Create app.py

app.py

@@ -0,0 +1,15 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "internistai/base-7b-v0.2"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+def chat(message):
+    inputs = tokenizer(message, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+iface = gr.Interface(fn=chat, inputs="text", outputs="text")
+iface.launch()