--- license: apache-2.0 tags: - medical - healthcare - collection - qlora - unsloth - qwen2.5 - clinical-nlp language: - en --- # Medical AI Fine-tuned Model Suite A collection of 16 [Qwen2.5](https://huggingface.co/Qwen) models fine-tuned with QLoRA, one per medical/healthcare task — ICD-10 coding, billing, clinical documentation, India's PM-JAY scheme, and more. Built by [Amaresh Hebbar](https://huggingface.co/AmareshHebbar). **Collection page:** [link to your HF collection here] Every model uses the same approach: a real public data source (CMS, NHA India, peer-reviewed biomedical corpora — no synthetic or LLM-generated training data), QLoRA fine-tuning on Qwen2.5, and a narrow, well-defined task with a strict system prompt. The goal is a set of small, deployable specialists rather than one large general-purpose medical model. ## Why specialist models instead of one big model A single general medical LLM has to be evaluated, monitored, and trusted across every task it might be asked to do. These models are scoped to one job each — ICD-10 coding, PM-JAY classification, radiology report coding — so each one is small enough to self-host cheaply, easy to evaluate against a clear ground truth, and safe to swap out independently if a better version ships later. ## The 16 models | Model | Task | Base | Rows | |---|---|---|---| | [icd10-coder-qwen25-7b](https://huggingface.co/AmareshHebbar/icd10-coder-qwen25-7b) | ICD-10-CM medical coding | Qwen2.5-7B | 74,719 | | [snomed-mapper-qwen25-7b](https://huggingface.co/AmareshHebbar/snomed-mapper-qwen25-7b) | Clinical terminology mapping | Qwen2.5-7B | 74,719 | | [clinical-summarizer-qwen25-7b](https://huggingface.co/AmareshHebbar/clinical-summarizer-qwen25-7b) | SOAP note summarization | Qwen2.5-7B | 30,000 | | [symptom-diagnoser-qwen25-7b](https://huggingface.co/AmareshHebbar/symptom-diagnoser-qwen25-7b) | Symptom → differential diagnosis | Qwen2.5-7B | 119,467 | | [discharge-qa-qwen25-3b](https://huggingface.co/AmareshHebbar/discharge-qa-qwen25-3b) | Discharge summary Q&A | Qwen2.5-3B | 30,000 | | [radiology-coder-qwen25-3b](https://huggingface.co/AmareshHebbar/radiology-coder-qwen25-3b) | Radiology report coding | Qwen2.5-3B | 25,090 | | [medical-ner-qwen25-3b](https://huggingface.co/AmareshHebbar/medical-ner-qwen25-3b) | Clinical named entity recognition | Qwen2.5-3B | 16,671 | | [hindi-medical-qwen25-3b](https://huggingface.co/AmareshHebbar/hindi-medical-qwen25-3b) | Hindi medical reasoning | Qwen2.5-3B | 19,704 | | [cpt-coder-qwen25-3b](https://huggingface.co/AmareshHebbar/cpt-coder-qwen25-3b) | CPT/HCPCS procedure coding | Qwen2.5-3B | 17,029 | | [medical-billing-qwen25-3b](https://huggingface.co/AmareshHebbar/medical-billing-qwen25-3b) | Medical billing assistant | Qwen2.5-3B | 17,029 | | [pmjay-classifier-qwen25-3b](https://huggingface.co/AmareshHebbar/pmjay-classifier-qwen25-3b) | India PM-JAY package classification | Qwen2.5-3B | 11,140 | | [pharmacy-ner-qwen25-1b](https://huggingface.co/AmareshHebbar/pharmacy-ner-qwen25-1b) | Drug entity extraction | Qwen2.5-1.5B | 3,500 | | [ayurveda-icd-qwen25-1b](https://huggingface.co/AmareshHebbar/ayurveda-icd-qwen25-1b) | Ayurveda to ICD-10 bridge | Qwen2.5-1.5B | 3,002 | | [insurance-classifier-qwen25-1b](https://huggingface.co/AmareshHebbar/insurance-classifier-qwen25-1b) | Stark Law DHS compliance | Qwen2.5-1.5B | 1,601 | | [icd10-to-drg-qwen25-1b](https://huggingface.co/AmareshHebbar/icd10-to-drg-qwen25-1b) | ICD-10 → MS-DRG reimbursement | Qwen2.5-1.5B | 5,385 | | [loinc-coder-qwen25-1b](https://huggingface.co/AmareshHebbar/loinc-coder-qwen25-1b) | Lab test CPT coding | Qwen2.5-1.5B | 2,179 | ## Training method All 16 models share the same recipe: | | | |---|---| | Fine-tuning method | QLoRA, 4-bit NF4 quantization, rank 16, alpha 32 | | Training framework | [Unsloth](https://github.com/unslothai/unsloth) + TRL `SFTTrainer` | | Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj | | Hardware | Single NVIDIA A40 (48GB) | | Optimizer | paged_adamw_8bit, cosine LR schedule | | Experiment tracking | [Weights & Biases](https://wandb.ai/amareshhebbar-/axiomapper) | Model size is matched to dataset size — large datasets (>50k rows) get Qwen2.5-7B, mid-size (10k–50k) get Qwen2.5-3B, and smaller specialist datasets (<10k) get Qwen2.5-1.5B. This keeps inference cost proportional to task complexity instead of running every task through the same large model. ## Data sources Every dataset behind these models is built from real authoritative public data — CMS (ICD-10-CM, MS-DRG, Physician Fee Schedule, HCPCS), NHA India (PM-JAY HBP 2022, PM RAHAT), and peer-reviewed biomedical corpora (chat_doctor, augmented-clinical-notes, drugprot). No synthetic or LLM-generated training data. Full extraction pipelines and column-level provenance are documented on each [dataset card](https://huggingface.co/AmareshHebbar). ## How to use any model in this suite Each model is a LoRA adapter on top of its base Qwen2.5 model. Load with PEFT: ```python from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel import torch base_model = "unsloth/Qwen2.5-7B-Instruct" # match the base size for the model you're using adapter = "AmareshHebbar/icd10-coder-qwen25-7b" tokenizer = AutoTokenizer.from_pretrained(base_model) model = AutoModelForCausalLM.from_pretrained(base_model, torch_dtype=torch.bfloat16, device_map="auto") model = PeftModel.from_pretrained(model, adapter) ``` See each model's individual card for its exact system prompt, example input/output, and recommended serving setup (Transformers, Unsloth, or vLLM). ## Limitations These are narrow specialist models, not general medical assistants. Each model only performs the single task it was trained on — using it outside that task will produce unreliable output. None of these models are a substitute for a licensed medical or billing professional; all output should be reviewed by a qualified person before being used in a clinical, billing, or compliance decision. ## Citation ```bibtex @misc{medicalai2026, author = {Hebbar, Amaresh}, title = {Medical AI Fine-tuning Suite}, year = {2026}, publisher = {HuggingFace}, url = {https://huggingface.co/AmareshHebbar} } ``` ## Contact - GitHub: [amareshhebbar](https://github.com/amareshhebbar) - LinkedIn: [gvamaresh](https://www.linkedin.com/in/gvamaresh) - HuggingFace: [AmareshHebbar](https://huggingface.co/AmareshHebbar)