Create README.md

README.md

@@ -0,0 +1,152 @@
+# II-Medical-7B-Preview
+
+## I. Model Overview
+
+II-Medical-7B-Preview is a medical reasoning model trained on a comprehensive dataset of medical knowledge. The model is designed to enhance AI capabilities in medical reasoning. 
+## II. Training Methodology
+
+We collected and generated a comprehensive set of reasoning datasets for the medical domain and performed SFT fine-tuning on the Qwen/Qwen2.5-7B-Instruct model. Following this, we further optimized the SFT model by training DAPO on a hard-reasoning dataset to boost performance.
+
+For SFT stage we using the hyperparameters: 
+
+- Max Length: 16378.
+- Batch Size: 128.
+- Learning-Rate: 5e-5.
+- Number Of Epoch: 4.
+
+For RL stage we setup training with:
+
+- Max prompt length: 2048 tokens.
+- Max response length: 12288 tokens.
+- Overlong buffer: Enabled, 4096 tokens, penalty factor 1.0.
+- Clip ratios: Low 0.2, High 0.28.
+- Batch sizes: Train prompt 512, Generation prompt 1536, Mini-batch 32.
+- Responses per prompt: 16.
+- Temperature: 1.0, Top-p: 1.0, Top-k: -1 (vLLM rollout).
+- Learning rate: 1e-6, Warmup steps: 10, Weight decay: 0.1.
+- Loss aggregation: Token-mean.
+- Gradient clipping: 1.0.
+- Entropy coefficient: 0.
+
+## III. Evaluation Results
+
+We evaluate on ten medical QA benchmarks include MedMCQA, MedQA, PubMedQA, medical related questions from MMLU-Pro and GPQA, small QA sets from Lancet and the New England
+Journal of Medicine,  4 Options  and 5 Options splits from the MedBullets platform and MedXpertQA.
+
+| Model                   | MedMC | MedQA | PubMed | MMLU-P | GPQA | Lancet | MedB-4 | MedB-5 | MedX  | NEJM  | Avg   |
+|--------------------------|-------|-------|--------|--------|------|--------|--------|--------|------|-------|-------|
+| QWQ 32B                  | 69.73 | 87.03 | 88.5   | 79.86  | 69.17| 71.3   | 72.07  | 69.01  |24.98 |75.12  | 70.68 |
+| Qwen2.5-7B-IT            | 56.56 | 61.51 | 71.3   | 61.17  | 42.56| 61.17  | 46.75  | 40.58  |13.26 |59.04  | 51.39 |
+| HuatuoGPT-o1-8B          | 63.97 | 74.78 | **80.10**  | 63.71  | 55.38| 64.32  | 58.44  | 51.95  |15.79 |64.84  | 59.32 |
+| Med-reason               | 61.67 | 71.87 | 77.4   | 64.1   | 50.51| 59.7   | 60.06  | 54.22  |22.87 |66.8   | 59.92 |
+| M1                       | 62.54 | 75.81 | 75.80  | 65.86  | 53.08| 62.62  | 63.64  | 59.74  |19.59 |64.34  | 60.3  |
+| II-Medical-7B-Preview-Wo-RL | 69.13 | 84.05 | 77.5   | 73.49  | 55.12| **67.71**  | 69.48  | 64.28  |19.51 |**70.64**  | 65.1  |
+| II-Medical-7B-Preview-RL | **69.42** | **85.15** | 77.9   | **77.26**  | **55.90**| **65.29**  | **72.72**  | **68.50**  |**22.97** |68.66  | **66.4**  |
+
+
+
+## IV. Dataset Curation
+
+The training dataset comprises 581,204 samples from the following sources:
+
+### 1. Public Medical Reasoning Datasets (103,031 samples)
+- General Medical Reasoning: 40,544 samples
+- Medical-R1-Distill-Data: 22,000 samples
+- Medical-R1-Distill-Data-Chinese: 17,000 samples
+- UCSC-VLAA/m23k-tokenized: 23,487 samples
+
+### 2. Synthetic Medical QA Data with QwQ Data (225,700 samples)
+Generated from established medical datasets:
+- MedMcQA (from openlifescienceai/medmcqa): 183,000 samples
+- MedQA: 10,000 samples
+- MedReason: 32,700 samples
+
+### 3. Curated Medical R1 Traces (338,055 samples)
+
+First we gather all the public R1 traces from:
+
+- PrimeIntellect/SYNTHETIC-1
+- GeneralReasoning/GeneralThought-430K
+- a-m-team/AM-DeepSeek-R1-Distilled-1.4M
+- open-thoughts/OpenThoughts2-1M
+- nvidia/Llama-Nemotron-Post-Training-Dataset: Science subset only
+- Other resources: cognitivecomputations/dolphin-r1, ServiceNow-AI/R1-Distill-SFT,...
+
+All R1 reasoning traces were processed through a domain-specific pipeline as follows:
+
+1. Embedding Generation: Prompts are embedded using sentence-transformers/all-MiniLM-L6-v2.
+
+2. Clustering: Perform K-means clustering with 50,000 clusters.
+
+3. Domain Classification:
+
+    - For each cluster, select the 10 prompts nearest to the cluster center.
+    - Classify the domain of each selected prompt using Qwen2.5-32b-Instruct.
+    - Assign the cluster's domain based on majority voting among the classified prompts.
+
+4. Domain Filtering: Keep only clusters labeled as Medical or Biology for the final dataset.
+
+
+### 4. Supplementary Math Dataset
+- Added 15,000 samples of reasoning traces from light-r1
+- Purpose: Enhance general reasoning capabilities of the model
+
+### Preprocessing Data
+1. Filtering for Complete Generation
+   - Retained only traces with complete generation outputs
+   - Removed incomplete or truncated samples
+
+2. Length-based Filtering
+   - Minimum threshold: Keep only the prompt with more than three words.
+   - Maximum threshold: Keep only the traces with less than 7,143 words.
+   - Wait Token Filter: Removed traces with has more than 47 occurrences of "Wait" (97th percentile threshold).
+
+
+### Data Decontamination
+
+We using two step decontamination:
+1. Following open-r1 project: We decontaminate a dataset using 10-grams with the evaluation datasets.
+2. After that, we using the fuzzy decontamination from `s1k` method with threshold 90%. 
+
+**Our pipeline is carefully decontaminated with the evaluation datasets.**
+
+Finally, we open sources our dataset at [Our Medical Reasoning SFT dataset](https://huggingface.co/datasets/Intelligent-Internet/II-Medical-Reasoning-SFT-V0).
+
+
+## V. How To Use
+Our model can be utilized in the same manner as Qwen or Deepseek-R1-Distill models.
+
+For instance, you can easily start a service using [vLLM](https://github.com/vllm-project/vllm):
+
+```bash
+vllm serve Intelligent-Internet/II-Medical-7B-Preview
+```
+
+You can also easily start a service using [SGLang](https://github.com/sgl-project/sglang):
+
+```bash
+python -m sglang.launch_server --model Intelligent-Internet/II-Medical-7B-Preview
+```
+
+## VI. Usage Guidelines
+
+- Recommended Sampling Parameters: temperature = 0.6, top_p = 0.9
+- When using, explicitly request step-by-step reasoning and format the final answer within \boxed{} (e.g., "Please reason step-by-step, and put your final answer within \boxed{}.").
+## VII. Limitations and Considerations
+
+- Dataset may contain inherent biases from source materials
+- Medical knowledge requires regular updates
+- Classification accuracy depends on embedding model and clustering parameters
+- Math reasoning traces may introduce domain-mixing effects
+- Please note that **It’s not suitable for medical use.**
+
+
+## VII. Citation
+
+```bib
+@misc{2025II-Medical-7B-Preview,
+      title={II-Medical-7B-Preview: Medical Reasoning Model}, 
+      author={Intelligent Internet},
+      year={2025}
+}
+```