Skip to content

gzone0111

AutoGraphR1-musique_hotpotqa_train-qwen2.5-7b-graph-retriever-grpo-judge-3b

gzone0111/AutoGraphR1-musique_hotpotqa_train-qwen2.5-7b-graph-retriever-grpo-judge-3b

AutoGraphR1-musique_hotpotqa_train-qwen2.5-7b-graph-retriever-grpo-judge-3b is a text generation model from gzone0111. Use it when you need the model to write or continue text. The card lists the license as mit.

Ablation from AutoGraph-R1 (ACL 2026). An LLM constructor is trained so the knowledge graph it builds is useful in a downstream RAG system. The reward judge is a 3B model.

Downloads · 30 days

19

48% of all-time downloads

All-time downloads

40

Public

Parameters

7.6B

107 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt91.4 GB · 85%

At a glance

Task
Text Generation
License
mit
Model type
qwen2
Access
Public
Created
Sep 24, 2026
Updated
Oct 23, 2026
SHA
c8aa1019

Try a prompt

Base models

Task
Text Generation
Type
qwen2
License
mit
Languages
en
Created
Sep 24, 2026
Updated
Oct 23, 2026