policy
weibo_robert_llm
ChenChiShui · PyTorch
or hover any field below to flag it
Overview
Name
weibo_robert_llm
Author
ChenChiShui
Framework
PyTorch
License
MIT
Skill type
other
Evidence level
untested
Task description
Weibo Robert LLM 基于 Qwen3-4B 和 CommentR Interaction Dataset 的微博评论机器人训练项目，通过多阶段训练（SFT → Reward Model → RL）学习生成符合人类偏好的高质量评论回复。
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 weibo_robert_llm yet.
Datasets that reference this policy
0No datasets reference weibo_robert_llm yet.