ducnh279/Align-LLMs-with-DPO
Align a Large Language Model (LLM) with DPO loss
This project helps machine learning engineers or researchers fine-tune Large Language Models (LLMs) to better align with human preferences. You provide an LLM and a dataset of preferred and dispreferred responses, and it outputs a fine-tuned LLM that generates more desirable text. This is for professionals working on improving the behavior and safety of AI models.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking to apply Direct Preference Optimization (DPO) to align your LLM using a custom dataset of human preferences.
Not ideal if you are an end-user without a technical background in machine learning and model training, as this is a developer-focused tool for LLM alignment.
Stars
8
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
Jun 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ducnh279/Align-LLMs-with-DPO"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.