text-generation-webui/README.md

# text-generation-webui
A gradio webui for running large language models locally. Supports gpt-j-6B, gpt-neox-20b, opt, galactica, and many others.

![webui screenshot](https://github.com/oobabooga/text-generation-webui/raw/main/webui.png)

## Installation

    conda env create -f environment.yml

## Downloading models

Models should be placed under `models/model-name`.

#### Hugging Face

Hugging Face is the main place to download models. For instance, [here](https://huggingface.co/EleutherAI/gpt-j-6B/tree/main) you can find the files for the model gpt-j-6B.

The files that you need to download and put under `models/gpt-j-6B` are the json, txt, and pytorch*.bin files. The remaining files are not necessary.

#### GPT-4chan

[GPT-4chan](https://huggingface.co/ykilcher/gpt-4chan) has been shut down from Hugging Face, so you need to download it elsewhere. You have two options:

* Torrent: [16-bit](https://archive.org/details/gpt4chan_model_float16) / [32-bit](https://archive.org/details/gpt4chan_model)
* Direct download: [16-bit](https://theswissbay.ch/pdf/_notpdf_/gpt4chan_model_float16/) / [32-bit](https://theswissbay.ch/pdf/_notpdf_/gpt4chan_model/)

## Starting the webui

    conda activate textgen
    python server.py

Then browse to `http://localhost:7860/?__theme=dark`
Initial commit 2022-12-20 23:17:38 -05:00			`# text-generation-webui`
			`A gradio webui for running large language models locally. Supports gpt-j-6B, gpt-neox-20b, opt, galactica, and many others.`
Initial commit 2022-12-21 11:17:06 -05:00
Update README.md 2022-12-21 12:04:51 -05:00			`![webui screenshot](https://github.com/oobabooga/text-generation-webui/raw/main/webui.png)`

Initial commit 2022-12-21 11:17:06 -05:00			`## Installation`

			`conda env create -f environment.yml`

Update README.md 2022-12-21 12:37:50 -05:00			`## Downloading models`

			Models should be placed under `models/model-name`.

Update README.md 2022-12-21 13:00:16 -05:00			`#### Hugging Face`
Update README.md 2022-12-21 12:37:50 -05:00
			`Hugging Face is the main place to download models. For instance, [here](https://huggingface.co/EleutherAI/gpt-j-6B/tree/main) you can find the files for the model gpt-j-6B.`

			The files that you need to download and put under `models/gpt-j-6B` are the json, txt, and pytorch*.bin files. The remaining files are not necessary.

Update README.md 2022-12-21 13:00:16 -05:00			`#### GPT-4chan`
Update README.md 2022-12-21 12:37:50 -05:00
			`[GPT-4chan](https://huggingface.co/ykilcher/gpt-4chan) has been shut down from Hugging Face, so you need to download it elsewhere. You have two options:`

			`* Torrent: [16-bit](https://archive.org/details/gpt4chan_model_float16) / [32-bit](https://archive.org/details/gpt4chan_model)`
			`* Direct download: [16-bit](https://theswissbay.ch/pdf/_notpdf_/gpt4chan_model_float16/) / [32-bit](https://theswissbay.ch/pdf/_notpdf_/gpt4chan_model/)`

Initial commit 2022-12-21 11:17:06 -05:00			`## Starting the webui`

			`conda activate textgen`
			`python server.py`

			Then browse to `http://localhost:7860/?__theme=dark`