Create app.py

app.py

@@ -0,0 +1,18 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("mailboxlab11/llama-3-medicalassistant")
+model = AutoModelForCausalLM.from_pretrained("mailboxlab11/llama-3-medicalassistant")
+
+def generate(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Create the Gradio interface
+iface = gr.Interface(fn=generate, inputs="text", outputs="text", title="Medical Assistant", description="Ask me any medical question.")
+
+# Launch the Gradio interface
+iface.launch()