agrv/llama-lr-3e-4-no-lora-ff-n-8-r-1
Updated • 4
Llama-MTPC-no-lora
Models for RQ1 and RQ2 - adapted byte-fied Llama from https://huggingface.co/benjamin/Llama3-2-3B-IT-Byte
-
-
agrv/llama-lr-3e-4-no-lora-ff-n-16-r-1
Updated • 1 -
agrv/llama-lr-3e-4-no-lora-cp-n-8-r-8
Updated -
agrv/llama-lr-3e-4-no-lora-cp-n-8-r-16
Updated -
agrv/llama-lr-3e-4-no-lora-cp-n-8-r-32
Updated -
agrv/llama-lr-3e-4-no-lora-cp-n-16-r-32
Updated -
agrv/llama-lr-3e-4-no-lora-hmm-n-8-r-32
Updated -
agrv/llama-lr-3e-4-no-lora-hmm-n-16-r-32
Updated -
agrv/llama-lr-3e-4-no-lora-btree-n-8-r-32-s-1
Updated • 4 -
agrv/llama-lr-3e-4-no-lora-btree-n-16-r-32-s-1
Updated