Doge 120M MoE Instruct SFT

---

Doge uses Dynamic Mask Attention as sequence transformation and can use Multi-Layer Perceptron or Cross Domain Mixture of Experts as state transformation. Dynamic Mask Attention allows the Transformer to use self-attention during training and state space during inference, and Cross Domain Mixture of Experts can directly inherit the weights of Multi-Layer Perceptron for further training. This model is trained by SmallDoge community, for detailed algorithm and model architecture, paper coming soon, all training details and code are available in the small-doge repository.

Uses

from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig, TextStreamer

tokenizer = AutoTokenizer.from_pretrained("SmallDoge/Doge-120M-MoE-Instruct-SFT")
model = AutoModelForCausalLM.from_pretrained("SmallDoge/Doge-120M-MoE-Instruct-SFT", trust_remote_code=True)

generation_config = GenerationConfig(
      max_new_tokens=100, 
      use_cache=True, 
      do_sample=True, 
      temperature=0.8, 
      top_p=0.9,
      repetition_penalty=1.0
)
steamer = TextStreamer(
      tokenizer=tokenizer, 
      skip_prompt=True
)

prompt = "Hi, how are you doing today?"
conversation = [
      {"role": "user", "content": prompt}
]
inputs = tokenizer.apply_chat_template(
    conversation=conversation,
    tokenize=True,
    return_tensors="pt",
)

outputs = model.generate(
    inputs, 
    tokenizer=tokenizer,
    generation_config=generation_config, 
    streamer=steamer
)

Model Details

We build the Doge-Instruct-SFT by SFT on SmolTalk.

SFT:

Procedure:

SFT:

Environment:

• Image: nvcr.io/nvidia/pytorch:24.12-py3
• Hardware: 1x NVIDIA RTX 4090
• Software: Transformers, TRL

Citation

@misc{smalldoges,
  title={SmallDoges: A Family of Dynamic UltraFast Small Language Models}, 
  author={Jingze, Shi and Yifan, Wu and Bingheng, Wu and Yuyu, Luo},
  year={2025},
  month={March},
  url={https://github.com/SmallDoges/small-doge}
}