Instructions to use wingchiuloong/DCore-Domino-Qwen3-4B-Budget16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wingchiuloong/DCore-Domino-Qwen3-4B-Budget16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="wingchiuloong/DCore-Domino-Qwen3-4B-Budget16", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("wingchiuloong/DCore-Domino-Qwen3-4B-Budget16", trust_remote_code=True) model = AutoModel.from_pretrained("wingchiuloong/DCore-Domino-Qwen3-4B-Budget16", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use wingchiuloong/DCore-Domino-Qwen3-4B-Budget16 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wingchiuloong/DCore-Domino-Qwen3-4B-Budget16" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wingchiuloong/DCore-Domino-Qwen3-4B-Budget16", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/wingchiuloong/DCore-Domino-Qwen3-4B-Budget16
- SGLang
How to use wingchiuloong/DCore-Domino-Qwen3-4B-Budget16 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 "wingchiuloong/DCore-Domino-Qwen3-4B-Budget16" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wingchiuloong/DCore-Domino-Qwen3-4B-Budget16", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "wingchiuloong/DCore-Domino-Qwen3-4B-Budget16" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wingchiuloong/DCore-Domino-Qwen3-4B-Budget16", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use wingchiuloong/DCore-Domino-Qwen3-4B-Budget16 with Docker Model Runner:
docker model run hf.co/wingchiuloong/DCore-Domino-Qwen3-4B-Budget16
DCore-Domino-Qwen3-4B-Budget16
Draft model for speculative decoding with Qwen/Qwen3-4B as the target model, trained with a draft budget of 16 tokens per block.
Domino baseline: DFlash architecture with a Domino projector, trained by us for comparison in the DCore paper.
This is a draft model: it is conditioned on hidden states of the target model and is not meant to be used as a standalone language model.
Paper: arXiv:2610.24993
Model Details
| Item | Value |
|---|---|
| Target model | Qwen/Qwen3-4B (36 layers) |
| Draft architecture | DFlashDraftModel |
| Draft layers | 5 |
| Hidden size / heads / KV heads | 2560 / 32 / 8 |
| Block size | 16 |
| Target layers used as context features | 1, 9, 17, 25, 33 |
projector_type |
domino |
emb_dim |
256 |
gru_hidden_dim |
1024 |
| Vocabulary | 151936 (Qwen3 tokenizer) |
| Precision | bfloat16 |
Files
config.jsondflash.pydomino.pymodel.safetensorsregistry.py
Usage
from transformers import AutoModel
draft = AutoModel.from_pretrained(
"wingchiuloong/DCore-Domino-Qwen3-4B-Budget16",
trust_remote_code=True,
dtype="bfloat16",
)
The draft model must be paired with Qwen/Qwen3-4B as the target model in a speculative decoding framework that supports DFlash-style block drafting.
Collection
Part of the DCore collection by ERNIE Research.
- Downloads last month
- 68