ModelVerificadoExterno

ReflectRL Qwen2.5 Math 7B DAPO

This model checkpoint is part of the work presented in ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning.

Fuentehuggingface.co/Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO/tree/bb6557fc35419474bcf887ab5e2c81abc8ecf38a

TipoText modelModelo baseQwen/Qwen2.5-Math-7BVersiónmodelPublicador@JinheCcalidad

Fuente del modelo

Tipo: Text model
Tamaño del archivo: 28,4 GB
Modelo base: Qwen/Qwen2.5-Math-7B
Versión: vmodel
Actualizado: 4 oct 2026
Publicador: @Jinhe
Descargas: 17
Parámetros: 7B
Fuente: Hugging Face

Descripción de la fuente

ReflectRL-Qwen2.5-Math-7B-GRPO-ReflectRL

This model checkpoint is part of the work presented in ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning.

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.

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

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={2026}
}

Fuentes

1 fuente

Hugging FacePrincipalVersión bb6557fc35419474bcf887ab5e2c81abc8ecf38a

huggingface.co/Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO/tree/bb6557fc35419474bcf887ab5e2c81abc8ecf38a

Verificado 4 oct

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 28,4 GB · SHA-256 926f8e2066dd…1ea5 · Hugging Face

Descargar

Extractos de fuentes

3 extractos

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

--- license: apache-2.0 library_name: transformers pipeline_tag: text-generation base_model: Qwen/Qwen2.5-Math-7B --- # ReflectRL-Qwen2.5-Math-7B-GRPO-ReflectRL This model checkpoint is part of the work presented in [ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning](https://huggingface.co/papers/2608.03972). 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. - **Paper:** [ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning](https://huggingface.co/papers/2608.03972) - **Repository:** [GitHub Repository](https://github.com/bibisbar/ReflectRL) ## 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={2026} } ```

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

Source context: 17 downloads · 0 likes · Pipeline text-generation · Library transformers · Repo Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO

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

Source context: 188 downloads · 0 likes · Repo Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO