Baichuan-M3-235B-GPTQ-INT4

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-M3-235B-GPTQ-INT4", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan-M3-235B-GPTQ-INT4")

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)

# vLLM
vllm serve baichuan-inc/Baichuan-M3-235B-GPTQ-INT4 --tensor-parallel-size 4 --reasoning-parser deepseek_r1