from unsloth import FastLanguageModel
from peft import PeftModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="unsloth/meta-llama-3.1-8b-bnb-4bit",
    max_seq_length=2048,
    load_in_4bit=True,
)
model = PeftModel.from_pretrained(model, "AnukeerthiReddy/llama-3.1-8b-clinical-fhir-lora")

note = "Patient: 58M with chest pain radiating to left arm x 2h. HTN, T2DM. BP 158/92."
inputs = tokenizer(note, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Dataset

ai-galileo/clinical-notes-to-fhir

Training Infrastructure

GPU: NVIDIA L40 (47.7 GB) — Georgia State University
Framework: Unsloth + TRL SFTTrainer
Logging: Weights & Biases