TideDra/VL-RLHF
A RLHF Infrastructure for Vision-Language Models
This project provides a robust framework for refining how Vision-Language Models (VLMs) understand and generate responses based on human preferences. It allows researchers and AI developers to input raw VLM models and preference-based datasets, then output fine-tuned models that align better with desired human-like interactions and evaluations. The primary users are AI researchers and machine learning engineers focused on improving VLM performance and alignment.
198 stars. No commits in the last 6 months.
Use this if you are an AI researcher or machine learning engineer looking to fine-tune existing Vision-Language Models (VLMs) like LLaVA or Qwen-VL using methods like DPO to better align them with human preferences or specific task requirements.
Not ideal if you are an end-user without a background in AI development, as this is an infrastructure tool for model training, not a ready-to-use application.
Stars
198
Forks
8
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/TideDra/VL-RLHF"
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.