text-generation-webui/README.md

Text generation web UI

A gradio web UI 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.
• Text output is streamed in real time.
• 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

1. You need to have the conda environment manager installed on your system. If you don't have it already, get miniconda here.

2. Open a terminal window and create a conda environment:

conda create -n textgen
conda activate textgen

3. 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 a GPU and want to run the web UI in CPU mode, you just need the standard pytorch and should use this command instead:

conda install pytorch torchvision torchaudio -c pytorch

4. Clone or download this repository, and then cd into its folder from your terminal window.

5. Install the required Python libraries:

pip install -r requirements.txt

After these steps, you should be able to start the web UI, 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 noteworthy examples:

• GPT-J 6B
• GPT-Neo
• OPT
• GALACTICA
• *-Erebus
• Pygmalion

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:

• Torrent: 16-bit / 32-bit
• Direct download: 16-bit / 32-bit

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:

1. Place the files under models/gpt4chan_model_float16 or models/gpt4chan_model.
2. Place GPT-J 6B's config.json file in that same folder: config.json.
3. 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 6B'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 web UI first looks for this .pt file; if it is not found, it loads the model as usual from models/model-name.

Starting the web UI

conda activate textgen
python server.py

Then browse to

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

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

Flag	Description
-h, --help	show this help message and exit
--model MODEL	Name of the model to load by default.
--notebook	Launch the web UI in notebook mode, where the output is written to the same text box as the input.
--chat	Launch the web UI in chat mode.
--cai-chat	Launch the web UI in chat mode with a style similar to Character.AI's. If the file profile.png or profile.jpg exists in the same folder as server.py, this image will be used as the bot's profile picture.
--cpu	Use the CPU to generate text.
--load-in-8bit	Load the model with 8-bit precision.
--auto-devices	Automatically split the model across the available GPU(s) and CPU.
--disk	If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.
--max-gpu-memory MAX_GPU_MEMORY	Maximum memory in GiB to allocate to the GPU when loading the model. This is useful if you get out of memory errors while trying to generate text. Must be an integer number.
--no-listen	Make the web UI unreachable from your local network.
--no-stream	Don't stream the text output in real time. This slightly improves the text generation performance.
--settings SETTINGS_FILE	Load the default interface settings from this json file. See settings-template.json for an example.

Out of memory errors? Check this guide.

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.

Credits

• NovelAI and KoboldAI presets: https://github.com/KoboldAI/KoboldAI-Client/wiki/Settings-Presets
• Pygmalion preset: https://github.com/PygmalionAI/gradio-ui/blob/master/src/gradio_ui.py
• Verbose preset: Anonymous 4chan user.