File size: 807 Bytes
c2d246d 5fd90b5 c2d246d 5fd90b5 c2d246d 5fd90b5 c2d246d |
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 |
from transformers import AutoTokenizer, AutoModelForCausalLM
import gradio as gr
import torch
# Используем более лёгкую модель
model_name = "Qwen/Qwen-1_8B"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_name,
device_map="auto",
torch_dtype=torch.float16,
trust_remote_code=True
)
def respond(message):
inputs = tokenizer(message, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=150)
return tokenizer.decode(outputs[0], skip_special_tokens=True)
gr.Interface(
fn=respond,
inputs="text",
outputs="text",
title="Qwen Прокси для Janotaro.ai",
description="Работает на Qwen-1_8B"
).launch() |