File size: 1,268 Bytes
99abe2b 31484bc 99abe2b 31484bc 99abe2b 31484bc 99abe2b 31484bc 99abe2b 31484bc 99abe2b 31484bc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 |
import streamlit as st
from transformers import AutoModelForCausalLM, AutoTokenizer
@st.cache_resource
def load_model_and_tokenizer():
model_name_or_path = "m42-health/med42-70b"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
return model, tokenizer
def generate_response(prompt):
prompt_template = f'''
<|system|>: You are a helpful medical assistant created by M42 Health in the UAE.
<|prompter|>:{prompt}
<|assistant|>:
'''
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.pad_token_id, max_new_tokens=512)
response = tokenizer.decode(output[0], skip_special_tokens=True)
return response
def main():
st.title("M42 Health Medical Assistant")
model, tokenizer = load_model_and_tokenizer()
prompt = st.text_area("Enter your medical query:")
if st.button("Submit"):
with st.spinner("Generating response..."):
response = generate_response(prompt)
st.write(response)
if __name__ == "__main__":
main() |