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]
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.
Stars
21
Forks
1
Language
Python
License
GPL-3.0
Category
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.
Higher-rated alternatives
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama,...
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5,...
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training