Spaces:
Sleeping
Sleeping
File size: 1,709 Bytes
4f68185 92e925d 4f68185 7ef4975 a32608f 7ef4975 4f68185 a32608f 4f68185 a32608f 3a6559c 4f68185 92e925d |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
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]})
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,
):
token = message.choices[0].delta.content
response += token
yield response
# Add a title to the UI
title = "Corenet"
# Modify the pre-prompt to be editable but greyed out
pre_prompt = gr.Textbox(
value="You are a friendly Chatbot, and you are a finetuned version of Llama-3 8B made possible by HX",
label="Pre-prompt",
interactive=True,
placeholder="Type here...",
style={"color": "grey"}
)
demo = gr.ChatInterface(
respond,
title=title,
additional_inputs=[
pre_prompt,
gr.Slider(minimum=256, maximum=8192, value=512, step=1, label="Max Gen tokens"),
gr.Slider(minimum=0.3, maximum=2.5, value=0.8, step=0.1, label="Creativity"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
if __name__ == "__main__":
demo.launch()
|