Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
bird-of-paradise
/
deepseek-mla
like
5
Text Generation
Transformers
PyTorch
English
deepseek-mla
attention-mechanism
mla
efficient-attention
arxiv:
2405.04434
License:
mit
Model card
Files
Files and versions
Community
1
Use this model
main
deepseek-mla
/
insights
2 contributors
History:
2 commits
bird-of-paradise
Fix: Rename to Multi-Head Latent Attention
098730b
about 1 month ago
architecture.md
3.36 kB
Fix: Rename to Multi-Head Latent Attention
about 1 month ago
attention_mask.md
1.7 kB
Initial commit: DeepSeek Multi-Latent Attention implementation
about 1 month ago