from transformers import AutoTokenizer, AutoModelForCausalLM
import os
import torch
model_path = "/home/download/baichuan-inc/Baichuan-M3-235B"
os.environ['TRANSFORMERS_OFFLINE'] = '1'
os.environ['MODELSCOPE_OFFLINE'] = '1'
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    trust_remote_code=True,
    device_map="auto",
    dtype=torch.bfloat16
)
enizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
messages = [{"role": "user", "content": "I've been having headaches lately, especially worse in the afternoon. What should I do?"}]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    thinking_mode='on'
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768,
    temperature=0.6
)
response = tokenizer.decode(generated_ids[0][len(model_inputs.input_ids[0]):], skip_special_tokens=True)
print(response)