Spaces:
Sleeping
Sleeping
File size: 1,891 Bytes
dc3ef30 01012b6 dc3ef30 01012b6 dc3ef30 c1de341 2395d36 01012b6 dc3ef30 f18008f 74fbf86 dc3ef30 c3c24f5 dc3ef30 f18008f dc3ef30 12b4bb0 dc3ef30 12b4bb0 dc3ef30 |
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 |
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")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
if not message[0] in list("{[("):
message = f"(((Say Start))) {message} (((Say End)))"
messages.append({"role": "user", "content": message})
response = ""
messageEnd = False
for message in client.chat_completion(messages,max_tokens=max_tokens,stream=True,temperature=temperature,top_p=top_p,):
token = message.choices[0].delta.content
print(token,end = '|')
response += token
yield token
#yield response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
with open("prompt.txt","r") as prompt_file:
prompt = prompt_file.read()
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value=prompt, 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)",
),
],
)
if __name__ == "__main__":
demo.launch()
|