Downloads · 30 days
16
30% of all-time downloads
gzone0111/AutoGraphR1-musique_hotpotqa_train-llama3.2-3b-graph-retriever-grpo-repetition-penalty
AutoGraphR1-musique_hotpotqa_train-llama3.2-3b-graph-retriever-grpo-repetition-penalty 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. GRPO is run with a repetition penalty.
Downloads · 30 days
16
30% of all-time downloads
All-time downloads
53
Public
Parameters
3.6B
13.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors7.2 GB · 54%
From the Hugging Face model README
Ablation from AutoGraph-R1 (ACL 2026). An LLM constructor is trained so the knowledge graph it builds is useful in a downstream RAG system. GRPO is run with a repetition penalty.
Base model: meta-llama/Llama-3.2-3B-Instruct.