policy

Qwen2.5-3B-Instruct-Reasoning-Enhanced-with-Unsloth-and-GRPO-on-GSM8K

siddhudonda · PyTorch

or hover any field below to flag it

Overview

Name
Qwen2.5-3B-Instruct-Reasoning-Enhanced-with-Unsloth-and-GRPO-on-GSM8K
Author
siddhudonda
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
This project enhances the Qwen2.5-3B-Instruct model by integrating advanced reasoning capabilities using Unsloth. Additionally, it leverages GRPO, a reinforcement learning policy, for optimized performance. Trained and fine-tuned on the GSM8K dataset to improve problem-solving and inference.

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 Qwen2.5-3B-Instruct-Reasoning-Enhanced-with-Unsloth-and-GRPO-on-GSM8K yet.

Datasets that reference this policy

0

No datasets reference Qwen2.5-3B-Instruct-Reasoning-Enhanced-with-Unsloth-and-GRPO-on-GSM8K yet.