File size: 1,945 Bytes
30befd8 264be56 30befd8 264be56 30befd8 264be56 30befd8 cdc540c 30befd8 264be56 30befd8 264be56 30befd8 264be56 30befd8 264be56 30befd8 264be56 |
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 |
from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr
# Загрузка модели и токенизатора
model_path = "verge4646/autotrain-qwen-1737303151"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype="auto"
).eval()
# Функция генерации ответа
def respond(message, history, system_message, max_tokens, temperature, top_p):
messages = [{"role": "system", "content": system_message}]
for user_msg, assistant_msg in history:
if user_msg:
messages.append({"role": "user", "content": user_msg})
if assistant_msg:
messages.append({"role": "assistant", "content": assistant_msg})
messages.append({"role": "user", "content": message})
# Создание входных данных для модели
input_ids = tokenizer.apply_chat_template(
conversation=messages,
tokenize=True,
add_generation_prompt=True,
return_tensors="pt"
)
# Генерация ответа
output_ids = model.generate(
input_ids.to('cpu'),
max_new_tokens=max_tokens,
temperature=temperature,
top_p=top_p
)
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
return response
# Определение интерфейса Gradio
demo = gr.ChatInterface(
fn=respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
],
)
if __name__ == "__main__":
demo.launch()
|