HuggingFaceTB / nanowhale-100m-base
Text Generation110M1.2K25Updated May 4, 2026
Downloads
1.2K
Likes
25
Last updated
May 4, 2026
License
apache-2.0
A small ~110M parameter language model implementing the DeepSeek-V4 architecture from scratch. This is the pretrained base model — see HuggingFaceTB/nanowhale-100m for the SFT/chat version.
Tasks & library
- text generation
- transformers
Tags
- transformers
- deepseek_v4
- text-generation
- deepseek
- moe
- causal-lm
Technical specifications
Parameters110M
Librarytransformers
Languagesen
Licenseapache-2.0
