Create app.py

app.py

@@ -0,0 +1,13 @@
+from transformers import pipeline
+import gradio as gr
+
+# Load your HF model (must be on Hub)
+pipe = pipeline("text-generation", model="eduard76/Llama3-8b-good-new", trust_remote_code=True)
+
+def chat_fn(message, history):
+    full_input = "\n".join([f"User: {turn[0]}\nAI: {turn[1]}" for turn in history] + [f"User: {message}\nAI:"])
+    result = pipe(full_input, max_new_tokens=256, do_sample=True, temperature=0.7)
+    response = result[0]['generated_text'].split("AI:")[-1].strip()
+    return response
+
+gr.ChatInterface(chat_fn, title="🤖 Chat with Eduard76's LLM").launch()