policy

Co-rewarding-I-Qwen3-8B-Base-MATH

TMLR-Group-HF · PyTorch

or hover any field below to flag it

Overview

Name
Co-rewarding-I-Qwen3-8B-Base-MATH
Author
TMLR-Group-HF
Framework
PyTorch
License
mit
Skill type
other
Evidence level
untested
Task description
Policy model: Co-rewarding-I-Qwen3-8B-Base-MATH. Tags: transformers, safetensors, qwen3, text-generation, conversational.

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

Paper (arXiv)
null

Compatible robots

20

Compatible environments

0

No environments list Co-rewarding-I-Qwen3-8B-Base-MATH yet.

Datasets that reference this policy

0

No datasets reference Co-rewarding-I-Qwen3-8B-Base-MATH yet.