A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
Go to file
2023-02-21 00:54:53 -03:00
characters Remove .gitignore 2023-02-02 12:42:49 -03:00
extensions Make it possible to disable the TTS from within the interface 2023-02-16 23:38:27 -03:00
models Add the default folders 2023-01-06 02:38:09 -03:00
modules Add some more margin 2023-02-20 20:49:21 -03:00
presets Reorganize the generation parameters 2023-02-17 16:18:01 -03:00
softprompts Add softprompt support (for real this time) 2023-02-13 15:25:16 -03:00
.gitignore Add .gitignore 2023-02-16 13:35:54 -03:00
api-example.py Add an example of usage for the API 2023-02-20 12:39:36 -03:00
convert-to-safetensors.py Add bf16 back here (the fp16 -> bf16 conversion takes a few seconds) 2023-02-21 00:54:53 -03:00
download-model.py Convert the download option (A-Z) to upper case 2023-02-20 15:50:48 -03:00
LICENSE Initial commit 2022-12-21 01:17:38 -03:00
README.md Deprecate torch dumps, move to safetensors (they load even faster) 2023-02-20 15:03:19 -03:00
requirements.txt Bump accelerate version 2023-02-18 22:15:47 -03:00
server.py Fix regex bug in loading character jsons with special characters 2023-02-20 19:38:19 -03:00
settings-template.json Set chat prompt size in tokens 2023-02-15 10:18:50 -03:00

Text generation web UI

A gradio web UI for running Large Language Models like gpt-j-6B, gpt-neo, opt, galactica, and pygmalion.

Its goal is to become the AUTOMATIC1111/stable-diffusion-webui of text generation.

[Try it on Google Colab]

Image1 Image2
Image3 Image4

Features

  • Switch between different models using a dropdown menu.
  • Notebook mode that resembles OpenAI's playground.
  • Chat mode for conversation and role playing.
  • Generate nice HTML output for GPT-4chan.
  • Generate Markdown output for GALACTICA, including LaTeX support.
  • Support for Pygmalion and custom characters in JSON or TavernAI Character Card formats (FAQ).
  • Advanced chat features (send images, get audio responses with TTS).
  • Stream the text output in real time.
  • Load parameter presets from text files.
  • Load large models in 8-bit mode (see here if you are on Windows).
  • Split large models across your GPU(s), CPU, and disk.
  • CPU mode.
  • DeepSpeed ZeRO-3 offload.
  • Get responses via API.
  • Supports softprompts.
  • Supports extensions.
  • Works on Google Colab.

Installation option 1: conda

Open a terminal and copy and paste these commands one at a time (install conda first if you don't have it already):

conda create -n textgen
conda activate textgen
conda install torchvision torchaudio pytorch-cuda=11.7 git -c pytorch -c nvidia
git clone https://github.com/oobabooga/text-generation-webui
cd text-generation-webui
pip install -r requirements.txt

The third line assumes that you have an NVIDIA GPU.

  • If you have an AMD GPU, replace the third command with this one:
pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/rocm5.2
  • If you are running in CPU mode, replace the third command with this one:
conda install pytorch torchvision torchaudio git -c pytorch

Installation option 2: one-click installers

oobabooga-windows.zip

oobabooga-linux.zip

Just download the zip above, extract it, and double click on "install". The web UI and all its dependencies will be installed in the same folder.

  • To download a model, double click on "download-model"
  • To start the web UI, double click on "start-webui"

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:

You can automatically download a model from HF using the script download-model.py:

python download-model.py organization/model

For instance:

python download-model.py facebook/opt-1.3b

If you want to download a model manually, note that all you need are the json, txt, and pytorch*.bin (or model*.safetensors) files. The remaining files are not necessary.

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:

  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's tokenizer files (they will be automatically detected when you attempt to load GPT-4chan):
python download-model.py EleutherAI/gpt-j-6B --text-only

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 img_bot.png or img_bot.jpg exists in the same folder as server.py, this image will be used as the bot's profile picture. Similarly, img_me.png or img_me.jpg will be used as your profile picture.
--picture Adds an ability to send pictures in chat UI modes. Captions are generated by BLIP.
--cpu Use the CPU to generate text.
--load-in-8bit Load the model with 8-bit precision.
--bf16 Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.
--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.
--disk-cache-dir DISK_CACHE_DIR Directory to save the disk cache to. Defaults to cache/.
--gpu-memory GPU_MEMORY Maximum GPU memory in GiB to allocate. This is useful if you get out of memory errors while trying to generate text. Must be an integer number.
--cpu-memory CPU_MEMORY Maximum CPU memory in GiB to allocate for offloaded weights. Must be an integer number. Defaults to 99.
--deepspeed Enable the use of DeepSpeed ZeRO-3 for inference via the Transformers integration.
--nvme-offload-dir NVME_OFFLOAD_DIR DeepSpeed: Directory to use for ZeRO-3 NVME offloading.
--local_rank LOCAL_RANK DeepSpeed: Optional argument for distributed setups.
--no-stream Don't stream the text output in real time. This improves the text generation performance.
--settings SETTINGS_FILE Load the default interface settings from this json file. See settings-template.json for an example.
--extensions EXTENSIONS The list of extensions to load. If you want to load more than one extension, write the names separated by commas and between quotation marks, "like,this".
--listen Make the web UI reachable from your local network.
--listen-port LISTEN_PORT The listening port that the server will use.
--share Create a public URL. This is useful for running the web UI on Google Colab or similar.
--verbose Print the prompts to the terminal.

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.

By default, 10 presets by NovelAI and KoboldAI are included. These were selected out of a sample of 43 presets after applying a K-Means clustering algorithm and selecting the elements closest to the average of each cluster.

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.

Before reporting a bug, make sure that you have created a conda environment and installed the dependencies exactly as in the Installation section above.

These issues are known:

  • 8-bit doesn't work properly on Windows or older GPUs.
  • DeepSpeed doesn't work properly on Windows.

For these two, please try commenting on an existing issue instead of creating a new one.

Credits