Spaces:
Sleeping
Sleeping
File size: 1,863 Bytes
dbc07cf 13f40ff c2dcb34 13f40ff c2dcb34 dbc07cf 8a8a71a c2dcb34 dbc07cf 058e552 dbc07cf 058e552 dbc07cf 5b32cbd dbc07cf 13f40ff c2dcb34 13f40ff |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
SYSTEM_MAGIC = """
Your container is written in HTML. All outputs must be in HTML format. User cannot see what you say unles it is in HTML.
<!DOCTYPE html>"""
def respond(message):
messages = [{"role": "system", "content": SYSTEM_MAGIC}]
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=4096,
stream=True,
temperature=0.248,
top_p=0.842,
):
token = message.choices[0].delta.content
response += token
yield response
print(response)
return response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
#demo = gr.ChatInterface(
# respond,
## 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.Row():
hml = gr.HTML("")
with gr.Row():
tb = gr.Textbox(placeholder="Your input here...")
with gr.Row():
bn = gr.Button("Submit")
bn.click(respond, inputs=[tb], outputs=[hml])
if __name__ == "__main__":
demo.launch() |