app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the model and tokenizer
model_name = "wanglab/ClinicalCamel-70B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

# Function to generate responses
def generate_response(input_text):
    inputs = tokenizer(input_text, return_tensors="pt").to("cuda")  # Use GPU if available
    outputs = model.generate(**inputs, max_new_tokens=150)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

# Gradio interface
iface = gr.Interface(fn=generate_response, inputs="text", outputs="text", title="ClinicalCamel-70B Assistant")

if __name__ == "__main__":
    iface.launch()