Initial app.py with LLaMA 3.1 assistant

app.py

@@ -0,0 +1,15 @@
+# app.py
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+model_id = "meta-llama/Llama-3.1-8B-Instruct"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+def chat_with_llama(prompt):
+    result = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7)
+    return result[0]['generated_text']
+
+gr.Interface(fn=chat_with_llama, inputs="text", outputs="text", title="Venkat Assistant").launch()