A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
Go to file
Alex "mcmonkey" Goodwin 459e725af9
Lora trainer docs (#1493)
2023-04-23 12:54:41 -03:00
.github Update stale.yml 2023-03-27 15:12:43 -03:00
characters Add ChatGLM support (#1256) 2023-04-16 19:15:03 -03:00
css SD_api_pictures: Modefix, +hires options, UI layout change (#1400) 2023-04-21 17:49:18 -03:00
docker Rename docker/README.md to docs/Docker.md 2023-04-22 03:03:05 -03:00
docs Lora trainer docs (#1493) 2023-04-23 12:54:41 -03:00
extensions Fix bug in api extension 2023-04-22 17:33:36 -03:00
loras Add dummy file 2023-03-30 21:08:50 -03:00
models Add ChatGLM support (#1256) 2023-04-16 19:15:03 -03:00
modules Lora trainer docs (#1493) 2023-04-23 12:54:41 -03:00
presets Revert the Default preset to a previous version 2023-04-13 13:02:02 -03:00
prompts Don't hardcode prompts in the settings dict/json 2023-03-29 22:47:01 -03:00
softprompts Add softprompt support (for real this time) 2023-02-13 15:25:16 -03:00
training Remove unnecessary file 2023-03-28 13:19:52 -03:00
.gitignore Add "Save current settings for this model" button 2023-04-15 12:54:02 -03:00
api-example-stream.py Update api-example-stream.py 2023-04-19 19:49:52 -03:00
api-example.py Fix stopping strings in the gradio API 2023-04-19 13:52:21 -03:00
convert-to-flexgen.py Make the code more like PEP8 for readability (#862) 2023-04-07 00:15:45 -03:00
convert-to-safetensors.py Make the code more like PEP8 for readability (#862) 2023-04-07 00:15:45 -03:00
download-model.py Add "do not download" and "download from HF" to download-model.py (#1439) 2023-04-21 12:54:50 -03:00
LICENSE Initial commit 2022-12-21 01:17:38 -03:00
README.md Change GPTQ triton default settings 2023-04-22 12:27:30 -03:00
requirements.txt Add an "Evaluate" tab to calculate the perplexities of models (#1322) 2023-04-21 00:20:33 -03:00
server.py Sort imports 2023-04-21 17:20:59 -03:00
settings-template.json Increase truncation_length_max value 2023-04-19 17:35:38 -03:00

Text generation web UI

A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.

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

Image1 Image2
Image3 Image4

Features

Installation

One-click installers

Windows Linux macOS
oobabooga-windows.zip oobabooga-linux.zip oobabooga-macos.zip

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

Manual installation using Conda

Recommended if you have some experience with the command-line.

On Windows, I additionally recommend carrying out the installation on WSL instead of the base system: WSL installation guide.

0. Install Conda

https://docs.conda.io/en/latest/miniconda.html

On Linux or WSL, it can be automatically installed with these two commands:

curl -sL "https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh" > "Miniconda3.sh"
bash Miniconda3.sh

Source: https://educe-ubc.github.io/conda.html

0.1 (Ubuntu/WSL) Install build tools

sudo apt install build-essential

1. Create a new conda environment

conda create -n textgen python=3.10.9
conda activate textgen

2. Install Pytorch

System GPU Command
Linux/WSL NVIDIA pip3 install torch torchvision torchaudio
Linux AMD pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm5.4.2
MacOS + MPS (untested) Any pip3 install torch torchvision torchaudio

The up to date commands can be found here: https://pytorch.org/get-started/locally/.

2.1 Special instructions

3. Install the web UI

git clone https://github.com/oobabooga/text-generation-webui
cd text-generation-webui
pip install -r requirements.txt

Alternative: manual Windows installation

As an alternative to the recommended WSL method, you can install the web UI natively on Windows using this guide. It will be a lot harder and the performance may be slower: Windows installation guide.

Alternative: Docker

ln -s docker/{Dockerfile,docker-compose.yml,.dockerignore} .
cp docker/.env.example .env
# Edit .env and set TORCH_CUDA_ARCH_LIST based on your GPU model
docker compose up --build

You need to have docker compose v2.17 or higher installed in your system. To see how to install docker compose itself, see the guide in here.

Contributed by @loeken in #633

Updating the requirements

From time to time, the requirements.txt changes. To update, use this command:

conda activate textgen
cd text-generation-webui
pip install -r requirements.txt --upgrade

Downloading models

Models should be placed inside the models folder.

Hugging Face is the main place to download models. These are some examples:

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

python download-model.py organization/model

For example:

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
cd text-generation-webui
python server.py

Then browse to

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

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

Basic settings

Flag Description
-h, --help Show this help message and exit.
--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.
--model MODEL Name of the model to load by default.
--lora LORA Name of the LoRA to apply to the model by default.
--model-dir MODEL_DIR Path to directory with all the models.
--lora-dir LORA_DIR Path to directory with all the loras.
--model-menu Show a model menu in the terminal when the web UI is first launched.
--no-stream Don't stream the text output in real time.
--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.
--verbose Print the prompts to the terminal.

Accelerate/transformers

Flag Description
--cpu Use the CPU to generate text. Warning: Training on CPU is extremely slow.
--auto-devices Automatically split the model across the available GPU(s) and CPU.
--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. You can also set values in MiB like --gpu-memory 3500MiB.
--cpu-memory CPU_MEMORY Maximum CPU memory in GiB to allocate for offloaded weights. Same as above.
--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/.
--load-in-8bit Load the model with 8-bit precision.
--bf16 Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.
--no-cache Set use_cache to False while generating text. This reduces the VRAM usage a bit with a performance cost.
--xformers Use xformer's memory efficient attention. This should increase your tokens/s.
--sdp-attention Use torch 2.0's sdp attention.
--trust-remote-code Set trust_remote_code=True while loading a model. Necessary for ChatGLM.

llama.cpp

Flag Description
--threads Number of threads to use in llama.cpp.

GPTQ

Flag Description
--wbits WBITS Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.
--model_type MODEL_TYPE Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported.
--groupsize GROUPSIZE Group size.
--pre_layer PRE_LAYER The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models.
--monkey-patch Apply the monkey patch for using LoRAs with quantized models.
--quant_attn (triton) Enable quant attention.
--warmup_autotune (triton) Enable warmup autotune.
--fused_mlp (triton) Enable fused mlp.

FlexGen

Flag Description
--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

Flag Description
--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

Flag Description
--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.

Gradio

Flag Description
--listen Make the web UI reachable from your local network.
--listen-host LISTEN_HOST The hostname that the server will use.
--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.
--auto-launch Open the web UI in the default browser upon launch.
--gradio-auth-path GRADIO_AUTH_PATH Set the gradio authentication file path. The file should contain one or more user:password pairs in this format: "u1:p1,u2:p2,u3:p3"

Out of memory errors? Check the low VRAM 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.

Visualization

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.

You are also welcome to review open pull requests.

Before reporting a bug, make sure that you have:

  1. Created a conda environment and installed the dependencies exactly as in the Installation section above.
  2. Searched to see if an issue already exists for the issue you encountered.

Credits