Update app.py

app.py

@@ -62,3 +62,19 @@ demo = gr.ChatInterface(
 
 if __name__ == "__main__":
     demo.launch()
+
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+model_id = "reedmayhew/claude-3.7-sonnet-reasoning-gemma3-12B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+def chat(prompt):
+    result = generator(prompt, max_new_tokens=256, temperature=0.7, do_sample=True)
+    return result[0]["generated_text"]
+
+app = gr.Interface(fn=chat, inputs=gr.Textbox(lines=4, label="Prompt"), outputs="text")
+app.launch()