Miraclemarvel55/LLaMA-MOSS-RLHF-LoRA

用RLHF可选LoRA对LLaMA和MOSS进行训练|Training LLaMA or MOSS with RLHF [LoRA]

26
/ 100
Experimental

This project allows you to customize the personality and self-perception of large language models like LLaMA or MOSS. You provide details like your name and a nickname for the AI, and the tool uses a technique called RLHF (Reinforcement Learning from Human Feedback) to integrate these into the model's responses. The output is a fine-tuned model that recognizes you as its 'master' and uses its new nickname. This is for AI practitioners or researchers who want to personalize open-source LLMs.

No commits in the last 6 months.

Use this if you want to fine-tune an existing open-source LLaMA or MOSS model to recognize specific 'master' and 'nickname' identities.

Not ideal if you need to perform complex batch processing of prompts or if you lack access to significant GPU resources.

LLM-fine-tuning AI-personalization natural-language-processing chatbot-customization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

21

Forks

1

Language

Python

License

GPL-3.0

Last pushed

May 16, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Miraclemarvel55/LLaMA-MOSS-RLHF-LoRA"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.