Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-12-26 14:20:40 +01:00
Code Issues Packages Projects Releases Wiki Activity
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
46 Commits 7 Branches 53 Tags 70 MiB
Python 89.2%
CSS 4%
JavaScript 3.9%
Shell 1.3%
Batchfile 0.7%
Other 0.9%
3aaf5fb4aa
Go to file
oobabooga 3aaf5fb4aa Make NovelAI-Sphinx Moth the default preset
2023-01-07 00:49:47 -03:00
models Add the default folders 2023-01-06 02:38:09 -03:00
presets Add new presets 2023-01-06 19:58:19 -03:00
torch-dumps Add folder 2023-01-06 10:08:17 -03:00
convert-to-torch.py Clean the convert to torch script 2023-01-07 00:04:52 -03:00
download-model.py Add script to download models 2023-01-06 19:57:31 -03:00
html_generator.py Add HTML support for gpt4chan 2023-01-06 23:14:08 -03:00
LICENSE Initial commit 2022-12-21 01:17:38 -03:00
README.md Update the README 2023-01-06 20:29:00 -03:00
requirements.txt Add script to download models 2023-01-06 19:57:31 -03:00
server.py Make NovelAI-Sphinx Moth the default preset 2023-01-07 00:49:47 -03:00
webui.png Add files via upload 2022-12-21 14:04:15 -03:00

README.md

text-generation-webui

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 of text generation.

webui screenshot

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

Downloading models

Models should be placed under models/model-name. For instance, models/gpt-j-6B for gpt-j-6B.

Hugging Face

Hugging Face is the main place to download models. These are some of my favorite:

The files that you need to download are the json, txt, and pytorch*.bin files. The remaining files are not necessary.

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

GPT-4chan

GPT-4chan has been shut down from Hugging Face, so you need to download it elsewhere. You have two options:

Converting to pytorch

The script convert-to-torch.py allows you to convert models to .pt format, which is about 10x faster to load:

python convert-to-torch.py models/model-name/

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/.

Starting the webui

conda activate textgen
python server.py

Then browse to

http://localhost:7860/?__theme=dark

Optionally, you can use the following command-line flags:

--model model-name: Load this model by default.

--notebook: Launch the webui in notebook mode, where the output is written to the same text box as the input.

Presets

Inference settings presets can be created under presets/ as text files. These files are detected automatically at startup.

Contributing

Pull requests are welcome.