Phi-4-mini Clinical (PyTorch / Transformers)
A specialized 3.8B biomedical & clinical reasoning foundation model built on Microsoft's Phi-4-mini-instruct, formatted for standard Hugging Face transformers and PyTorch.
🏗️ 3-Stage Transfer Learning Curriculum
- Stage 1 (STEM Foundation): 116,000 instruction pairs across NCERT Classes 6–12 (Physics, Chemistry, Biology) eliminating foundational science hallucinations.
- Stage 2 (PubMed 2026 Evidence): 12 recent 2026 clinical update archives from NCBI FTP covering survival outcomes (OS, PFS, HR), targeted therapeutics, and clinical trial endpoints.
- Stage 3 (Comprehensive Internal Medicine): Balanced multi-specialty clinical curriculum (cardiology, nephrology, endocrinology, pulmonology) with an active oncology replay buffer.
All LoRA adapter weights have been permanently fused into the base weights.
📊 Benchmark Results (PubMedQA)
Evaluated on 50 biomedical research decision tasks from PubMedQA:
| Model | Accuracy | Score | Avg Latency | Relative Improvement |
|---|---|---|---|---|
| Base Phi-4-mini (4-bit) | 26.0% | 13 / 50 | 1.02s / question | Baseline |
| Phi-4-mini Clinical (Merged) | 40.0% | 20 / 50 | 0.93s / question | +53.8% relative gain |
⚡ Quickstart with Transformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "charakaweb/phi4-clinical"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto"
)
prompt = "<|user|>\nWhat are the first-line therapeutic recommendations for heart failure with preserved ejection fraction (HFpEF)?<|end|>\n<|assistant|>\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
⚕️ Clinical Disclaimer
This model is intended solely for biomedical research, educational exploration, and experimental evaluation. It is not an FDA-cleared medical device and must not be used as a substitute for professional clinical judgment, diagnosis, or treatment.
🏆 Verified Medical Benchmark Results
| Benchmark | Scope | Tested Samples | Accuracy | Evaluation Hardware |
|---|---|---|---|---|
| PubMedQA | Clinical Trial Evidence Decisions | 100 | 49.0% | Apple Silicon Metal GPU |
| MedQA (USMLE) | Medical Board Diagnostic Cases | 100 | 53.0% | Apple Silicon Metal GPU |