VOOZH about

URL: https://huggingface.co/justinj92/MediQwen-Reasoning-4B

⇱ justinj92/MediQwen-Reasoning-4B · Hugging Face


  • Developed by: justinj92
  • License: apache-2.0
  • Finetuned from model : unsloth/Qwen3-4B-Instruct-2507
  • GPU : AMD MI300x
  • EPOCH : 2
  • Training Time : 3 Days

👁 WandB

Dataset Mix

  • Reasoning - II-Medical-Reasoning at 70%
  • Non-Reasoning - Mediflow at 30%
Benchmark MediQwen-Reasoning-4B Qwen3-4B-Instruct-2507 Δ
MedQA 55.85% (711/1273) 12.73% (162/1273) +43.12%
MedMCQA 54.29% (2271/4183) 53.50% (2238/4183) +0.79%
PubMedQA 71.90% (719/1000) 60.00% (600/1000) +11.90%

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

👁 Image

Downloads last month
6
Safetensors
Model size
4B params
Tensor type
BF16
·

Model tree for justinj92/MediQwen-Reasoning-4B

Finetuned
(420)
this model
Quantizations
1 model

Datasets used to train justinj92/MediQwen-Reasoning-4B

Collection including justinj92/MediQwen-Reasoning-4B