Spaces:
Sleeping
Sleeping
from flask import Flask, request, Response, jsonify | |
from huggingface_hub import InferenceClient | |
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=[], temperature=0.2, max_new_tokens=2000, 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(prompt, history) | |
#stream = client.text_generation(prompt, **generate_kwargs, stream=True, details=False, return_full_text=False) | |
stream = client.text_generation(prompt=prompt, stream=True) | |
print(stream) | |
output = "" | |
for response in stream: | |
yield response.token.text.encode('utf-8') | |
app = Flask(__name__) | |
def health(): | |
return jsonify({"status": "ok"}) | |
def search_route(): | |
data = request.get_json() | |
prompt = data.get('prompt', '') | |
#truncated_prompt = prompt[:32768] | |
return Response(generate(prompt), content_type='text/plain', status=200, direct_passthrough=True) | |
if __name__ == '__main__': | |
app.run(debug=False, host='0.0.0.0', port=7860) | |