Spaces:
Running
Running
File size: 1,745 Bytes
7f99b50 e864fc9 7f99b50 e864fc9 7f99b50 e864fc9 7f99b50 e864fc9 7f99b50 e864fc9 7f99b50 e864fc9 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
def respond(
message,
history: list[dict[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
"""
Public version of the chatbot — no OAuth required.
Uses Hugging Face's Inference API (requires the model to be public).
"""
client = InferenceClient(model="openai/gpt-oss-20b")
messages = [{"role": "system", "content": system_message}]
messages.extend(history)
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
choices = message.choices
token = ""
if len(choices) and choices[0].delta.content:
token = choices[0].delta.content
response += token
yield response
# Chatbot UI
chatbot = gr.ChatInterface(
respond,
type="messages",
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)",
),
],
)
# Public app (no login, no auth)
with gr.Blocks() as demo:
gr.Markdown("## 🤖 JoeyMerhej Public Chatbot\nNo login required — start chatting below!")
chatbot.render()
if __name__ == "__main__":
demo.launch(server_name="0.0.0.0", server_port=7860)
|