Spaces:
Sleeping
Sleeping
File size: 1,815 Bytes
4dadddb 9c9ed59 4dadddb 9c9ed59 4dadddb 9c9ed59 4dadddb 9c9ed59 ca677a9 9c9ed59 ca677a9 9c9ed59 4dadddb 9c9ed59 4dadddb 9c9ed59 4dadddb 9c9ed59 4dadddb |
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 flask import Flask, render_template, request, jsonify
from huggingface_hub import InferenceClient
import gradio as gr
app = Flask(__name__)
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, system_prompt, temperature=0.9, max_new_tokens=256, 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=42,
)
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
@app.route('/generate', methods=['POST'])
def generate_response():
data = request.get_json()
prompt = data['prompt']
history = data['history']
system_prompt = data['system_prompt']
temperature = data['temperature']
max_new_tokens = data['max_new_tokens']
top_p = data['top_p']
repetition_penalty = data['repetition_penalty']
result = list(generate(prompt, history, system_prompt, temperature, max_new_tokens, top_p, repetition_penalty))
return jsonify({'result': result})
if __name__ == '__main__':
app.run(port=7860)
|