https://github.com/sanjeevanahilan/nanochatgpt
A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick
https://github.com/sanjeevanahilan/nanochatgpt
Last synced: 4 days ago
JSON representation
A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick
- Host: GitHub
- URL: https://github.com/sanjeevanahilan/nanochatgpt
- Owner: sanjeevanahilan
- License: mit
- Fork: true (karpathy/nanoGPT)
- Created: 2023-02-23T17:18:35.000Z (about 2 years ago)
- Default Branch: master
- Last Pushed: 2023-11-25T16:46:12.000Z (over 1 year ago)
- Last Synced: 2024-11-09T19:39:32.207Z (6 months ago)
- Language: Python
- Homepage:
- Size: 965 KB
- Stars: 287
- Watchers: 8
- Forks: 25
- Open Issues: 0
Awesome Lists containing this project
- awesome-ChatGPT-repositories - nanoChatGPT - A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick (Others)