TMAE-Triage/MedConsultLLM

Direct Use

#Load model

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-32B")
model3 = PeftModel.from_pretrained(base_model, "TMAE-Triage/MedConsultLLM")
tokenizer3 = AutoTokenizer.from_pretrained("TMAE-Triage/MedConsultLLM")

inputs3 = tokenizer3("<|im_start|>system\n<|im_end|>\n<|im_start|>user\nNKDA \n\n Patient SOB & RNA.<|im_end|><|im_start|>assistant\n", return_tensors="pt")
outputs3 = model3.generate(input_ids=inputs3.input_ids, max_new_tokens=100)
print(tokenizer3.decode(outputs3[0], skip_special_tokens=True))

#Result:

<|im_start|>system
<|im_end|>
<|im_start|>user
NKDA 

Patient SOB & RNA.<|im_end|><|im_start|>assistant

 no known drug allergies. 

 Patient shortness of breath and ribonucleic acid<|im_end|>.

Metrics

Training Detail

Framework versions

• PEFT 0.15.2