Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-12-25 05:48:55 +01:00
Code Issues Packages Projects Releases Wiki Activity

Mention gpt4chan's config.json

Browse Source
This commit is contained in:
oobabooga 2023-01-07 23:13:43 -03:00
parent ef4e610d37
commit a0b1b1beb2
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -62,6 +62,8 @@ 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/)
You also need to put GPT-J-6B's config.json file in the same folder: [config.json](https://huggingface.co/EleutherAI/gpt-j-6B/raw/main/config.json)
## Converting to pytorch ## Converting to pytorch
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: