Just the original weights converted to be compatible with transformers.
Anton Vlasjuk
AntonV
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Mamba-3: Improved Sequence Modeling using State Space Principles liked a Space 1 day ago
transformers-community/circle-ci-viz new activity 3 days ago
jinaai/xlm-roberta-flash-implementation:Fixup post init (for v5 remot compatibility)Organizations
models 14
AntonV/ernie4_5_fonts
Updated
AntonV/ernie4_5_configs
Updated
AntonV/Ernie4_5Tokenizer
Updated
AntonV/Dia-1.6B
2B • Updated • 119k
AntonV/mamba2-2.7b-hf
3B • Updated • 122 • 3
AntonV/mamba2-1.3b-hf
1B • Updated • 2.31k • 1
AntonV/mamba2-780m-hf
0.8B • Updated • 13k • 2
AntonV/mamba2-370m-hf
0.4B • Updated • 1.57k • 2
AntonV/mamba2-130m-hf
0.1B • Updated • 11.1k • 7
AntonV/mamba2-130m-av
0.1B • Updated • 2 • 2