Yuqian-Fu
/

SRFT-Qwen2.5-Math-7B

Text Generation

text-generation-inference

Model card Files Files and versions Community

📄 Introduction

Supervised Reinforcement Fine-Tuning (SRFT) is a single-stage method that unifies both fine-tuning paradigms through entropy-aware weighting mechanisms.

Paper: arXiv

Project Website: SRFT

Downloads last month: 19

Safetensors

Model size

7.62B params

Tensor type

F32

·

Model tree for Yuqian-Fu/SRFT-Qwen2.5-Math-7B

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Math-7B

Finetuned

(583)

this model

Quantizations

Dataset used to train Yuqian-Fu/SRFT-Qwen2.5-Math-7B

Collection including Yuqian-Fu/SRFT-Qwen2.5-Math-7B

SRFT

3 items • Updated Jun 25