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

Model

📄 Introduction

9 commits

1 linked in READMEs

updated Jul 24, 2025

See the code

README

📄 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

conversational

endpoints_compatible

qwen2

safetensors

text-generation

text-generation-inference

transformers

Contributors

Yuqian-Fu

5 commits

nielsr

2 commits

Yuqian Fu

2 commits

Similar repos

sunblaze-ucb/Qwen2.5-1.5B-GRPO-MATH-1EPOCH

Model

Qwen2.5-1.5B-GRPO-MATH-1EPOCH

openbmb/RLPR-Qwen2.5-7B-Base

Model

Model Card for RLPR-Qwen2.5-7B-Base

xinlai/Qwen2-7B-SFT

Model

sunblaze-ucb/Qwen2.5-3B-GRPO-MATH-1EPOCH

Model

Qwen2.5-3B-GRPO-MATH-1EPOCH

xinlai/Qwen2-72B-SFT

Model

sunblaze-ucb/Qwen2.5-3B-Intuitor-MATH-1EPOCH

Model

Qwen2.5-3B-Intuitor-MATH-1EPOCH

lllyx/Qwen3-1.7B-SFT

Model

Qwen3-1.7B-SFT is a supervised fine-tuned model based on Qwen3-1.7B-Base, trained on the…

sunblaze-ucb/Qwen2.5-1.5B-Intuitor-MATH-1EPOCH

Model

Qwen2.5-1.5B-Intuitor-MATH-1EPOCH

Linked in READMEs

AheadOFpotato/Awesome-LRM-Mechanisms

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and…

README badge

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

Model

📄 Introduction

9 commits

1 linked in READMEs

updated Jul 24, 2025

See the code

README

📄 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

conversational

endpoints_compatible

qwen2

safetensors

text-generation

text-generation-inference

transformers