from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "krishna195/medgemma-anatomy-v1.3"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

question = "What structures form the boundaries of the femoral triangle?"
prompt = f"<start_of_turn>user\n{question}<end_of_turn>\n<start_of_turn>model\n"

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Performance

Inference Speed: ~30-40 tokens/sec (T4)
Memory: 8-9GB (bfloat16), 3-4GB (4-bit)
Final Training Loss: 14.2034

Focus Areas

Orthopedic injuries
Nerve anatomy
Clinical presentations
Diagnostic workflows
Management protocols

License

Apache 2.0