Spaces:
Sleeping
Sleeping
File size: 1,772 Bytes
5c1f5a0 560bb48 5c1f5a0 |
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 |
from huggingface_hub import InferenceClient
import gradio as gr
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
def format_prompt(new_message, history):
prompt = "<s>"
for user_msg, bot_msg in history:
prompt += f"[INST] {user_msg} [/INST]"
prompt += f" {bot_msg}</s> "
prompt += f"[INST] {new_message} [/INST]"
return prompt
def generate(prompt, history,
temperature=0.25,
max_new_tokens=512,
top_p=0.95,
repetition_penalty=1.0,):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=727,
)
formatted_prompt = format_prompt(prompt, history)
stream = client.text_generation(formatted_prompt,
**generate_kwargs,
stream=True,
details=True,
return_full_text=False)
output = ""
for response in stream:
output += response.token.text
yield output
return output
samir_chatbot = gr.Chatbot(avatar_images=["./user.png", "./bot.png"],
bubble_full_width=False,
show_label=False,
show_copy_button=True,
likeable=True,)
demo = gr.ChatInterface(fn=generate,
chatbot=samir_chatbot,
title="Samir's Mixtral 8x7b Chat",)
demo.queue().launch(show_api=False) |