https://github.com/fareedkhan-dev/improve-weak-llm-using-spin-technique
After RLHF and SFT show promising results, a new technique named SPIN is invented for 2024
https://github.com/fareedkhan-dev/improve-weak-llm-using-spin-technique
finetuning gemini large-language-models llm rlhf
Last synced: 3 months ago
JSON representation
After RLHF and SFT show promising results, a new technique named SPIN is invented for 2024
- Host: GitHub
- URL: https://github.com/fareedkhan-dev/improve-weak-llm-using-spin-technique
- Owner: FareedKhan-dev
- Created: 2024-01-10T06:25:44.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-01-17T02:59:51.000Z (over 1 year ago)
- Last Synced: 2024-01-17T09:56:47.620Z (over 1 year ago)
- Topics: finetuning, gemini, large-language-models, llm, rlhf
- Homepage: https://medium.com/gitconnected/convert-weak-llm-to-strong-llm-using-spin-technique-9a083d3811df
- Size: 10.7 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0