File size: 1,292 Bytes
0132665 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 |
import gradio as gr
from huggingface_hub import InferenceClient
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
def respond(message, history, system_message, max_tokens, temperature, top_p):
# history 現在是 list[dict] 格式，直接使用
messages = [{"role": "system", "content": system_message}] + history
messages.append({"role": "user", "content": message})
response = ""
for msg in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = msg.choices[0].delta.content
response += token
yield response
demo = gr.ChatInterface(
respond,
type="messages", # ✅ 使用新版 messages 格式，避免警告
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
if __name__ == "__main__":
demo.launch()
|