policy

trl-ppo-for-docstrings

aaditey932 · PyTorch

or hover any field below to flag it

Overview

Name
trl-ppo-for-docstrings
Author
aaditey932
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
End-to-end RLHF-style pipeline: train a language model to write Python docstrings via SFT, preference pairs, a reward model, and PPO (Qwen/HF + TRL).

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 yet

Compatible environments

0

No environments list trl-ppo-for-docstrings yet.

Datasets that reference this policy

0

No datasets reference trl-ppo-for-docstrings yet.