policy
RLHF-finetune-pipeline
prtk1729 · PyTorch
or hover any field below to flag it
Overview
Name
RLHF-finetune-pipeline
Author
prtk1729
Framework
PyTorch
License
MIT
Skill type
other
Evidence level
untested
Task description
A complete pipeline for fine-tuning language models using RLHF, inspired by ChatGPT. Includes reward model training, supervised fine-tuning (SFT), and reinforcement learning via PPO. Features pre-trained models, scripts for rollout generation, KL regularization, and training loops to align models wi
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list RLHF-finetune-pipeline yet.
Datasets that reference this policy
0No datasets reference RLHF-finetune-pipeline yet.