Spaces:
Sleeping
Sleeping
File size: 2,920 Bytes
c7ed3e6 30b0c87 c7ed3e6 a996723 30b0c87 c7ed3e6 a996723 c7ed3e6 a996723 c7ed3e6 9490597 c7ed3e6 3171a1c c069ea9 | 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 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 | import gradio as gr
from huggingface_hub import InferenceClient
def respond(
message,
history: list[dict[str, str]],
system_message,
max_tokens,
temperature,
top_p,
hf_token: None,
):
from huggingface_hub import InferenceClient
client = InferenceClient(model="Ana8413/model")
# Build the message history for the model
messages = [{"role": "system", "content": system_message}]
messages.extend(history)
messages.append({"role": "user", "content": message})
response = ""
# Use try/finally to safely iterate over the streaming generator
try:
for chunk in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
# Some chunks may not have choices or content
if chunk.choices and chunk.choices[0].delta.content:
token = chunk.choices[0].delta.content
response += token
yield response # Yield incremental response for streaming
except Exception as e:
# Catch other possible exceptions from the generator
print(f"Stream error: {e}")
yield response # Return whatever has been accumulated so far
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
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)",
),
],
)
with gr.Blocks() as demo:
#with gr.Sidebar():
# gr.LoginButton()
chatbot.render()
if __name__ == "__main__":
demo.launch(show_error=True)
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
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)",
),
],
)
with gr.Blocks() as demo:
#with gr.Sidebar():
# gr.LoginButton()
chatbot.render()
if __name__ == "__main__":
demo.launch(show_error=True)
|