qwen3-ner-grpo-v2-merged/README.md

base_model, library_name, pipeline_tag, language, tags

base_model	library_name	pipeline_tag	language	tags
bibocat/qwen3-ner-sft-4epochs-100k-merged	transformers	text-generation	vi	qwen3 grpo medical named-entity-recognition vietnamese

Qwen3 Vietnamese Medical NER — GRPO v2

BF16 merged checkpoint from the Qwen3 Vietnamese medical SFT model and the models/qwen3-ner-grpo-v2 GRPO v2 LoRA adapter. The adapter was trained for one epoch on data_train/grpo_v2/full_train.jsonl with the span-aware v2 reward.

Use the bundled tokenizer and Qwen3 chat template. The output is a JSON array with entity, type, position, assertions, and candidates fields.