MiniMax-Text-01

from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig, QuantoConfig, GenerationConfig

# load hf config
hf_config = AutoConfig.from_pretrained("MiniMaxAI/MiniMax-Text-01", trust_remote_code=True)

# quantization config, int8 is recommended
quantization_config =  QuantoConfig(
            weights="int8",
            modules_to_not_convert=[
                "lm_head",
                "embed_tokens",
            ] + [f"model.layers.{i}.coefficient" for i in range(hf_config.num_hidden_layers)]
            + [f"model.layers.{i}.block_sparse_moe.gate" for i in range(hf_config.num_hidden_layers)]
        )

# assume 8 GPUs
world_size = 8
layers_per_device = hf_config.num_hidden_layers // world_size
# set device map
device_map = {
    'model.embed_tokens': 'cuda:0',
    'model.norm': f'cuda:{world_size - 1}',
    'lm_head': f'cuda:{world_size - 1}'
}
for i in range(world_size):
    for j in range(layers_per_device):
        device_map[f'model.layers.{i * layers_per_device + j}'] = f'cuda:{i}'

# load tokenizer
tokenizer = AutoTokenizer.from_pretrained("MiniMaxAI/MiniMax-Text-01")
prompt = "Hello!"
messages = [
    {"role": "system", "content": [{"type": "text", "text": "You are a helpful assistant created by MiniMax based on MiniMax-Text-01 model."}]},
    {"role": "user", "content": [{"type": "text", "text": prompt}]},
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
# tokenize and move to device
model_inputs = tokenizer(text, return_tensors="pt").to("cuda")

# load bfloat16 model, move to device, and apply quantization
quantized_model = AutoModelForCausalLM.from_pretrained(
    "MiniMaxAI/MiniMax-Text-01",
    torch_dtype="bfloat16",
    device_map=device_map,
    quantization_config=quantization_config,
    trust_remote_code=True,
    offload_buffers=True,
)

# generate response
generation_config = GenerationConfig(
    max_new_tokens=20,
    eos_token_id=200020,
    use_cache=True,
)
generated_ids = quantized_model.generate(**model_inputs, generation_config=generation_config)
print(f"generated_ids: {generated_ids}")
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

@misc{minimax2025minimax01scalingfoundationmodels,
      title={MiniMax-01: Scaling Foundation Models with Lightning Attention}, 
      author={MiniMax and Aonian Li and Bangwei Gong and Bo Yang and Boji Shan and Chang Liu and Cheng Zhu and Chunhao Zhang and Congchao Guo and Da Chen and Dong Li and Enwei Jiao and Gengxin Li and Guojun Zhang and Haohai Sun and Houze Dong and Jiadai Zhu and Jiaqi Zhuang and Jiayuan Song and Jin Zhu and Jingtao Han and Jingyang Li and Junbin Xie and Junhao Xu and Junjie Yan and Kaishun Zhang and Kecheng Xiao and Kexi Kang and Le Han and Leyang Wang and Lianfei Yu and Liheng Feng and Lin Zheng and Linbo Chai and Long Xing and Meizhi Ju and Mingyuan Chi and Mozhi Zhang and Peikai Huang and Pengcheng Niu and Pengfei Li and Pengyu Zhao and Qi Yang and Qidi Xu and Qiexiang Wang and Qin Wang and Qiuhui Li and Ruitao Leng and Shengmin Shi and Shuqi Yu and Sichen Li and Songquan Zhu and Tao Huang and Tianrun Liang and Weigao Sun and Weixuan Sun and Weiyu Cheng and Wenkai Li and Xiangjun Song and Xiao Su and Xiaodong Han and Xinjie Zhang and Xinzhu Hou and Xu Min and Xun Zou and Xuyang Shen and Yan Gong and Yingjie Zhu and Yipeng Zhou and Yiran Zhong and Yongyi Hu and Yuanxiang Fan and Yue Yu and Yufeng Yang and Yuhao Li and Yunan Huang and Yunji Li and Yunpeng Huang and Yunzhi Xu and Yuxin Mao and Zehan Li and Zekang Li and Zewei Tao and Zewen Ying and Zhaoyang Cong and Zhen Qin and Zhenhua Fan and Zhihang Yu and Zhuo Jiang and Zijia Wu},
      year={2025},
      eprint={2501.08313},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2501.08313}, 
}