| import gradio as gr | |
| from transformers import pipeline | |
| chat = pipeline("text-generation", model="meta-llama/Meta-Llama-3-8B-Instruct", device_map="auto") | |
| def respond(msg, history): | |
| history = history or [] | |
| out = chat(history + [msg], max_new_tokens=256) | |
| reply = out[0]["generated_text"] | |
| history.append((msg, reply)) | |
| return history, history | |
| iface = gr.ChatInterface(respond) | |
| iface.launch() | |