AI/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-10-01 01:26:03 -04:00
Code Issues Packages Projects Releases Wiki Activity

Installation instructions

Browse Source
This commit is contained in:
oobabooga 2023-01-13 01:37:12 -03:00
parent 323aaa074f
commit 44b4274ec2
1 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@ -23,7 +23,7 @@ Its goal is to become the [AUTOMATIC1111/stable-diffusion-webui](https://github.
1. You need to have the conda environment manager installed into your system. If you don't have it already, [get miniconda here](https://docs.conda.io/en/latest/miniconda.html). 1. You need to have the conda environment manager installed into your system. If you don't have it already, [get miniconda here](https://docs.conda.io/en/latest/miniconda.html).
2. Then open a terminal window and create a conda environment: 2. Open a terminal window and create a conda environment:
``` ```
conda create -n textgen conda create -n textgen
@ -36,7 +36,7 @@ conda activate textgen
conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
``` ```
For AMD GPUs, you need the ROCm version of pytorch. For running exclusively on the CPU, you just need the stock pytorch and this should probably work: For AMD GPUs, you need the ROCm version of pytorch. If you don't have any GPU and want to run in CPU mode, you just need the stock pytorch and this should work:
``` ```
conda install pytorch torchvision torchaudio -c pytorch conda install pytorch torchvision torchaudio -c pytorch
@ -83,21 +83,23 @@ For instance:
* Torrent: [16-bit](https://archive.org/details/gpt4chan_model_float16) / [32-bit](https://archive.org/details/gpt4chan_model) * 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/) * Direct download: [16-bit](https://theswissbay.ch/pdf/_notpdf_/gpt4chan_model_float16/) / [32-bit](https://theswissbay.ch/pdf/_notpdf_/gpt4chan_model/)
Then follow these steps to install: The 32-bit version is only relevant if you intend to run the model in CPU mode. Otherwise, I recommend using the 16-bit version.
1. Place the files under `models/gpt4chan_model_float16` or `models/gpt4chan_model` After downloading the model, follow these steps:
2. Place GPT-J-6B's config.json file in that same folder: [config.json](https://huggingface.co/EleutherAI/gpt-j-6B/raw/main/config.json)
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](https://huggingface.co/EleutherAI/gpt-j-6B/raw/main/config.json).
3. Download GPT-J-6B under `models/gpt-j-6B`: 3. Download GPT-J-6B under `models/gpt-j-6B`:
``` ```
python download-model.py EleutherAI/gpt-j-6B python download-model.py EleutherAI/gpt-j-6B
``` ```
You don't really need all of GPT-J's files, just the tokenizer files, but you might as well download the whole thing. Those files will be automatically detected when you attempt to load gpt4chan. You don't really need all of GPT-J's files, just the tokenizer files, but you might as well download the whole thing. Those files will be automatically detected when you attempt to load GPT-4chan.
#### Converting to pytorch (optional) #### Converting to pytorch (optional)
The script `convert-to-torch.py` allows you to convert models to .pt format, which is about 10x faster to load: The script `convert-to-torch.py` allows you to convert models to .pt format, which is about 10x faster to load to the GPU:
python convert-to-torch.py models/model-name python convert-to-torch.py models/model-name