Downloads · 30 days
969
2% of all-time downloads
DeepSeek-V3-0324-NextN
lmsys/DeepSeek-V3-0324-NextN
DeepSeek-V3-0324-NextN is a machine learning model from lmsys. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
NextN layer exported from deepseek-ai/DeepSeek-V3-0324 model with script. Used for speculative decoding in SGLang.
All-time downloads
51.2K
Public
Parameters
11.6B
11.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors11.7 GB · 100%
Parameter types
How the weights are stored.
F8_E4M311.5B · 99%
Model card
From the Hugging Face model README
DeepSeek-V3-0324-NextN
NextN layer exported from deepseek-ai/DeepSeek-V3-0324 model with script. Used for speculative decoding in SGLang.
Usage
python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-V3-0324 --speculative-algo EAGLE --speculative-draft lmsys/DeepSeek-V3-0324-NextN --speculative-num-steps 2 --speculative-eagle-topk 4 --speculative-num-draft-tokens 4 --trust-remote --tp 8
- Type
- deepseek_v3
- Created
- Mar 27, 2025
- Updated
- Mar 27, 2025