qwen2.5-3b-base-tool-n1-grpo/README.md

base_model, library_name, pipeline_tag, tags

base_model	library_name	pipeline_tag	tags
BillyWang1/qwen2.5-3b-base-tool-n1-sft	transformers	text-generation	qwen2 tool-use grpo verl tool-n1

qwen2.5-3b-base-tool-n1-grpo

This is a Hugging Face export of the GRPO-trained Tool-N1 Qwen2.5-3B checkpoint:

• Base model: BillyWang1/qwen2.5-3b-base-tool-n1-sft
• Training script: gflowrl/tool-call/scripts/qwen_3b_grpo.sh
• Checkpoint: gflowrl/tool-call/ckpt/qwen_grpo_3b_seed54321/global_step_280/actor
• Seed: 54321
• Step: 280
• Export format: verl FSDP shards merged to Transformers safetensors

The model is intended for Tool-N1-style function/tool calling experiments.