ModelVérifiéExterne

ReflectRL Qwen2.5 Math 7B GRPO ReflectRL

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

Sourcehuggingface.co/Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO-ReflectRL/tree/8ad563a01d331f5de99a4e5f3b51a195937d9f83

TypeText modelModèle de baseQwen/Qwen2.5-Math-7BVersionmodelÉditeur@JinheCClasse

Source du modèle

Type: Text model
Taille du fichier: 28,4 GB
Modèle de base: Qwen/Qwen2.5-Math-7B
Version: vmodel
Mis à jour: 4 oct. 2026
Éditeur: @Jinhe
Téléchargements: 27
Paramètres: 7B
Source: Hugging Face

Description de la source

ReflectRL

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

Code & Repository: GitHub - ReflectRL
Base Model: Qwen/Qwen2.5-Math-7B
Paper: ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning

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}
}

Sources

1 source

Hugging FacePrincipalVersion 8ad563a01d331f5de99a4e5f3b51a195937d9f83

huggingface.co/Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO-ReflectRL/tree/8ad563a01d331f5de99a4e5f3b51a195937d9f83

Vérifié 4 oct.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 28,4 GB · SHA-256 c400634a3498…a47c · Hugging Face

Télécharger

Extraits de sources

3 extraits

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

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

Source context: 27 downloads · 0 likes · Pipeline text-generation · Library transformers · Repo Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO-ReflectRL

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

Source context: 189 downloads · 0 likes · Repo Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO-ReflectRL