Instructions to use zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit

SGLang

How to use zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit with Docker Model Runner:
```
docker model run hf.co/zjiayu064/DeepSeek-V2-Lite-BitsMoE-2bit
```

BitsMoE-DeepSeek-V2-Lite-2bit

This repository provides a 2-bit quantized version of DeepSeek-V2-Lite using the BitsMoE quantization framework. The model was introduced in the paper BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization.

The model is based on deepseek-ai/DeepSeek-V2-Lite and is intended for efficient inference of Mixture-of-Experts (MoE) large language models with significantly reduced memory footprint.

Paper: BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization
Code: GitHub - zjiayu064/BitsMoE

Model Details

Base model: deepseek-ai/DeepSeek-V2-Lite
Quantization: 2-bit (Experts-Only)
Architecture: Mixture-of-Experts (MoE)
Method: BitsMoE, a spectral-energy-guided bit-allocation framework.

Usage

Since this model uses custom architecture code via auto_map, ensure you load it with trust_remote_code=True.

Please refer to the BitsMoE GitHub repository for environment setup, custom kernels, and detailed usage instructions.

By default, models are downloaded from Hugging Face via the BitsMoE CLI:

bitsmoe demo

To run evaluation on benchmarks like MMLU or Hellaswag using the provided configs:

bitsmoe eval --config configs/deepseekv2/eval.yaml

License

This model follows the license of the original DeepSeek-V2-Lite model. Please refer to the license information provided in the metadata and the original DeepSeek model license for details.

Citation

If you find our work useful, please consider citing:

@misc{zhao2026bitsmoe,
      title={{BitsMoE}: Efficient Spectral Energy-Guided Bit Allocation for {MoE} {LLM} Quantization}, 
      author={Jiayu Zhao and Zihan Teng and Minhao Fan and Tianrui Ma and Wentao Ren and Song Chen and Weichen Liu},
      year={2026},
      eprint={2606.00079},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2606.00079}
}