Text generation web UI

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

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

[Try it on Google Colab]

Features

• Dropdown menu for switching between models
• Notebook mode that resembles OpenAI's playground
• Chat mode for conversation and role playing
• Nice HTML output for GPT-4chan
• Markdown output for GALACTICA, including LaTeX rendering
• Custom chat characters in JSON format (FAQ)
• Advanced chat features (send images, get audio responses with TTS)
• Very efficient text streaming
• Parameter presets
• 8-bit mode
• Layers splitting across GPU(s), CPU, and disk
• CPU mode
• FlexGen
• DeepSpeed ZeRO-3
• API with streaming and without streaming
• LLaMA model, including 4-bit GPTQ
• llama.cpp *NEW!*
• RWKV model
• LoRa (loading and training)
• Softprompts
• Extensions
• Google Colab

Installation

One-click installers

oobabooga-windows.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"

Source codes: https://github.com/oobabooga/one-click-installers

Note

Thanks to @jllllll and @ClayShoaf, the Windows 1-click installer now sets up 8-bit and 4-bit requirements out of the box. No additional installation steps are necessary.

Note

There is no need to run the installer as admin.

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

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/.

MacOS users, refer to the comments here: https://github.com/oobabooga/text-generation-webui/pull/393

3. Install the web UI

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

Note

For bitsandbytes and --load-in-8bit to work on Linux/WSL, this dirty fix is currently necessary: https://github.com/oobabooga/text-generation-webui/issues/400#issuecomment-1474876859

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

https://github.com/oobabooga/text-generation-webui/issues/174, https://github.com/oobabooga/text-generation-webui/issues/87

Downloading models

Models should be placed inside the models folder.

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

• Pythia
• OPT
• GALACTICA
• GPT-J 6B

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:

• 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'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.
--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.
--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
--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.
--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.

llama.cpp

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

GPTQ

Flag	Description
--wbits WBITS	GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.
--model_type MODEL_TYPE	GPTQ: Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported.
--groupsize GROUPSIZE	GPTQ: Group size.
--pre_layer PRE_LAYER	GPTQ: The number of layers to preload.

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-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.

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

• Gradio dropdown menu refresh button, code for reloading the interface: https://github.com/AUTOMATIC1111/stable-diffusion-webui
• Verbose preset: Anonymous 4chan user.
• NovelAI and KoboldAI presets: https://github.com/KoboldAI/KoboldAI-Client/wiki/Settings-Presets
• Code for early stopping in chat mode, code for some of the sliders: https://github.com/PygmalionAI/gradio-ui/