Downloads · 30 days
7
10% of all-time downloads
Qwen2.5-7B-ReasonMed-reason-123k
Chens7/Qwen2.5-7B-ReasonMed-reason-123k
Qwen2.5-7B-ReasonMed-reason-123k is a text generation model from Chens7. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Full fine-tune of Qwen/Qwen2.5-7B on the ReasonMed dataset (<thinkCoT</thinkResponse format), using a 123K-sample subset (1/3 of the full 370K dataset) for 3 epochs.
All-time downloads
67
Public
Parameters
7.6B
15.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Mar 10, 2026
- Updated
- Mar 10, 2026
- SHA
- e1e00a91
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Qwen2.5-7B-ReasonMed-reason-123k
Full fine-tune of Qwen/Qwen2.5-7B on the ReasonMed dataset (<think>CoT</think>Response format), using a 123K-sample subset (1/3 of the full 370K dataset) for 3 epochs.
Training code: https://github.com/Chen-Jie7/NLP_project
Training data
lingshu-medical-mllm/ReasonMed — ReasonMed.json variant. Each sample wraps chain-of-thought reasoning in <think>...</think> tags followed by the final answer.
Evaluation
Loglikelihood multiple-choice scoring across 9 medical QA benchmarks (eval_ll.py in the repo). Paper baseline is ReasonMed-7B trained on the full 370K samples.
| Benchmark | Ours (123K) | Paper (370K) | Δ |
|---|---|---|---|
| MedQA | 62.2 | 66.9 | -4.7 |
| MedMCQA (val) | 60.9 | 65.1 | -4.2 |
| PubMedQA | 77.5 | 82.0 | -4.5 |
| MMLU-Anatomy | 75.6 | 75.6 | 0.0 |
| MMLU-Clinical-Knowledge | 78.5 | 79.3 | -0.8 |
| MMLU-College-Biology | 81.9 | 79.2 | +2.7 |
| MMLU-College-Medicine | 70.5 | 73.4 | -2.9 |
| MMLU-Medical-Genetics | 84.0 | 85.0 | -1.0 |
| MMLU-Professional-Medicine | 79.0 | 80.9 | -1.9 |
| Total | 65.8 | 69.6 | -3.8 |
The gap is consistent with training on 1/3 of the data.
Training hyperparameters
- learning_rate: 1e-05
- effective batch size: 128 (4 GPU × 4 per-device × 8 accum)
- num_epochs: 3.0
- lr_scheduler: cosine, warmup_ratio 0.1
- precision: bf16
- deepspeed: ZeRO stage 2
- framework: LlamaFactory
Framework versions
- Transformers 4.57.6
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.1
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- apache-2.0
- Created
- Mar 10, 2026
- Updated
- Mar 10, 2026