app.py

from huggingface_hub import InferenceClient
import gradio as gr
import random
import prompts
client = InferenceClient("mistralai/Mixtral-8x7B-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)
    seed = random.randint(1,9999999999999)

    system_prompt = agent.SONG_WRITER
    generate_kwargs = dict(
        temperature=0.9,
        max_new_tokens=1024,
        top_p=0.95,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=seed,
    )

    formatted_prompt = format_prompt(f"{system_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