text-generation-webui/README.md

83 lines
2.9 KiB
Markdown
Raw Normal View History

2022-12-20 23:17:38 -05:00
# text-generation-webui
2022-12-21 14:49:30 -05:00
A gradio webui for running large language models locally. Supports gpt-j-6B, gpt-neox-20b, opt, galactica, and many others.
Its goal is to become the [AUTOMATIC1111/stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) of text generation.
2022-12-21 11:17:06 -05:00
2022-12-21 12:04:51 -05:00
![webui screenshot](https://github.com/oobabooga/text-generation-webui/raw/main/webui.png)
2022-12-21 11:17:06 -05:00
## Installation
Create a conda environment:
conda create -n textgen
conda activate textgen
Install the appropriate pytorch for your GPU. For NVIDIA GPUs, this should work:
conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
Install the requirements:
pip install -r requirements.txt
2022-12-21 11:17:06 -05:00
2022-12-21 12:37:50 -05:00
## Downloading models
2023-01-06 00:12:38 -05:00
Models should be placed under `models/model-name`. For instance, `models/gpt-j-6B` for [gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B/tree/main).
2022-12-21 12:37:50 -05:00
2022-12-21 13:00:16 -05:00
#### Hugging Face
2022-12-21 12:37:50 -05:00
2023-01-06 00:13:48 -05:00
Hugging Face is the main place to download models. These are some of my favorite:
2022-12-21 12:37:50 -05:00
2023-01-05 22:13:26 -05:00
* [gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B/tree/main)
* [gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b/tree/main)
* [opt](https://huggingface.co/models?search=facebook/opt)
* [galactica](https://huggingface.co/models?search=facebook/galactica)
* [\*-Erebus](https://huggingface.co/models?search=erebus)
2023-01-06 00:12:38 -05:00
The files that you need to download are the json, txt, and pytorch\*.bin files. The remaining files are not necessary.
2022-12-21 12:37:50 -05:00
2023-01-06 18:00:58 -05:00
For your convenience, you can automatically download a model from HF using the script download-model.py. Its usage is very simple:
python download-model.py organization/model
For instance:
python download-model.py facebook/opt-1.3b
2022-12-21 13:00:16 -05:00
#### GPT-4chan
2022-12-21 12:37:50 -05:00
[GPT-4chan](https://huggingface.co/ykilcher/gpt-4chan) has been shut down from Hugging Face, so you need to download it elsewhere. You have two options:
* Torrent: [16-bit](https://archive.org/details/gpt4chan_model_float16) / [32-bit](https://archive.org/details/gpt4chan_model)
* Direct download: [16-bit](https://theswissbay.ch/pdf/_notpdf_/gpt4chan_model_float16/) / [32-bit](https://theswissbay.ch/pdf/_notpdf_/gpt4chan_model/)
2022-12-21 14:49:30 -05:00
## Converting to pytorch
2023-01-05 23:41:52 -05:00
The script `convert-to-torch.py` allows you to convert models to .pt format, which is about 10x faster to load:
2022-12-21 14:49:30 -05:00
python convert-to-torch.py models/model-name/
2023-01-05 23:44:40 -05:00
The output model will be saved to `torch-dumps/model-name.pt`. When you load a new model, the webui first looks for this .pt file; if it is not found, it loads the model as usual from `models/model-name/`.
2022-12-21 14:49:30 -05:00
2022-12-21 11:17:06 -05:00
## Starting the webui
conda activate textgen
python server.py
2023-01-06 18:00:58 -05:00
Then browse to
`http://localhost:7860/?__theme=dark`
#### Command-line flags
* `--model MODEL`: load this model by default.
2022-12-21 14:52:23 -05:00
2023-01-05 23:33:21 -05:00
## Presets
Inference settings presets can be created under `presets/` as text files. These files are detected automatically at startup.
2022-12-21 14:52:23 -05:00
## Contributing
Pull requests are welcome.