import torch
from transformers import AutoTokenizer, GenerationConfig
from gptqmodel import GPTQModel
model_name = "ModelCloud/DeepSeek-V2-Chat-0628-gptq-4bit"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
# `max_memory` should be set based on your devices
max_memory = {i: "75GB" for i in range(2)}
# `device_map` cannot be set to `auto`
model = GPTQModel.from_quantized(model_name, trust_remote_code=True, device_map="sequential", max_memory=max_memory, torch_dtype=torch.float16, attn_implementation="eager")

model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id

messages = [
    {"role": "user", "content": "Write a piece of quicksort code in C++"}
]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(input_ids=input_tensor.to(model.device), max_new_tokens=100)
result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
print(result)
 