smpanaro
/

Llama-2-7b-coreml

Model card Files Files and versions Community

Llama-2-7b-coreml

Commit History

Update README.md

402bd4f
verified

smpanaro commited on Oct 12

Update README.md

1122b87
verified

smpanaro commited on Oct 12

Add new joint prefill+generation cache processor

07183f4

smpanaro commited on Oct 5

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

dba673f

smpanaro commited on Aug 15

Update sequoia mode with transposed value cache and 4:508 input:cache length

722eedf
verified

smpanaro commited on Jul 25

Upload Sequoia model

f554427
verified

smpanaro commited on Jul 7

Update README.md

3764204
verified

smpanaro commited on May 28

Add model

a76a14d

smpanaro commited on May 25

initial commit

6fcd72b
verified

smpanaro commited on May 25