Spaces:
Runtime error
Runtime error
File size: 2,349 Bytes
3998dc6 226409a 3998dc6 226409a 3998dc6 226409a 3998dc6 226409a 3998dc6 226409a 3998dc6 226409a 3998dc6 226409a 3998dc6 226409a 3998dc6 226409a 3998dc6 226409a 3998dc6 226409a | 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 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 | import os
import gradio as gr
from huggingface_hub import InferenceClient
MODEL_ID = "HauhauCS/GLM-4.7-Flash-Uncensored-HauhauCS-Balanced"
def get_token(hf_token: gr.OAuthToken | None) -> str | None:
"""
Priority:
1) Gradio OAuth token (when user clicks LoginButton)
2) Space secret HF_TOKEN (Settings -> Secrets)
"""
if hf_token is not None and getattr(hf_token, "token", None):
return hf_token.token
return os.getenv("HF_TOKEN")
def respond(
message,
history: list[dict[str, str]],
system_message,
max_tokens,
temperature,
top_p,
hf_token: gr.OAuthToken,
):
token = get_token(hf_token)
# If the repo is gated/private, you need a token.
# If it's public, token can be None and it may still work depending on the endpoint limits.
client = InferenceClient(model=MODEL_ID, token=token)
messages = [{"role": "system", "content": system_message}]
messages.extend(history)
messages.append({"role": "user", "content": message})
response = ""
# Stream output token-by-token
for chunk in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token_text = ""
if chunk.choices and chunk.choices[0].delta and chunk.choices[0].delta.content:
token_text = chunk.choices[0].delta.content
response += token_text
yield response
chatbot = gr.ChatInterface(
respond,
type="messages",
additional_inputs=[
gr.Textbox(value="You are a helpful coding assistant.", 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)",
),
],
)
with gr.Blocks() as demo:
with gr.Sidebar():
gr.Markdown(f"### Model\n`{MODEL_ID}`")
gr.LoginButton()
gr.Markdown(
"If this model requires authentication, click **Login** "
"or set a Space secret named `HF_TOKEN`."
)
chatbot.render()
if __name__ == "__main__":
demo.launch()
|