Spaces:
Sleeping
Sleeping
File size: 1,616 Bytes
090e80f 2d0d654 090e80f acaf862 |
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 |
from huggingface_hub import InferenceClient
import gradio as gr
client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.2")
def format_prompt(message, history):
system_prompt = "You are Mistral, a gentle and a useful AI assistant. My input is "
prompt = "<s>"
prompt += f"[INST] {system_prompt} [/INST]"
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST]"
prompt += f" {bot_response}</s> "
prompt += f"[INST] {message} [/INST]"
return prompt
def generate(
prompt, history, temperature=0.2, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
):
temperature = float(temperature)
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=42,
)
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
mychatbot = gr.Chatbot(
avatar_images=["./user.png", "./bot.png"], bubble_full_width=False, show_label=False, show_copy_button=True,)
demo = gr.ChatInterface(fn=generate,
chatbot=mychatbot,
title="Tomoniai's Mistral 7b v0.2 Chat",
retry_btn=None,
undo_btn=None
)
demo.queue().launch(show_api=True) |