ModelVerificadoExterno

ReflectRL Qwen2.5 Math 7B GRPO

This repository contains model weights trained using ReflectRL, as presented in the paper ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning.

Fuentehuggingface.co/Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO/tree/ef1a1f65b5a557944f5815af0cc6ea84bbace610

TipoText modelModelo baseQwen2.5VersiónmodelPublicador@JinheCcalidad

Fuente del modelo

Tipo: Text model
Tamaño del archivo: 28,4 GB
Modelo base: Qwen2.5
Versión: vmodel
Actualizado: 4 oct 2026
Publicador: @Jinhe
Descargas: 23
Parámetros: 7B
Fuente: Hugging Face

Descripción de la fuente

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning

This repository contains model weights trained using ReflectRL, as presented in the paper ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning.

Paper: ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Repository: GitHub - bibisbar/ReflectRL

Overview

ReflectRL is a lightweight framework for learning from Golden Negative Trajectories (GNTs) during on-policy post-training. Instead of imitating failed expert trajectories directly, ReflectRL uses them as reflective context during training and gradually transitions the policy back to direct reasoning for inference.

Citation

@article{reflectrl2027,
  title={ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning},
  author={Jinhe Bi and Chennan Zhou and Zengjie Jin and Aniri and Shuo Lu and Wenke Huang and Hu Cao and Xun Xiao and Zhihong Zhu and Volker Tresp and Fei Shen and Yunpu Ma and Tat-Seng Chua},
  year={2027}
}

Fuentes

1 fuente

Hugging FacePrincipalVersión ef1a1f65b5a557944f5815af0cc6ea84bbace610

huggingface.co/Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO/tree/ef1a1f65b5a557944f5815af0cc6ea84bbace610

Verificado 4 oct

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 28,4 GB · SHA-256 ad2350a0ca3f…bf2b · Hugging Face

Descargar

Extractos de fuentes

3 extractos

Readme4 octhuggingface.co/Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO

--- license: apache-2.0 library_name: transformers pipeline_tag: text-generation --- # ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning This repository contains model weights trained using **ReflectRL**, as presented in the paper [ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning](https://huggingface.co/papers/2608.03972). - **Paper:** [ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning](https://huggingface.co/papers/2608.03972) - **Repository:** [GitHub - bibisbar/ReflectRL](https://github.com/bibisbar/ReflectRL) ## Overview ReflectRL is a lightweight framework for learning from Golden Negative Trajectories (GNTs) during on-policy post-training. Instead of imitating failed expert trajectories directly, ReflectRL uses them as reflective context during training and gradually transitions the policy back to direct reasoning for inference. ## Citation ```bibtex @article{reflectrl2027, title={ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning}, author={Jinhe Bi and Chennan Zhou and Zengjie Jin and Aniri and Shuo Lu and Wenke Huang and Hu Cao and Xun Xiao and Zhihong Zhu and Volker Tresp and Fei Shen and Yunpu Ma and Tat-Seng Chua}, year={2027} } ```

Note4 octhuggingface.co/Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO

Source context: 23 downloads · 0 likes · Pipeline text-generation · Library transformers · Repo Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO

Note18 julhuggingface.co/Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO

Source context: 191 downloads · 0 likes · Repo Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO