arxiv:2504.19270
Sameera Ramasinghe
sampluralis
·
AI & ML interests
None yet
Organizations
models 18
sampluralis/llama-sft-proj-layers-shmid-pm
Text Generation • 2B • Updated • 6
sampluralis/llama-sft-proj-layers-shmid-pm-lora
Updated
sampluralis/llama-sft-proj-layers-shmid-continue
Text Generation • 1B • Updated • 7 •
sampluralis/llama-sft-masked
Text Generation • 1B • Updated • 10 •
sampluralis/llama-sft-baseline
Text Generation • 1B • Updated • 4 •
sampluralis/llama-sft-proj-layers-shmid
Text Generation • 1B • Updated • 18 •
sampluralis/llama-sft-sgd
Text Generation • 1B • Updated • 6 •
sampluralis/llama-sft-muon
Text Generation • 1B • Updated • 7 •
sampluralis/llama-sft-proj-layers
Text Generation • 1B • Updated • 5 •
sampluralis/llama-sft-proj
Text Generation • 1B • Updated • 4 •
datasets 0
None public yet