Spaces:
Paused
Paused
File size: 2,205 Bytes
548b4c3 4635c7e 548b4c3 4635c7e 548b4c3 4635c7e 548b4c3 | 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 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 | import gradio as gr
from huggingface_hub import InferenceClient
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
def _history_to_messages(history):
messages = []
if not history:
return messages
# Gradio 5 uses list[dict]; older ChatInterface used list[tuple]
if isinstance(history[0], dict):
for item in history:
role = item.get("role")
content = item.get("content")
if role in {"user", "assistant"} and content:
messages.append({"role": role, "content": content})
return messages
for user_msg, assistant_msg in history:
if user_msg:
messages.append({"role": "user", "content": user_msg})
if assistant_msg:
messages.append({"role": "assistant", "content": assistant_msg})
return messages
def respond(message, history, system_message, max_tokens, temperature, top_p):
messages = [{"role": "system", "content": system_message}]
messages.extend(_history_to_messages(history))
messages.append({"role": "user", "content": message})
response = ""
try:
for chunk in client.chat_completion(
messages,
max_tokens=int(max_tokens),
stream=True,
temperature=temperature,
top_p=top_p,
):
token = chunk.choices[0].delta.content
if token:
response += token
yield response
except Exception as exc:
yield f"Model call failed: {exc}. Add HF_TOKEN in Space secrets if needed."
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(
value="You are a friendly chatbot. Speak as if you are age n and a given sex. Example: n = 17 and sex = male",
label="System message",
),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=2.0, 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"),
],
)
if __name__ == "__main__":
demo.launch()
|