app.py

from huggingface_hub import InferenceClient
import gradio as gr

client = InferenceClient(
    "mistralai/Mistral-7B-Instruct-v0.1"
)


def format_prompt(message, history):
  prompt = "<s>"
  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, max_tokens=2000,
):
    '''temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)'''

    generate_kwargs = dict(
        #temperature=temperature,
        max_tokens=max_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


additional_inputs=[
    gr.Slider(
        label="Max tokens",
        value=2000,
        minimum=0,
        maximum=2048,
        step=64,
        interactive=True,
        info="The maximum numbers of new tokens",
    ),

]


gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
    additional_inputs=additional_inputs,
    title="""Mistral 7B"""
).launch(show_api=False)