Create app.py

app.py

@@ -0,0 +1,23 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Load the model
+model_name = "ruslanmv/Medical-Llama3-8B"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
+
+def generate_response(question):
+    inputs = tokenizer(question, return_tensors="pt").input_ids.to(model.device)
+    outputs = model.generate(inputs, max_new_tokens=256)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+iface = gr.Interface(
+    fn=generate_response,
+    inputs="text",
+    outputs="text",
+    title="Medical Query Assistant",
+    description="Ask medical questions and receive AI-powered answers.",
+)
+
+iface.launch(share=True)