6.1 KiB
text-generation-webui
A gradio webui for running large language models like gpt-j-6B, gpt-neo, opt, galactica and pygmalion on your own computer.
Its goal is to become the AUTOMATIC1111/stable-diffusion-webui of text generation.
Features
- Switch between different models using a dropdown menu.
- Generate nice HTML output for GPT-4chan.
- Generate Markdown output for GALACTICA, including LaTeX support.
- Notebook mode that resembles OpenAI's playground.
- Chat mode for conversation and role playing.
- Load parameter presets from text files.
- Load large models in 8-bit mode.
- Split large models across your GPU(s) and CPU.
- CPU mode.
- Get responses via API.
Installation
-
You need to have the conda environment manager installed into your system. If you don't have it already, get miniconda here.
-
Open a terminal window and create a conda environment:
conda create -n textgen
conda activate textgen
- Install the appropriate pytorch. For NVIDIA GPUs, this should work:
conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
For AMD GPUs, you need the ROCm version of pytorch. If you don't have any GPU and want to run the webui in CPU mode, you just need the stock pytorch and should use this command instead:
conda install pytorch torchvision torchaudio -c pytorch
-
Clone or download this repository, and then
cd
into its directory from your terminal window. -
Install the required Python libraries:
pip install -r requirements.txt
After these steps, you should be able to start the webui, but first you need to download some model to load.
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:
The 32-bit version is only relevant if you intend to run the model in CPU mode. Otherwise, you should use the 16-bit version.
After downloading the model, follow these steps:
- Place the files under
models/gpt4chan_model_float16
ormodels/gpt4chan_model
. - Place GPT-J-6B's config.json file in that same folder: config.json.
- Download GPT-J-6B under
models/gpt-j-6B
:
python download-model.py EleutherAI/gpt-j-6B
You don't really need all of GPT-J's files, just the tokenizer files, but you might as well download the whole thing. Those files will be automatically detected when you attempt to load GPT-4chan.
Converting to pytorch (optional)
The script convert-to-torch.py
allows you to convert models to .pt format, which is about 10x faster to load to the GPU:
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:
-h, --help show this help message and exit
--model MODEL Name of the model to load by default.
--notebook Launch the webui in notebook mode, where the output is written to the same text
box as the input.
--chat Launch the webui in chat mode.
--cpu Use the CPU to generate text.
--auto-devices Automatically split the model across the available GPU(s) and CPU.
--load-in-8bit Load the model with 8-bit precision.
--no-listen Make the webui unreachable from your local network.
Presets
Inference settings presets can be created under presets/
as text files. These files are detected automatically at startup.
System requirements
Check the wiki for some examples of VRAM and RAM usage in both GPU and CPU mode.
Contributing
Pull requests, suggestions and issue reports are welcome.
Other projects
Make sure to also check out the great work by KoboldAI. I have borrowed some of the presets listed on their wiki after performing a k-means clustering analysis to select the most relevant subsample.