---
base_model:
- open-r1/Qwen2.5-Math-7B-RoPE-300k
- Qwen/Qwen2.5-Math-7B
datasets:
- Elliott/Openr1-Math-46k-8192
license: mit
pipeline_tag: text-generation
library_name: transformers
arxiv: 2506.19767
---

# 📄 Introduction

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

Paper: [arXiv](https://arxiv.org/abs/2506.19767)

Project Website: [SRFT](https://anonymous.4open.science/w/SRFT2025)

# File information

The repository contains the following file information:

Filename: model.safetensors.index.json
Content: {
  "metadata": {
    "total_size": 30462466048
  },
  "weight_map": {
    "lm_head.weight": "model-00007-of-00007.safetensors",
    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
    "model.layers.23.mlp.down