smpanaro
/

Llama-2-7b-coreml

Model card Files Files and versions Community

Llama-2-7b-coreml / Llama-2-7b-hf_chunk8.mlmodelc

1 contributor

History: 2 commits

smpanaro's picture

Update Sonoma model with faster 8x8 conv and split einsum attention

dba673f 3 months ago

analytics
Update Sonoma model with faster 8x8 conv and split einsum attention 3 months ago
weights
Update Sonoma model with faster 8x8 conv and split einsum attention 3 months ago
coremldata.bin

793 Bytes
LFS

Update Sonoma model with faster 8x8 conv and split einsum attention 3 months ago
metadata.json

6.62 kB

Update Sonoma model with faster 8x8 conv and split einsum attention 3 months ago
model.mil

403 kB

Update Sonoma model with faster 8x8 conv and split einsum attention 3 months ago