2.86 TB

Ctrl+K

1 contributor

History: 378 commits

ASzecsenyi

Add HF-format checkpoint qwen8b_fsq_H410_ushape28_rec025_10_s42

9df3673 verified 1 day ago

PILOT_turboquant_cv_1536_s42
Squash history after pruning to one checkpoint per trained model about 2 months ago
cg_base_d12w768
Squash history after pruning to one checkpoint per trained model about 2 months ago
checkpoints_8b
Metadata sidecar for qwen8b_fsq_H410_ushape28_rec025_10_s42 2 days ago
ckpt_kivi_1536
Squash history after pruning to one checkpoint per trained model about 2 months ago
ckpt_kivi_768
Squash history after pruning to one checkpoint per trained model about 2 months ago
ckpt_pyramidkv_1536
Squash history after pruning to one checkpoint per trained model about 2 months ago
ckpt_pyramidkv_256
Squash history after pruning to one checkpoint per trained model about 2 months ago
ckpt_turboquant_1536
Squash history after pruning to one checkpoint per trained model about 2 months ago
ckpt_turboquant_768
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_base_d12w768_mlafsq
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_base_d12w768_prerope_kv
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_base_d12w768_prerope_kv_lr0p03
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_base_d12w768_prerope_kv_lr0p03_s43
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_base_d12w768_prerope_kv_lr0p03_s44
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_base_d12w768_rope_lr0p03
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_base_gpt3m_mlafsq
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_base_gpt3m_prerope_kv
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_base_gpt3m_rope
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_128B_lr0p03_fromrope_nofreeze_s42
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_128B_lr0p03_fromrope_nofreeze_s43
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_128B_lr0p03_fromrope_nofreeze_s44
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_1536B_lr0p03_fromrope_nofreeze_s42
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_1536B_lr0p03_fromrope_nofreeze_s43
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_1536B_lr0p03_fromrope_nofreeze_s44
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_256B_lr0p03_fromrope_nofreeze_s42
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_256B_lr0p03_fromrope_nofreeze_s43
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_256B_lr0p03_fromrope_nofreeze_s44
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_768B_lr0p03_fromrope_nofreeze_s42
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_768B_lr0p03_fromrope_nofreeze_s43
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_prerope_kv_768B_lr0p03_fromrope_nofreeze_s44
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_128B_lr0p03_s42
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_128B_lr0p03_s43
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_128B_lr0p03_s44
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_1536B_lr0p03_s42
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_1536B_lr0p03_s43
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_1536B_lr0p03_s44
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_256B_lr0p03_s42
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_256B_lr0p03_s43
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_256B_lr0p03_s44
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_32B_lr0p03_s42
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_32B_lr0p03_s43
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_32B_lr0p03_s44
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_768B_lr0p03_s42
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_768B_lr0p03_s43
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_768B_lr0p03_s44
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_8B_lr0p03_s42
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_8B_lr0p03_s43
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_8B_lr0p03_s44
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_pre_16x128_lr0p03_b0p03_fullb_fromrope_qlora64_xtcproj
Squash history after pruning to one checkpoint per trained model about 2 months ago
comp_cv_d12w768_rope_pre_16x32_lr0p03_b0p03_fullb_fromrope_qlora64_xtcproj
Squash history after pruning to one checkpoint per trained model about 2 months ago