smpanaro
/

Llama-3.2-1B-Instruct-CoreML

Model card Files Files and versions Community

Llama-3.2-1B-Instruct-CoreML / Llama-3.2-1B-Instruct_chunk6.mlmodelc

1 contributor

History: 2 commits

smpanaro's picture

Faster argmax by skipping logit concat

f519906 about 1 month ago