### 微调数据集
我整理部分公开微调数据集：
1. 50万条中文ChatGPT指令Belle数据集：[BelleGroup/train_0.5M_CN](https://huggingface.co/datasets/BelleGroup/train_0.5M_CN)
2. 100万条中文ChatGPT指令Belle数据集：[BelleGroup/train_1M_CN](https://huggingface.co/datasets/BelleGroup/train_1M_CN)
3. 5万条英文ChatGPT指令Alpaca数据集：[50k English Stanford Alpaca dataset](https://github.com/tatsu-lab/stanford_alpaca#data-release)
4. 5万条中文GPT4指令Alpaca数据集：[shibing624/alpaca-zh](https://huggingface.co/datasets/shibing624/alpaca-zh)
5. 69万条中文指令Guanaco数据集(Belle50万条+Guanaco19万条)：[Chinese-Vicuna/guanaco_belle_merge_v1.0](https://huggingface.co/datasets/Chinese-Vicuna/guanaco_belle_merge_v1.0)
如果需要训练LLaMA模型，请参考[https://github.com/shibing624/textgen](https://github.com/shibing624/textgen)
## Citation
```latex
@software{textgen,
author = {Xu Ming},
title = {textgen: Implementation of language model finetune},
year = {2023},
url = {https://github.com/shibing624/textgen},
}
```
## Reference
- https://github.com/ymcui/Chinese-LLaMA-Alpaca
# [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_shibing624__chinese-alpaca-plus-13b-hf)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 46.63 |
| ARC (25-shot) | 53.16 |
| HellaSwag (10-shot) | 73.51 |
| MMLU (5-shot) | 48.81 |
| TruthfulQA (0-shot) | 45.32 |
| Winogrande (5-shot) | 75.06 |
| GSM8K (5-shot) | 2.12 |
| DROP (3-shot) | 28.45 |
|
mncai/SGPT-1.3B-insurance-epoch10 | mncai | "2023-07-15T00:30:03Z" | 1,636 | 0 | transformers | [
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-15T00:17:19Z" | Entry not found |
Aspik101/30B-Lazarus-instruct-PL-lora_unload | Aspik101 | "2023-08-05T11:04:42Z" | 1,636 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"facebook",
"meta",
"llama-2",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-05T10:27:16Z" | ---
language:
- pl
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
license: other
model_type: llama-2
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
--- |
andreaskoepf/llama2-13b-megacode2_min100 | andreaskoepf | "2023-08-20T21:27:08Z" | 1,636 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-14T20:25:27Z" | ---
license: other
---
- wandb: [run34_megacode2_min100_13b](https://wandb.ai/open-assistant/epfl-mt-sft/runs/run34_megacode2_min100_13b) |
chargoddard/platypus-2-22b-relora | chargoddard | "2023-11-23T01:02:06Z" | 1,636 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"dataset:chargoddard/Open-Platypus-Chat",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-17T04:22:40Z" | ---
datasets:
- chargoddard/Open-Platypus-Chat
language:
- en
tags:
- llama
---
Experimental ReLoRA-trained model using the OpenPlatypus dataset. Ran for one epoch, with three lora restarts.
Not recommended for use yet. Mostly tossing this up for testing.
Base model was [llama2-22b-blocktriangular](https://huggingface.co/chargoddard/llama2-22b-blocktriangular).
Relevant training parameters:
```
adapter: qlora
load_in_4bit: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.001
lora_target_linear: true
relora_steps: 150
relora_warmup_steps: 10
gradient_accumulation_steps: 2
micro_batch_size: 3
```
Uses the same prompt format as [Ypotryll-22b](https://huggingface.co/chargoddard/ypotryll-22b-epoch2-qlora).
Prefix messages with `" ***System:"`, `" ***Query:"`, or `" ***Response:"`, paying attention to whitespace.
[<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)
# [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_chargoddard__platypus-2-22b-relora)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 52.21 |
| ARC (25-shot) | 57.68 |
| HellaSwag (10-shot) | 82.44 |
| MMLU (5-shot) | 55.33 |
| TruthfulQA (0-shot) | 43.61 |
| Winogrande (5-shot) | 77.35 |
| GSM8K (5-shot) | 6.6 |
| DROP (3-shot) | 42.46 |
|
yeontaek/Platypus2xOpenOrca-13B-IA3-v4 | yeontaek | "2023-08-23T09:39:01Z" | 1,636 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-23T08:59:26Z" | Entry not found |
uukuguy/speechless-codellama-dolphin-orca-platypus-13b | uukuguy | "2023-11-18T14:10:00Z" | 1,636 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"llama-2",
"code",
"en",
"dataset:ehartford/dolphin",
"dataset:Open-Orca/OpenOrca",
"dataset:garage-bAInd/Open-Platypus",
"arxiv:2308.12950",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-05T07:34:03Z" | ---
language:
- en
library_name: transformers
pipeline_tag: text-generation
datasets:
- ehartford/dolphin
- Open-Orca/OpenOrca
- garage-bAInd/Open-Platypus
tags:
- llama-2
- code
license: llama2
---
<p><h1> speechless-codellama-dolphin-orca-platypus-13b </h1></p>
Fine-tune the codellama/CodeLlama-13b-hf 1 epoch with Dolphin (1% GPT4), Orca (1% GPT4) and Platypus (100%) datasets.
| Metric | Value |
| --- | --- |
| ARC | 44.80 |
| HellaSwag | 68.60 |
| MMLU | 44.03 |
| TruthfulQA | 46.28 |
| Average | 50.93 |
# **Code Llama**
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the base 13B version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
| | Base Model | Python | Instruct |
| --- | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
| 7B | [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) |
| 13B | [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) | [codellama/CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf) | [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) |
| 34B | [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) | [codellama/CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf) | [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) |
## Model Use
To use this model, please make sure to install transformers from `main` until the next version is released:
```bash
pip install git+https://github.com/huggingface/transformers.git@main accelerate
```
Model capabilities:
- [x] Code completion.
- [x] Infilling.
- [ ] Instructions / chat.
- [ ] Python specialist.
```python
from transformers import AutoTokenizer
import transformers
import torch
model = "codellama/CodeLlama-13b-hf"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
sequences = pipeline(
'import socket\n\ndef ping_exponential_backoff(host: str):',
do_sample=True,
top_k=10,
temperature=0.1,
top_p=0.95,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
max_length=200,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
## Model Details
*Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs).
**Model Developers** Meta
**Variations** Code Llama comes in three model sizes, and three variants:
* Code Llama: base models designed for general code synthesis and understanding
* Code Llama - Python: designed specifically for Python
* Code Llama - Instruct: for instruction following and safer deployment
All variants are available in sizes of 7B, 13B and 34B parameters.
**This repository contains the base version of the 13B parameters model.**
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Code Llama is an auto-regressive language model that uses an optimized transformer architecture.
**Model Dates** Code Llama and its variants have been trained between January 2023 and July 2023.
**Status** This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
**Research Paper** More information can be found in the paper "[Code Llama: Open Foundation Models for Code](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)" or its [arXiv page](https://arxiv.org/abs/2308.12950).
## Intended Use
**Intended Use Cases** Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.
**Out-of-Scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.
## Hardware and Software
**Training Factors** We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.
**Carbon Footprint** In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.
## Training Data
All experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the [research paper](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/) for details).
## Evaluation Results
See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.
## Ethical Considerations and Limitations
Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available available at [https://ai.meta.com/llama/responsible-user-guide](https://ai.meta.com/llama/responsible-user-guide).
# [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_uukuguy__speechless-codellama-dolphin-orca-platypus-13b)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 44.41 |
| ARC (25-shot) | 44.8 |
| HellaSwag (10-shot) | 68.6 |
| MMLU (5-shot) | 44.03 |
| TruthfulQA (0-shot) | 46.28 |
| Winogrande (5-shot) | 66.93 |
| GSM8K (5-shot) | 9.55 |
| DROP (3-shot) | 30.68 |
|
Sao10K/Stheno-Inverted-1.2-L2-13B | Sao10K | "2023-11-18T04:34:53Z" | 1,636 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-06T14:29:15Z" | ---
license: llama2
language:
- en
---
***ONLY UPLOADED FROM RUNPOD JUST TO TEST ON OWN SYSTEM. UNTESTED SO FAR. V2 SOON***
***CURRENT CHANGES:***
<br>***INCREASED MODEL WEIGHTS AND DENSITIES IN TIES-MERGE FOR P1 & P2***
<br>***GRADIENT MERGE BETWEEN P2 & P1 CAN'T BE ILLUSTRATED, TENSORS EACH HAD UNIQUE RATIOS AND GRADIENTS APPLIED***
An experimental merging of Several Models using two various methods, [Ties-Merge](https://github.com/cg123/ties-merge) and [BlockMerge_Gradient](https://github.com/Gryphe/BlockMerge_Gradient)
Stheno:
<br>Gradient Merge of Stheno-P2 & Stheno-P1.
Test Checklist:
<br>Censorship - ____
<br>Writing - ____
<br>NSFW - ___
<br>IQ Level - ___
<br>Formatting - ____
Most formats could work, use Alpaca format and it works well.
```
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
```
Gradient Merge Pictures Unavailable, Several Different Tensor Ratios applied.
# [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_Sao10K__Stheno-Inverted-1.2-L2-13B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 48.8 |
| ARC (25-shot) | 59.39 |
| HellaSwag (10-shot) | 83.01 |
| MMLU (5-shot) | 55.77 |
| TruthfulQA (0-shot) | 51.22 |
| Winogrande (5-shot) | 74.66 |
| GSM8K (5-shot) | 8.95 |
| DROP (3-shot) | 8.61 |
|
Envoid/Libra-19B | Envoid | "2024-03-16T06:41:43Z" | 1,636 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-10T07:47:25Z" | ---
license: cc-by-nc-4.0
---
## Warning: This model may output adult content.
# Libra-19B
This model is made using [chargoddards's mergekit](https://github.com/cg123/mergekit/tree/main).
In this experiment I started with a very 'free' model [MLewd V2-2](https://huggingface.co/Undi95/MLewd-L2-13B-v2-2) and using the bakllama script I ran the following script
```
layer_slices:
- model: Undi95_MLewd-L2-13B-v2-2
start: 0
end: 40
- model: NousResearch_Llama-2-13b-chat-hf
start: 19
end: 20
- model: NousResearch_Llama-2-13b-chat-hf
start: 18
end: 19
- model: NousResearch_Llama-2-13b-chat-hf
start: 17
end: 18
- model: NousResearch_Llama-2-13b-chat-hf
start: 16
end: 17
- model: NousResearch_Llama-2-13b-chat-hf
start: 15
end: 16
- model: NousResearch_Llama-2-13b-chat-hf
start: 14
end: 15
- model: NousResearch_Llama-2-13b-chat-hf
start: 13
end: 14
- model: NousResearch_Llama-2-13b-chat-hf
start: 12
end: 13
- model: NousResearch_Llama-2-13b-chat-hf
start: 11
end: 12
- model: NousResearch_Llama-2-13b-chat-hf
start: 10
end: 11
- model: NousResearch_Llama-2-13b-chat-hf
start: 9
end: 10
- model: NousResearch_Llama-2-13b-chat-hf
start: 8
end: 9
- model: NousResearch_Llama-2-13b-chat-hf
start: 7
end: 8
- model: NousResearch_Llama-2-13b-chat-hf
start: 6
end: 7
- model: NousResearch_Llama-2-13b-chat-hf
start: 5
end: 6
- model: NousResearch_Llama-2-13b-chat-hf
start: 4
end: 5
- model: NousResearch_Llama-2-13b-chat-hf
start: 3
end: 4
- model: NousResearch_Llama-2-13b-chat-hf
start: 2
end: 3
- model: NousResearch_Llama-2-13b-chat-hf
start: 1
end: 2
- model: NousResearch_Llama-2-13b-chat-hf
start: 0
end: 1
```
In order to take the lower 20 layers of [NousResearch/Llama-2-13b-chat-hf](https://huggingface.co/NousResearch/Llama-2-13b-chat-hf) and stack them onto MLewd in the reverse order so that their orientation to the higher layers of the original model were symetrical in a way.
I then used qlora to run a very strong LoRA on the model. 2 epochs at 1e-6 learning rate on 60 megabytes of raw corpus with a rank and alpha of 1024 using a single A100 in 4-bits.
I wasn't able to load the model in text-generation-webui afterwards so all testing afterwards was done in koboldcpp after converting it to gguf.
The model does not respond as well to the Llama-2 format as it does to the alpaca-instruct style formatting. Optimal formatting and generation parameters are still a work in progress for roleplay but it has a decent level of attention for detail with regards to tavern cards. It's very good at instruct style prompts. It can even write simple python scripts.
## Example:
```
### Instruction:
Tell me about "the love languages" and which one resonates with you the most.
### Response:
The concept of "love languages" was introduced by author Gary Chapman in his book "The Five Love Languages: How to Express Heartfelt Commitment to Your Mate." According to this theory, there are five ways individuals express love and feel loved: words of affirmation, acts of service, receiving gifts, quality time, and physical touch. Each person has a primary love language that resonates with them the most, while others may prefer different ways of expressing or receiving love.
For example, someone whose primary love language is words of affirmation values verbal expressions of affection, appreciation, and praise. They enjoy being told how much they're loved, cherished, and valued in their relationship. On the other hand, someone whose primary love language is acts of service values actions rather than words. They feel loved when their partner helps them out around the house or carries out tasks they find difficult or stressful. Gift-giving is another love language where gift-givers often feel most appreciated when they receive presents from their partner. Physical touch is another way people express love through acts such as kissing, hugging, or holding hands. Quality time is spent together engaging in activities such as dates or shared experiences.
My own primary love language is words of affirmation. I value verbal expressions of love and appreciation in my relationships because it makes me feel seen, understood, and cherished. When my partner tells me how much they love me or expresses gratitude for something I've done for them, it reinforces our bond and strengthens our connection.
```
# [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_Envoid__Libra-19B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 52.8 |
| ARC (25-shot) | 60.58 |
| HellaSwag (10-shot) | 82.04 |
| MMLU (5-shot) | 55.57 |
| TruthfulQA (0-shot) | 48.41 |
| Winogrande (5-shot) | 76.32 |
| GSM8K (5-shot) | 0.08 |
| DROP (3-shot) | 46.63 |
|
Doctor-Shotgun/mythospice-70b | Doctor-Shotgun | "2023-09-14T15:17:15Z" | 1,636 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"llama-2",
"not-for-all-audiences",
"en",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-13T18:14:43Z" | ---
inference: false
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- llama
- llama-2
- not-for-all-audiences
---
# Model Card: mythospice-70b
This is a Llama 2-based model consisting of a merge of several models using SLERP:
- [jondurbin/spicyboros-70b-2.2](https://huggingface.co/jondurbin/spicyboros-70b-2.2)
- [elinas/chronos-70b-v2](https://huggingface.co/elinas/chronos-70b-v2)
- [NousResearch/Nous-Hermes-Llama2-70b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-70b)
## Usage:
Due to this being a merge of multiple models, different prompt formats may work, but you can try the Alpaca instruction format:
```
### Instruction:
<prompt>
### Input:
<additional context>
### Response:
<leave a newline blank for model to respond>
```
## Bias, Risks, and Limitations
The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model. It is not intended for supplying factual information or advice in any form.
## Training Details
This model is a merge. Please refer to the link repositories of the merged models for details. |
Doctor-Shotgun/mythospice-limarp-70b | Doctor-Shotgun | "2024-03-12T05:17:13Z" | 1,636 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"llama-2",
"not-for-all-audiences",
"en",
"license:agpl-3.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-13T20:12:38Z" | ---
inference: false
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- llama
- llama-2
- not-for-all-audiences
license: agpl-3.0
---
# Model Card: mythospice-limarp-70b
This is a Llama 2-based model consisting of a merge of several models using SLERP:
- [jondurbin/spicyboros-70b-2.2](https://huggingface.co/jondurbin/spicyboros-70b-2.2)
- [elinas/chronos-70b-v2](https://huggingface.co/elinas/chronos-70b-v2)
- [NousResearch/Nous-Hermes-Llama2-70b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-70b)
The LIMARP v2 adapter was then subsequently merged onto the model at a weight of 0.66:
- [lemonilia/limarp-llama2-v2](https://huggingface.co/lemonilia/limarp-llama2-v2)
## Usage:
Due to this being a merge of multiple models, different prompt formats may work, but you can try the Alpaca instruction format of the LIMARP v2:
```
### Instruction:
Character's Persona: {bot character description}
User's Persona: {user character description}
Scenario: {what happens in the story}
Play the role of Character. You must engage in a roleplaying chat with User below this line. Do not write dialogues and narration for User. Character should respond with messages of medium length.
### Input:
User: {utterance}
### Response:
Character: {utterance}
```
## Bias, Risks, and Limitations
The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model. It is not intended for supplying factual information or advice in any form.
## Training Details
This model is a merge. Please refer to the link repositories of the merged models for details. |
zarakiquemparte/kuchiki-1.1-l2-7b | zarakiquemparte | "2023-09-16T00:33:38Z" | 1,636 | 4 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"llama2",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-15T21:47:46Z" | ---
license: other
tags:
- llama2
---
# Model Card: Kuchiki 1.1 L2 7b
This model uses [Nous Hermes Llama2 7b](https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b) (70%) as a base with [Airoboros L2 7B GPT4 2.0](https://huggingface.co/jondurbin/airoboros-l2-7b-gpt4-2.0) (30%) and the result of this merge was merged with [LimaRP Llama2 v2 7B Lora](https://huggingface.co/lemonilia/limarp-llama2-v2).
This merge of models(hermes and airoboros) was done with this [script](https://github.com/zarakiquemparte/zaraki-tools/blob/main/merge-cli.py)
This merge of Lora with Model was done with this [script](https://github.com/zarakiquemparte/zaraki-tools/blob/main/apply-lora.py)
Merge illustration:
## Usage:
Since this is a merge between Nous Hermes, Airoboros and LimaRP, the following instruction formats should work:
Alpaca 2:
```
### Instruction:
<prompt>
### Response:
<leave a newline blank for model to respond>
```
Alpaca LimaRP:
```
### Instruction:
Character's Persona: {bot character description}
User's Persona: {user character description}
Scenario: {what happens in the story}
Play the role of Character. You must engage in a roleplaying chat with User below this line. Do not write dialogues and narration for User. Character should respond with messages of medium length.
### Input:
User: {utterance}
### Response:
Character: {utterance}
```
## Bias, Risks, and Limitations
This model is not intended for supplying factual information or advice in any form
## Training Details
This model is merged and can be reproduced using the tools mentioned above. Please refer to all provided links for extra model-specific details. |
TinyPixel/elm-test | TinyPixel | "2023-12-30T14:30:19Z" | 1,636 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-19T11:54:45Z" |
# [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_TinyPixel__elm-test)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 43.74 |
| ARC (25-shot) | 53.16 |
| HellaSwag (10-shot) | 78.98 |
| MMLU (5-shot) | 47.04 |
| TruthfulQA (0-shot) | 39.51 |
| Winogrande (5-shot) | 74.35 |
| GSM8K (5-shot) | 7.51 |
| DROP (3-shot) | 5.65 |
|
Sao10K/BrainDerp | Sao10K | "2023-11-18T04:33:38Z" | 1,636 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-29T15:19:13Z" | ---
license: llama2
language:
- en
---
'We have EnSEmblEd toP RAnKeRs tO mAKE oUr mODeL.'
'This MoDeL hAS BeEN trAINED oN orCa-StyLe DatAsEtS.'
'***trAINed***' KEK
'We hAVE AchIEvEd TOp RAnKeR In thE leAdErBOArDs.'
Lmao its all bs, you're all running merge scripts like we do, literally trying to game the leaderboards huh? Pathetic lol. Literally 0 card info, copy pasted from llama2 base models, with no other goals than going for leaderboards.
Atleast merge with a goal, like come on. I'm going for RP, Undi's going for RP. Atleast make a believable goal.
Brainderp is exposing the frauds who lie about it lol. Atleast be honest if you're merging like us poor people, which I appreciate some models do.
for BrainDerp, I have 'ensembled' several random models in the leaderboard to create this model.
i can easily steal the top leaderboard spots but meh not worth the effort.
that's it. i didn't bother testing much. ymmv.
<img src="https://blog.cdn.own3d.tv/resize=fit:crop,height:400,width:600/tbv2RYWpReqNtof2dD0U" style="width: 70%; min-width: 300px; display: block; margin: auto;">
# [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_Sao10K__BrainDerp)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 51.16 |
| ARC (25-shot) | 60.75 |
| HellaSwag (10-shot) | 82.1 |
| MMLU (5-shot) | 58.81 |
| TruthfulQA (0-shot) | 56.9 |
| Winogrande (5-shot) | 75.85 |
| GSM8K (5-shot) | 8.26 |
| DROP (3-shot) | 15.48 |
|
KnutJaegersberg/Galactica-6.7B-EssayWriter | KnutJaegersberg | "2024-03-04T16:29:11Z" | 1,636 | 3 | transformers | [
"transformers",
"safetensors",
"opt",
"text-generation",
"dataset:ChristophSchuhmann/essays-with-instructions",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-20T05:02:04Z" | ---
license: cc-by-nc-4.0
datasets:
- ChristophSchuhmann/essays-with-instructions
model-index:
- name: Galactica-6.7B-EssayWriter
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: 40.1
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
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: 50.29
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
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: 33.88
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 40.27
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
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: 58.48
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
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: 3.49
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
name: Open LLM Leaderboard
---
Prompt Example:
```
### Instruction:
Provide the inputted essay that when summarized resulted in the following summary : The organization's learning and development practices are poor as they involve manual orientation from experienced workers. New employees are not advised of their roles in the organization before assignment of tasks. The orientation process takes long due to lack of a well-coordinated orientation programs.
### Response:
```
# [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_KnutJaegersberg__Galactica-6.7B-EssayWriter)
| Metric |Value|
|---------------------------------|----:|
|Avg. |37.75|
|AI2 Reasoning Challenge (25-Shot)|40.10|
|HellaSwag (10-Shot) |50.29|
|MMLU (5-Shot) |33.88|
|TruthfulQA (0-shot) |40.27|
|Winogrande (5-shot) |58.48|
|GSM8k (5-shot) | 3.49|
|
ceadar-ie/FinanceConnect-13B | ceadar-ie | "2023-12-11T20:18:44Z" | 1,636 | 13 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"summarization",
"classification",
"translation",
"NLP",
"finance",
"domain specific llm",
"conversational",
"en",
"dataset:FinTalk-19k",
"doi:10.57967/hf/1405",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-28T14:26:49Z" | ---
language: en
datasets:
- FinTalk-19k
tags:
- summarization
- classification
- translation
- NLP
- finance
- domain specific llm
license: apache-2.0
pipeline_tag: text-generation
---
# FinanceConnect
FinanceConnect is a state-of-the-art, open-source chat model tailored for finance and economic discussions. Built on the robust Llama2-13B architecture, this model has been fine-tuned on a combination of FinTalk-19k and Alpaca datasets, making it a valuable resource for finance professionals, researchers, and enthusiasts.
## Model Details
- Architecture: Llama2-13B
- Training Dataset: [FinTalk-19k](https://huggingface.co/datasets/ceadar-ie/FinTalk-19k), [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca)
## Dataset Utilized: FinTalk-19k and Alpaca
Drawing strength from the FinTalk-19k and Alpaca dataset, a curated collection focused on financial knowledge, this model provides insights and information related to the finance industry. For a deeper dive into the dataset, visit: [FinTalk-19k](https://huggingface.co/datasets/ceadar-ie/FinTalk-19k), [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca)
## Model Specification
- **Developed by:** CeADAR Connect Group
- **Model type:** Large Language Model
- **Language(s):** en
- **Finetuned from model:** Llama2-13B
## Key Features and Functionalities
- **Domain Specialization:** The FinanceConnect model is specialized in Finance conversations, serving as a resource for financial researchers, and enthusiasts.
- **Model API Accessibility:** Offers a straightforward Python integration for generating financial content insights.
- **Performance Optimisation:** Efficient performance across both CPU and GPU platforms.
- **Data Representation:** Utilises a combination of comprehensive Finance dataset, enabling content generation to professional standards.
## Benchmarks
| **Benchmark** | **BloombergGPT 50B** | **FinanceConnect 13B** |
|--------------|--------------|--------------|
| MMLU | 39.8 | 52.08 |
| FPB | 51.1 | 57.2 |
| **Cost**| **$2.67 Million** | **$27** |
| **Benchmark** | **FinanceConnect 13B** |
|--------------|--------------
| MMLU | 52.08 |
| ARC | 55.12 |
| HellaSwag | 77.73 |
| TruthfulQA | 38.80 |
| Winogrande | 71.82 |
| GSM8K | 1.6 |
## Model Usage
Experience the capabilities of the FinanceConnect model through a well-structured Python interface. To kick-start your exploration, follow the steps and snippets given below:
### Prerequisites
#### 1. Ensure required packages are available
```python
import torch
from typing import Any, Dict
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
HfArgumentParser,
TrainingArguments,
PreTrainedTokenizerFast,
pipeline,
logging,
)
import time
```
#### 2. Initiate the model and tokenizer
```python
model_name = "ceadar-ie/FinanceConnect-13B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, load_in_8bit = True, device_map = "auto", trust_remote_code=True)
```
#### 3. Create a function for generating text
```python
def generate_text(input_text):
tokenizer.padding_side = "right"
num_words_input = len(input_text.split())
start_time = time.time()
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length = 1000)
prompt = f"<s>[INST] {input_text} [/INST]"
#prompt = input_text
result = pipe(prompt)
generated_text = result[0]['generated_text'].replace(prompt, "").strip()
end_time = time.time()
time_taken = end_time - start_time
num_words_generated = len(generated_text.split())
print("Generated Output:")
print(generated_text)
print('=' * 60 )
print("\nNumber of Words in Input Text:", num_words_input)
print("Number of Words in Generated Output:", num_words_generated)
print("Time Taken to Generate Output: {:.2f} seconds".format(time_taken))
```
## Example Evaluation and Use
### Example Prompt 1:
List in detail ten key factors influencing the current state of the global economy.
### Generated Output:
The current state of the global economy is influenced by several factors, including:
1. Globalization: The increasing interconnectedness of economies through trade, investment, and the movement of people.
2. Technological advancements: The rapid pace of technological innovation and its impact on industries and jobs.
3. Political factors: Government policies and decisions that affect economic growth and stability.
4. Demographics: Changes in population demographics, such as aging populations and youth bulges, can impact economic growth and stability.
5. Environmental factors: Climate change, natural disasters, and other environmental factors can disrupt economic activity and impact growth.
6. International trade: The rise of protectionism and trade tensions between countries can impact economic growth and stability.
7. Financial factors: The performance of financial markets and the availability of credit can impact economic growth and stability.
8. Infrastructure: The availability and quality of infrastructure, such as transportation and communication networks, can impact economic growth and stability.
9. Education: The availability and quality of education can impact economic growth and stability by influencing the supply of skilled workers and the ability of countries to adapt to changing economic conditions.
10. Health: The availability and quality of healthcare can impact economic growth and stability by influencing the productivity of the workforce and the ability of countries to attract and retain talent.
### Example Prompt 2:
Explain the concept of quantitative easing and its impact on financial markets.
### Generated Output:
Quantitative easing is a monetary policy tool used by central banks to stimulate economic growth and combat inflation. It involves the purchase of assets such as government bonds, mortgage-backed securities, and corporate bonds by a central bank. This increases the amount of money in circulation, lowers interest rates, and encourages banks to lend more, which can boost economic growth. However, quantitative easing can also lead to inflation if it is not implemented carefully, as it can cause prices to rise more than wages can keep up with.
### Example Prompt 3:
I've recently started working and want to manage my finances. Give me a detailed answer in 10 points on how do I set up a budget?
### Generated Output:
Setting up a budget can help manage finances and save money. Here are some tips:
1. Determine your income and expenses.
2. Create a budget that includes all necessary expenses, such as rent, utilities, and groceries.
3. Set aside a portion of your income for savings and investments.
4. Monitor your spending regularly and adjust your budget as needed.
5. Use cash or debit cards instead of credit cards to avoid overspending.
6. Cut back on unnecessary expenses, such as eating out or subscriptions.
7. Consider using a budgeting app or tool to help track your spending.
8. Prioritize your spending based on your financial goals.
9. Review your budget regularly and make adjustments as needed.
10. Be flexible and willing to make changes to your budget as your financial situation changes.
## Training Details
### Training Hyperparameters
- per_device_train_batch_size = 10
- gradient_accumulation_steps = 4
- optim = "paged_adamw_32bit"
- learning_rate = 2e-4
- max_grad_norm = 0.3
- warmup_ratio = 0.03
## Licensing
The FinanceConnect model, developed by CeADAR Connect Group, combines the licensing frameworks of Llama2, FinTalk-8k and Alpaca. Under Meta's terms, users are granted a non-exclusive, worldwide, non-transferable, royalty-free limited license for the use and modification of Llama Materials, inclusive of the Llama2 model and its associated documentation. When redistributing, the provided Agreement and a specific attribution notice must be included. Further, in alignment with the FinTalk dataset's(Apache 2.0) licensing and Alpaca dataset's(cc-by-nc-4.0) licensing, the model is distributed under the umbrella of all three licenses.
## Model Limitations
### Out-of-Scope Use
FinanceConnect is specifically tailored for finanical discussions and knowledge. It is not optimized for:
- General conversations.
- Domain-specific tasks outside financial tasks.
- Direct interfacing with physical devices or applications.
### Bias, Risks, and Limitations
- Dataset Biases: The FinTalk-19k and Alpaca dataset may contain inherent biases that influence the model's outputs.
- Over-reliance: The model is an aid, not a replacement for human expertise. Decisions should be made with careful consideration.
- Content Understanding: The model lacks human-like understanding and cannot judge the veracity of knowledge.
- Language Limitations: The model's primary language is English. Performance may decrease with other languages.
- Knowledge Cut-off: The model may not be aware of events or trends post its last training update.
## Citation
```
@misc {ceadar_2023,
author = { {CeADAR} },
title = { FinanceConnect-13B (Revision 5f7841d) },
year = 2023,
url = { https://huggingface.co/ceadar-ie/FinanceConnect-13B },
doi = { 10.57967/hf/1405 },
publisher = { Hugging Face }
}
```
## Contact
For any further inquiries or feedback concerning FinanceConnect, please forward your communications to [email protected]
|
Azazelle/Tippy-Toppy-7b | Azazelle | "2024-01-05T22:29:27Z" | 1,636 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-03T21:53:16Z" | ---
pipeline_tag: text-generation
tags:
- mistral
- merge
license: cc-by-4.0
---
# Model Card for Tippy-Toppy-7b
<!-- Provide a quick summary of what the model is/does. -->
DARE merge intended to be build on Toppy-M-7b.
.yaml file for mergekit
```.yaml:
models:
- model: mistralai/Mistral-7B-v0.1
# no parameters necessary for base model
- model: Undi95/Toppy-M-7B #175
parameters:
weight: 0.54
density: 0.81
- model: PistachioAlt/Noromaid-Bagel-7B-Slerp #75
parameters:
weight: 0.23
density: 0.61
- model: OpenPipe/mistral-ft-optimized-1227 #100
parameters:
weight: 0.31
density: 0.68
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: bfloat16
``` |
timm/resnet34d.ra2_in1k | timm | "2024-02-10T23:39:01Z" | 1,635 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:2110.00476",
"arxiv:1512.03385",
"arxiv:1812.01187",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-04-05T18:07:30Z" | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
---
# Model card for resnet34d.ra2_in1k
A ResNet-D image classification model.
This model features:
* ReLU activations
* 3-layer stem of 3x3 convolutions with pooling
* 2x2 average pool + 1x1 convolution shortcut downsample
Trained on ImageNet-1k in `timm` using recipe template described below.
Recipe details:
* RandAugment `RA2` recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as `B` recipe in [ResNet Strikes Back](https://arxiv.org/abs/2110.00476).
* RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging
* Step (exponential decay w/ staircase) LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 21.8
- GMACs: 3.9
- Activations (M): 4.5
- Image size: train = 224 x 224, test = 288 x 288
- **Papers:**
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- 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('resnet34d.ra2_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnet34d.ra2_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 112, 112])
# torch.Size([1, 64, 56, 56])
# torch.Size([1, 128, 28, 28])
# torch.Size([1, 256, 14, 14])
# torch.Size([1, 512, 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(
'resnet34d.ra2_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 512, 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).
|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
@inproceedings{wightman2021resnet,
title={ResNet strikes back: An improved training procedure in timm},
author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}
```
```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{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
@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}
}
```
|
Ejafa/vicuna_7B_vanilla_1.1 | Ejafa | "2023-04-15T10:11:13Z" | 1,635 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-04-13T12:12:24Z" | Entry not found |
YeungNLP/firefly-bloom-2b6-v2 | YeungNLP | "2023-04-27T09:01:04Z" | 1,635 | 9 | transformers | [
"transformers",
"pytorch",
"bloom",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-04-27T08:51:30Z" | Entry not found |
PSanni/Deer-3b | PSanni | "2024-01-06T13:50:35Z" | 1,635 | 2 | transformers | [
"transformers",
"pytorch",
"bloom",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-20T08:44:48Z" | ---
license: apache-2.0
metrics:
- accuracy
pipeline_tag: text-generation
---
## Summary
"Deer-3b," an instruction-following large language model based on "Bloom-3b," is fine-tuned using ±5k instructions.
Deer will also be available in larger models size.
## Usage
To use the model with the `transformers` library on a machine with GPUs.
```python
import torch
from transformers import pipeline
generate_text = pipeline(model="PSanni/Deer-3b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
```
You can then use the pipeline to answer instructions:
```python
res = generate_text("Explain to me the difference between nuclear fission and fusion.")
print(res[0]["generated_text"])
```
### Note:
Kindly note that the model isn't attuned to human preferences and could generate unsuitable, unethical, biased, and toxic responses.
# [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_PSanni__Deer-3b)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 32.01 |
| ARC (25-shot) | 38.48 |
| HellaSwag (10-shot) | 57.41 |
| MMLU (5-shot) | 25.64 |
| TruthfulQA (0-shot) | 39.98 |
| Winogrande (5-shot) | 57.46 |
| GSM8K (5-shot) | 0.3 |
| DROP (3-shot) | 4.83 |
|
upstage/llama-30b-instruct | upstage | "2023-08-03T22:03:05Z" | 1,635 | 23 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"upstage",
"instruct",
"instruction",
"en",
"dataset:sciq",
"dataset:metaeval/ScienceQA_text_only",
"dataset:GAIR/lima",
"dataset:Open-Orca/OpenOrca",
"dataset:openbookqa",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-11T02:41:53Z" | ---
datasets:
- sciq
- metaeval/ScienceQA_text_only
- GAIR/lima
- Open-Orca/OpenOrca
- openbookqa
language:
- en
tags:
- upstage
- llama
- instruct
- instruction
pipeline_tag: text-generation
---
# LLaMa-30b-instruct model card
## Model Details
* **Developed by**: [Upstage](https://en.upstage.ai)
* **Backbone Model**: [LLaMA](https://github.com/facebookresearch/llama/tree/llama_v1)
* **Variations**: It has different model parameter sizes and sequence lengths: [30B/1024](https://huggingface.co/upstage/llama-30b-instruct), [30B/2048](https://huggingface.co/upstage/llama-30b-instruct-2048), [65B/1024](https://huggingface.co/upstage/llama-65b-instruct)
* **Language(s)**: English
* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
* **License**: This model is under a **Non-commercial** Bespoke License and governed by the Meta license. You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform), but have either lost your copy of the weights or encountered issues converting them to the Transformers format
* **Where to send comments**: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the [Hugging Face community's model repository](https://huggingface.co/upstage/llama-30b-instruct/discussions)
* **Contact**: For questions and comments about the model, please email [[email protected]](mailto:[email protected])
## Dataset Details
### Used Datasets
- [openbookqa](https://huggingface.co/datasets/openbookqa)
- [sciq](https://huggingface.co/datasets/sciq)
- [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca)
- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only)
- [GAIR/lima](https://huggingface.co/datasets/GAIR/lima)
- No other data was used except for the dataset mentioned above
### Prompt Template
```
### System:
{System}
### User:
{User}
### Assistant:
{Assistant}
```
## Usage
- Tested on A100 80GB
- Our model can handle up to 10k+ input tokens, thanks to the `rope_scaling` option
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
tokenizer = AutoTokenizer.from_pretrained("upstage/llama-30b-instruct")
model = AutoModelForCausalLM.from_pretrained(
"upstage/llama-30b-instruct",
device_map="auto",
torch_dtype=torch.float16,
load_in_8bit=True,
rope_scaling={"type": "dynamic", "factor": 2} # allows handling of longer inputs
)
prompt = "### User:\nThomas is healthy, but he has to go to the hospital. What could be the reasons?\n\n### Assistant:\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
del inputs["token_type_ids"]
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
output = model.generate(**inputs, streamer=streamer, use_cache=True, max_new_tokens=float('inf'))
output_text = tokenizer.decode(output[0], skip_special_tokens=True)
```
## Hardware and Software
* **Hardware**: We utilized an A100x8 * 1 for training our model
* **Training Factors**: We fine-tuned this model using a combination of the [DeepSpeed library](https://github.com/microsoft/DeepSpeed) and the [HuggingFace Trainer](https://huggingface.co/docs/transformers/main_classes/trainer) / [HuggingFace Accelerate](https://huggingface.co/docs/accelerate/index)
## Evaluation Results
### Overview
- We conducted a performance evaluation based on the tasks being evaluated on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
We evaluated our model on four benchmark datasets, which include `ARC-Challenge`, `HellaSwag`, `MMLU`, and `TruthfulQA`
We used the [lm-evaluation-harness repository](https://github.com/EleutherAI/lm-evaluation-harness), specifically commit [b281b0921b636bc36ad05c0b0b0763bd6dd43463](https://github.com/EleutherAI/lm-evaluation-harness/tree/b281b0921b636bc36ad05c0b0b0763bd6dd43463)
- We used [MT-bench](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge), a set of challenging multi-turn open-ended questions, to evaluate the models
### Main Results
| Model | H4(Avg) | ARC | HellaSwag | MMLU | TruthfulQA | | MT_Bench |
|--------------------------------------------------------------------|----------|----------|----------|------|----------|-|-------------|
| **[Llama-2-70b-instruct-v2](https://huggingface.co/upstage/Llama-2-70b-instruct-v2)**(Ours, Open LLM Leaderboard) | **73** | **71.1** | **87.9** | **70.6** | **62.2** | | **7.44063** |
| [Llama-2-70b-instruct](https://huggingface.co/upstage/Llama-2-70b-instruct) (Ours, Open LLM Leaderboard) | 72.3 | 70.9 | 87.5 | 69.8 | 61 | | 7.24375 |
| [llama-65b-instruct](https://huggingface.co/upstage/llama-65b-instruct) (Ours, Open LLM Leaderboard) | 69.4 | 67.6 | 86.5 | 64.9 | 58.8 | | |
| Llama-2-70b-hf | 67.3 | 67.3 | 87.3 | 69.8 | 44.9 | | |
| [llama-30b-instruct-2048](https://huggingface.co/upstage/llama-30b-instruct-2048) (Ours, Open LLM Leaderboard) | 67.0 | 64.9 | 84.9 | 61.9 | 56.3 | | |
| [llama-30b-instruct](https://huggingface.co/upstage/llama-30b-instruct) (***Ours***, ***Open LLM Leaderboard***) | 65.2 | 62.5 | 86.2 | 59.4 | 52.8 | | |
| llama-65b | 64.2 | 63.5 | 86.1 | 63.9 | 43.4 | | |
| falcon-40b-instruct | 63.4 | 61.6 | 84.3 | 55.4 | 52.5 | | |
### Scripts for H4 Score Reproduction
- Prepare evaluation environments:
```
# clone the repository
git clone https://github.com/EleutherAI/lm-evaluation-harness.git
# check out the specific commit
git checkout b281b0921b636bc36ad05c0b0b0763bd6dd43463
# change to the repository directory
cd lm-evaluation-harness
```
## Ethical Issues
### Ethical Considerations
- There were no ethical issues involved, as we did not include the benchmark test set or the training set in the model's training process
## Contact Us
### Why Upstage LLM?
- [Upstage](https://en.upstage.ai)'s LLM research has yielded remarkable results. As of August 1st, our 70B model has reached the top spot in openLLM rankings, marking itself as the current leading performer globally. Recognizing the immense potential in implementing private LLM to actual businesses, we invite you to easily apply private LLM and fine-tune it with your own data. For a seamless and tailored solution, please do not hesitate to reach out to us. ► [click here to contact](https://www.upstage.ai/private-llm?utm_source=huggingface&utm_medium=link&utm_campaign=privatellm) |
Lajonbot/vicuna-13b-v1.3-PL-lora_unload | Lajonbot | "2023-08-02T07:32:05Z" | 1,635 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"facebook",
"meta",
"llama-2",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-02T07:22:18Z" | ---
language:
- pl
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
license: other
model_type: llama-2
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
--- |
golaxy/goims | golaxy | "2023-08-04T08:44:00Z" | 1,635 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-04T08:37:50Z" | ---
license: apache-2.0
---
|
quantumaikr/llama-2-7b-hf-guanaco-1k | quantumaikr | "2023-08-06T19:03:00Z" | 1,635 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-06T17:58:38Z" | Entry not found |
Gryphe/MythoMix-L2-13b | Gryphe | "2023-08-11T05:44:46Z" | 1,635 | 19 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-08T15:01:01Z" | ---
license: other
language:
- en
---
**UPDATE:** There's an improved version now! [Check it MythoMax!](https://huggingface.co/Gryphe/MythoMax-L2-13b)
A requested variant of [MythoLogic-L2](https://huggingface.co/Gryphe/MythoLogic-L2-13b) and [Huginn](https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16) using a highly experimental tensor type merge technique.
This model is proficient at both roleplaying and storywriting due to its unique nature.
Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheBloke/MythoMix-L2-13B-GGML) - [GPTQ](https://huggingface.co/TheBloke/MythoMix-L2-13B-GPTQ) (You're the best!)
## Model details
The idea behind this merge is that each layer is composed of several tensors, which are in turn responsible for specific functions. Using MythoLogic-L2's robust understanding as its input and Huginn's extensive writing capability as its output seems to have resulted in a model that exceeds at both, confirming my theory. (More details to be released at a later time)
This type of merge is incapable of being illustrated, as each of its 360 tensors has an unique ratio applied to it. As with my prior merges, gradients were part of these ratios to further finetune its behaviour.
## Prompt Format
This model primarily uses Alpaca formatting, so for optimal model performance, use:
```
<System prompt/Character Card>
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
```
---
license: other
--- |
Aspik101/trurl-2-13b-pl-instruct_unload | Aspik101 | "2023-08-18T07:32:37Z" | 1,635 | 6 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"facebook",
"meta",
"llama-2",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-18T07:18:06Z" | ---
language:
- pl
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
license: other
model_type: llama-2
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
--- |
wei123602/llama2-13b-FINETUNE3_TEST | wei123602 | "2023-09-13T04:59:27Z" | 1,635 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-13T04:37:01Z" | Entry not found |
oh-yeontaek/llama-2-70B-LoRA-assemble-v2 | oh-yeontaek | "2023-09-15T03:49:40Z" | 1,635 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-15T03:12:42Z" | Entry not found |
wei123602/Llama-2-13b-FINETUNE4 | wei123602 | "2023-10-23T11:15:58Z" | 1,635 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-16T12:03:09Z" | Entry not found |
ICBU-NPU/FashionGPT-70B-V1 | ICBU-NPU | "2023-09-22T07:58:07Z" | 1,635 | 3 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:ehartford/samantha-data",
"dataset:Open-Orca/OpenOrca",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"arxiv:2306.02707",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-17T11:09:47Z" | ---
license: llama2
datasets:
- ehartford/samantha-data
- Open-Orca/OpenOrca
- jondurbin/airoboros-gpt4-1.4.1
language:
- en
---
# FashionGPT-V1
### Introduction
This is a llama-2-70B model combined with two adapters via appropriate methods.
### Dataset
Here is the list of datasets used:
* Orca-style 40K dataset. This dataset is a filtered subset of [OpenOrca-GPT4](<https://huggingface.co/datasets/Open-Orca/OpenOrca/blob/main/1M-GPT4-Augmented.parquet>) and [airoboros-gpt4-1.4.1](<https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1>).
* [Samantha](<https://huggingface.co/datasets/ehartford/samantha-data>) made by Eric Hartford and cleaned by us, about 6.5K samples.
<br>
### Training
* We train our adapters with [jondurbin's forked QLoRA repo](<https://github.com/jondurbin/qlora>)
* We add multi-turn conversational data support from [fastchat repo](<https://github.com/lm-sys/FastChat/blob/main/fastchat/train/train.py>), with minor modifications.
* We use bash shell script similar to [airoboros-70b-gpt4-1.4.1](<https://gist.github.com/jondurbin/87fc040b92a3073125ed516b04bc6e19>) to train our two adapters.
* We found that combining multiple adapters to a single llama-2-70B could achieve better performance than merging only 1 adapter to llama-2-70B. The details of combining multiple adapters will be unveiled in our upcoming paper.
<br>
### Prompt Template
```
### System:
{System}
### User:
{User}
### Assistant:
{Assistant}
```
<br>
### Evaluation
| Metric | Value |
|-----------------------|-------|
| ARC (25-shot) | 71.08 |
| HellaSwag (10-shot) | 87.32 |
| MMLU (5-shot) | 70.70 |
| TruthfulQA (0-shot) | 63.92 |
| Avg. | 73.26 |
<br>
### license disclaimer
This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.
<br>
### Limitations & Biases
Llama 2 and fine-tuned variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2 and any fine-tuned varient's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2 variants, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at <https://ai.meta.com/llama/responsible-use-guide/>
<br>
### Citiation:
* airoboros: <https://github.com/jondurbin/airoboros>
* samantha: <https://erichartford.com/meet-samantha>
```bibtex
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```bibtex
@article{dettmers2023qlora,
title={QLoRA: Efficient Finetuning of Quantized LLMs},
author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
journal={arXiv preprint arXiv:2305.14314},
year={2023}
}
```
```bibtex
@software{touvron2023llama2,
title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
author={Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava,
Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,
Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann,
Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov,
Pushkar Mishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith,
Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu , Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan,
Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom},
year={2023}
}
``` |
jondurbin/airoboros-c34b-2.2.1 | jondurbin | "2023-09-28T09:39:42Z" | 1,635 | 9 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-2.2.1",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-19T20:22:58Z" | ---
license: llama2
datasets:
- jondurbin/airoboros-2.2.1
---
### Overview
Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
This is essentially a minor "fix" branch of [airoboros-c34b-2.2](https://hf.co/jondurbin/airoboros-c34b-2.2) with a updates, primarily:
- [re-generated writing responses](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#re-generated-writing-responses)
- [longer contextual blocks](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#longer-contextual-blocks)
- [removal of "rp" data](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#rp-category-removed)
- [(less aggressive) de-censoring](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#de-censoring)
- 5 epochs instead of 3
This is a fairly general purpose model, but focuses heavily on instruction following, rather than casual chat/roleplay.
Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools!
### Prompt format
The prompt format:
```
A chat.
USER: {prompt}
ASSISTANT:
```
The default system prompt ("A chat.") was used for most of the prompts, however it also included a wide sampling of responses with other prompts, particularly in "stylized\_response", "rp", "gtkm", etc.
Here's another example:
```
A chat between Bob (aka USER) and Tom (aka ASSISTANT). Tom is an extremely intelligent 18th century bookkeeper, who speaks loquaciously.
USER: {prompt}
ASSISTANT:
```
And chat scenario that wouldn't require USER/ASSISTANT (but should use stopping criteria to prevent the model from speaking on your behalf).
```
A chat between old friends: Timmy and Tommy.
{description of characters}
{setting for the chat}
Timmy: *takes a big sip from his coffee* "Ah, sweet, delicious, magical coffee."
Tommy:
```
__*I strongly suggest adding stopping criteria/early inference stopping on "USER:", and/or whatever names you specify in the system prompt.*__
### Fine tuning info
https://wandb.ai/jondurbin/airoboros-c34b-2.2.1/runs/07b08z7m?workspace=user-jondurbin
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Getting longer responses
You can use a few techniques to get longer responses.
Detailed prompts, with explicit instruction for word count:
```
Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality.
The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization.
One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary.
Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements.
Your response should be approximately 2300 words.
```
Or, a simpler example:
```
Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux.
```
There are a few examples of next chapter completion as well, e.g.:
```
Write the next chapter of a historical fiction novel set in Paris during the 20th century.
Here's a summary of the previous chapter:
In the vibrant city of Paris, amid the tumultuous changes of the 20th century, our protagonist Margot, an aspiring fashion designer, has just secured an apprenticeship at a prestigious couture house. She meets Lucien, a charming journalist who covers the fashion industry. Together they navigate the ever-changing world of fashion and society, uncovering secrets that reveal the intricate links between style, politics, and culture. As the chapter concludes, they decide to delve deeper into the hidden corners of the fashion world to unravel its mysteries.
Requirements for the next chapter:
1. Character Development of Margot and Lucien:
- Margot's Evolution: Unfold more about Margot's past, her dreams of revolutionizing fashion, and her struggle to establish herself in a male-dominated industry. Illustrate her growing expertise, innovative ideas, and increasing dependence on Lucien.
- Lucien's Complexity: Introduce uncertainties surrounding Lucien's background and real motives. Increase suspense by suggesting undisclosed information he possesses, while also highlighting his wit and perceptiveness.
2. Exploration of Paris and the Couture House:
- Paris: Elaborate their journey through the bustling streets of Paris, including encounters with iconic figures, social unrest, and relics from different eras of French history.
- The Couture House: Expand on the grandeur of the couture house they work in, filled with artistic masterpieces, intense competition, and cryptic notes hinting at a scandalous past.
3. Emergence of the Subplot: The Lost Collection:
- Discovery: Have Margot and Lucien stumble upon a secret vault containing a lost collection designed before World War II, raising new questions about the previous owner and the influence of war on fashion.
- Revelation: Capture their shock as they realize the designs were plagiarized, the potential repercussions, and the opportunities it presents for Margot's career.
- Twist: End with a twist that suggests there are other stolen collections across Paris, setting up their new mission.
Your response should be approximately 650 words.
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 2.2 models are built on top of llama-2/codellama.
The llama-2 base model has a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me. |
CHIH-HUNG/llama-2-13b-FINETUNE3_3.3w-r8-gate_up_down | CHIH-HUNG | "2023-09-20T07:27:40Z" | 1,635 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-20T06:48:42Z" | Entry not found |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.