Ed Addario
Ed Addario
This PR adds the ability to prune all tensors from user-defined layers (blocks) by providing a comma-separated list in the `--prune-layers` command line option. It will renumber remaining layers to...
This PR implements @slaren's regex matching recommendation for allowed tensors. For example: `--tensor-type attn=q4_k` will now apply to all tensors named \*attn\*
A new `--show-statistics` option generates a report highlighting which tensors/layers contribute the most in a model. The report is sorted from the highest influence to lowest. The process computes the...