Create app.py

app.py

@@ -0,0 +1,21 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import gradio as gr
+
+# ✅ Load your model
+model_name = "meta-llama/Llama-3.2-1B-Instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",
+    torch_dtype=torch.float16
+)
+
+# ✅ Define chatbot function
+def chatbot(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    output = model.generate(**inputs, max_length=200)
+    return tokenizer.decode(output[0], skip_special_tokens=True)
+
+# ✅ Deploy on Gradio
+gr.Interface(fn=chatbot, inputs="text", outputs="text", title="Llama Chatbot").launch()