arxiv:2506.06266
Simran
simarora
AI & ML interests
None yet
Organizations
models 39
simarora/qwen3_5-qk256-p1b-t50b-re0
Updated
simarora/qwen3_5-cylon-k4-p1b-t50b-re0
Updated
simarora/qwen3_5-cylon-k2-p1b-t50b-re0
Updated
simarora/qwen3_5-p1b-t50b-pile-re0
Updated
simarora/qwen3_5-cylon-k4-p1b-t10b-re0
Updated
simarora/qwen3_5-qk256-v256-p1b-t10b-re0
Updated
simarora/qwen3_5-full-attention-mha-fullrope-p1b-t10b-re0
Updated
simarora/qwen3_5-qk256-p1b-t10b-re0
Updated
simarora/qwen3_5-cylon-k2-p1b-t10b-re0
Updated
simarora/cylon-nocumsum-k8-v256-sep-wide-dtype32-p1b-t50b-re0
Updated
datasets 0
None public yet