A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
Go to file
2023-03-06 20:55:01 -03:00
characters Change Chiharu's example dialogue definition format 2023-02-28 01:13:58 -03:00
extensions Improve readability 2023-03-06 19:46:46 -03:00
models Add the default folders 2023-01-06 02:38:09 -03:00
modules Add --rwkv-cuda-on parameter, bump rwkv version 2023-03-06 20:12:54 -03:00
presets Change some parameters 2023-03-06 16:29:43 -03:00
softprompts Add softprompt support (for real this time) 2023-02-13 15:25:16 -03:00
.gitignore Rename the folder 2023-03-06 19:38:36 -03:00
api-example-stream.py Add credits 2023-03-06 20:34:36 -03:00
api-example.py Fix the API 2023-02-24 17:38:15 -03:00
convert-to-flexgen.py Improve the imports 2023-02-23 14:41:42 -03:00
convert-to-safetensors.py Improve the imports 2023-02-23 14:41:42 -03:00
download-model.py Fix the download script (sort of) 2023-03-02 14:05:21 -03:00
LICENSE Initial commit 2022-12-21 01:17:38 -03:00
README.md Update README.md 2023-03-06 20:55:01 -03:00
requirements.txt Add --rwkv-cuda-on parameter, bump rwkv version 2023-03-06 20:12:54 -03:00
server.py Load settings.json without the need for --settings settings.json 2023-03-06 10:57:45 -03:00
settings-template.json Model-aware prompts and presets 2023-03-02 11:25:04 -03:00

Text generation web UI

A gradio web UI for running Large Language Models like GPT-J 6B, OPT, GALACTICA, GPT-Neo, 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, here and here if you are on Windows).
  • Split large models across your GPU(s), CPU, and disk.
  • CPU mode.
  • FlexGen offload.
  • DeepSpeed ZeRO-3 offload.
  • Get responses via API, with or without streaming.
  • Supports the RWKV model.
  • 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.
--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 [GPU_MEMORY ...] Maxmimum GPU memory in GiB to be allocated per GPU. Example: --gpu-memory 10 for a single GPU, --gpu-memory 10 5 for two GPUs.
--cpu-memory CPU_MEMORY Maximum CPU memory in GiB to allocate for offloaded weights. Must be an integer number. Defaults to 99.
--flexgen Enable the use of FlexGen offloading.
--percent PERCENT [PERCENT ...] FlexGen: allocation percentages. Must be 6 numbers separated by spaces (default: 0, 100, 100, 0, 100, 0).
--compress-weight FlexGen: Whether to compress weight (default: False).
--pin-weight [PIN_WEIGHT] FlexGen: whether to pin weights (setting this to False reduces CPU memory by 20%).
--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.
--rwkv-strategy RWKV_STRATEGY RWKV: The strategy to use while loading the model. Examples: "cpu fp32", "cuda fp16", "cuda fp16i8".
--rwkv-cuda-on RWKV: Compile the CUDA kernel for better performance.
--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. If you create a file called settings.json, this file will be loaded by default without the need to use the --settings flag.
--extensions EXTENSIONS [EXTENSIONS ...] The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.
--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