Downloads · 30 days
12
5% of all-time downloads
bibocat/qwen3-ner-grpo-v2-merged
qwen3-ner-grpo-v2-merged is a text generation model from bibocat. Use it when you need the model to write or continue text. It is set up for transformers.
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 datatrain/grpov2/fulltrain.jsonl with the span-aware v…
Downloads · 30 days
12
5% of all-time downloads
All-time downloads
260
Public
Parameters
8.2B
16.4 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors16.4 GB · 100%
From the Hugging Face model README
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.