Skip to page content
SAVRN
Search Plan a project

Open-weight model

cs781-p1-runs

by Dev Sachan D-230353/cs781-p1-runs

cs781-p1-runs is an open-weight model from Dev Sachan. Its published files total 49.8 GB.

Parameters—
Context—
Weights49.8 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
D-230353/cs781-p1-runs
Publisher
Dev Sachan
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
7fe25215b5f8c6260ba15ec5650d27d8d19290d4
First published
2026-09-26
Last updated
2026-10-09

Files and Weights

448 files, 49.8 GB in total. The weights are 82 files totalling 49.8 GB in pt.

Weights82 files · 49.8 GB
Configuration239 files · 1.5 MB
Other126 files · 1.4 MB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
runs/A_decoder/best.ptWeights438.2 MB 1ef47e1989cf
runs/A_decoder/current.ptWeights1.3 GB 84d73e163c3a
runs/A_decoder/pre_decay.ptWeights1.3 GB 7c3936c4dea8
runs/A_decoder_ext/best.ptWeights438.2 MB e48472057190
runs/B_prefixlm/best.ptWeights438.2 MB a06b8de7d97c
runs/B_prefixlm/current.ptWeights1.3 GB d3a36dde449d
runs/B_prefixlm/pre_decay.ptWeights1.3 GB 446d50a6708c
runs/C_encdec/best.ptWeights494.8 MB 4093420294b6
runs/C_encdec/current.ptWeights1.5 GB 8c88247e52c6
runs/C_encdec/pre_decay.ptWeights1.5 GB a4285299353a
runs/D_retnet/best.ptWeights466.6 MB b25db8604605
runs/E_student_kd/best.ptWeights233.1 MB 96f9b5b427ab
runs/E_student_kd/current.ptWeights699.2 MB e810e483d864
runs/E_student_kd/pre_decay.ptWeights699.2 MB fe7b92c26ad4
runs/E_student_nokd/best.ptWeights233.1 MB e262c7c3e396
runs/E_student_nokd/current.ptWeights699.2 MB c957adbdd09e
runs/E_student_nokd/pre_decay.ptWeights699.2 MB 8c17fc140896
runs/p2_A_final_all/best.ptWeights444.5 MB 4dc2877c30fd
runs/p2_B_adapters_all/best.ptWeights454.1 MB 251e47884fc8
runs/p2_B_final_all/best.ptWeights444.5 MB 6e140914773a
runs/p2_B_header_all/best.ptWeights444.5 MB ae3f36fc16ea
runs/p2_B_lora_all/best.ptWeights446.9 MB 51cc6925d6fb
runs/p2_B_lorma_all/best.ptWeights446.9 MB b166cf2b5a87
runs/p2_B_partial_all/best.ptWeights444.5 MB 28307b9d95be
runs/p2_C_final_all/best.ptWeights274.6 MB 33dbc92045fc
runs/p2_D_final_all/best.ptWeights472.9 MB b4848b62d26f
runs/p2_E_kd_all/best.ptWeights238.2 MB ec610b7c25e3
runs/p3_B_cw_f0/best.ptWeights444.5 MB d39ae50dbb8e
runs/p3_B_cw_f0/current.ptWeights1.3 GB dc70e9995fc2
runs/p3_B_cw_f3/current.ptWeights1.3 GB e4a9c8e01fde
runs/p3_B_cw_f3/heldout.ptWeights205.2 KB 69b2c9dc4e8c
runs/p3_B_full_f0/best.ptWeights444.5 MB b47deee74093
runs/p3_B_full_f0/current.ptWeights1.3 GB b38dbabef98f
runs/p3_B_full_f0/heldout.ptWeights203.2 KB 82e953ac4197
runs/p3_B_full_f1/best.ptWeights444.5 MB a4e388a4733b
runs/p3_B_full_f1/current.ptWeights1.3 GB cd42a824f4bb
runs/p3_B_full_f1/heldout.ptWeights201.1 KB 29d0b7d9ee02
runs/p3_B_full_f2/best.ptWeights444.5 MB 2641d3f856ef
runs/p3_B_full_f2/current.ptWeights1.3 GB 3e38ba0ec04e
runs/p3_B_full_f2/heldout.ptWeights205.3 KB 08be35e900d5
runs/p3_B_full_f3/best.ptWeights444.5 MB c264c3567255
runs/p3_B_full_f3/current.ptWeights1.3 GB 1669dc3f4ca3
runs/p3_B_full_f3/heldout.ptWeights205.2 KB 605363ed27d2
runs/p3_B_full_f4/best.ptWeights444.5 MB f264b89d3bfe
runs/p3_B_full_f4/current.ptWeights1.3 GB 88639d3c3d28
runs/p3_B_full_f4/heldout.ptWeights203.2 KB 16306aab4213
runs/p3_B_sentonly_f1/best.ptWeights438.2 MB 65ddb63658fe
runs/p3_B_sentonly_f1/current.ptWeights1.3 GB cdf09400fd02
runs/p3_B_sentonly_f2/best.ptWeights438.2 MB 01136290a0b4
runs/p3_B_sentonly_f2/current.ptWeights1.3 GB 1145f882b8c0
runs/p3_B_sentonly_f3/best.ptWeights438.2 MB cd352ac72289
runs/p3_B_sentonly_f3/current.ptWeights1.3 GB 3f49f7038c7d
runs/p3_B_window_f0/best.ptWeights438.2 MB d7ae2d6fba36
runs/p3_B_window_f0/current.ptWeights1.3 GB 814e885c6f32
runs/p3_B_window_f0/heldout.ptWeights203.2 KB 2bc9657cb657
runs/p3_B_window_f1/best.ptWeights438.2 MB 2561a5b31242
runs/p3_B_window_f1/current.ptWeights1.3 GB 70898fda69a4
runs/p3_B_window_f1/heldout.ptWeights201.1 KB a2d2d104ebb7
runs/p3_B_window_f2/best.ptWeights438.2 MB ee75c5d7bc6f
runs/p3_B_window_f2/current.ptWeights1.3 GB ddbdc262d375
runs/p3_B_window_f2/heldout.ptWeights205.3 KB 2fed4b1ccee7
runs/p3_B_window_f3/best.ptWeights438.2 MB d00224164b45
runs/p3_B_window_f3/current.ptWeights1.3 GB 074042ffa373
runs/p3_B_window_f3/heldout.ptWeights205.2 KB 47743f37a9f2
runs/p3_B_window_f4/best.ptWeights438.2 MB 3656d893cbd8
runs/p3_B_window_f4/current.ptWeights1.3 GB 922bbd700ba9
runs/p3_B_window_f4/heldout.ptWeights203.2 KB ddf43cc36925
runs/proxy_ctx2048/best.ptWeights168.4 MB edd8762bcf76
runs/proxy_ctx2048/current.ptWeights505.1 MB 1714d8e60e34
runs/proxy_ctx2048/pre_decay.ptWeights505.1 MB d95ed6fd6807
runs/proxy_ctx512/best.ptWeights168.4 MB b03c0eaccabf
runs/proxy_ctx512/current.ptWeights505.1 MB 75b5d8adfa90
runs/proxy_ctx512/pre_decay.ptWeights505.1 MB a3fa9687c079
runs/proxy_mix_natural/best.ptWeights168.4 MB 6ea2662180c7
runs/proxy_mix_natural/current.ptWeights505.1 MB 37002516813a
runs/proxy_mix_natural/pre_decay.ptWeights505.1 MB c91467acceb9
runs/proxy_mix_sc_heavy/best.ptWeights168.4 MB 91d25b9d5846
runs/proxy_mix_sc_heavy/current.ptWeights505.1 MB fe9d8d82d3f3
runs/proxy_mix_sc_heavy/pre_decay.ptWeights505.1 MB 1b92c33e1dcf
runs/proxy_mix_sc_only/best.ptWeights168.4 MB 1c9a2c8b44f1
runs/proxy_mix_sc_only/current.ptWeights505.1 MB c29a6dc305fe
runs/proxy_mix_sc_only/pre_decay.ptWeights505.1 MB 2c9183e26ded
phase2/predictions/ens_BDE/prediction.jsonConfiguration110.6 KB —
phase2/predictions/ens_HDE/prediction.jsonConfiguration110.8 KB —
phase2/predictions/p2_A_final_all/prediction.jsonConfiguration113.7 KB —
phase2/predictions/p2_B_adapters_all/prediction.jsonConfiguration110.6 KB —
phase2/predictions/p2_B_final_all/prediction.jsonConfiguration111.5 KB —
phase2/predictions/p2_B_header_all/prediction.jsonConfiguration110.2 KB —
phase2/predictions/p2_B_lora_all/prediction.jsonConfiguration107.9 KB —
phase2/predictions/p2_B_lorma_all/prediction.jsonConfiguration108.3 KB —
phase2/predictions/p2_B_partial_all/prediction.jsonConfiguration108.5 KB —
phase2/predictions/p2_C_final_all/prediction.jsonConfiguration109.6 KB —
phase2/predictions/p2_D_final_all/prediction.jsonConfiguration116.2 KB —
phase2/predictions/p2_E_kd_all/prediction.jsonConfiguration115.0 KB —
phase3/results/cv_B_full.jsonConfiguration2.3 KB —
phase3/results/cv_B_sentonly.jsonConfiguration2.3 KB —
phase3/results/cv_B_window.jsonConfiguration2.3 KB —
runs/A_decoder/config.yamlConfiguration819 B —
runs/A_decoder/summary.jsonConfiguration518 B —
runs/A_decoder_ext/config.yamlConfiguration816 B —
runs/A_decoder_ext/summary.jsonConfiguration525 B —
runs/B_prefixlm/config.yamlConfiguration875 B —
runs/B_prefixlm/summary.jsonConfiguration524 B —
runs/C_encdec/config.yamlConfiguration893 B —
runs/C_encdec/summary.jsonConfiguration520 B —
runs/D_retnet/config.yamlConfiguration820 B —
runs/D_retnet/summary.jsonConfiguration519 B —
runs/E_student_kd/config.yamlConfiguration887 B —
runs/E_student_kd/summary.jsonConfiguration524 B —
runs/E_student_nokd/config.yamlConfiguration816 B —
runs/E_student_nokd/summary.jsonConfiguration527 B —
runs/p2_A_final_all/config.yamlConfiguration579 B —
runs/p2_A_final_all/summary.jsonConfiguration459 B —
runs/p2_A_final_f0/config.yamlConfiguration577 B —
runs/p2_A_final_f0/summary.jsonConfiguration674 B —
runs/p2_A_final_f1/config.yamlConfiguration577 B —
runs/p2_A_final_f1/summary.jsonConfiguration675 B —
runs/p2_A_final_f2/config.yamlConfiguration577 B —
runs/p2_A_final_f2/summary.jsonConfiguration675 B —
runs/p2_A_final_f3/config.yamlConfiguration577 B —
runs/p2_A_final_f3/summary.jsonConfiguration671 B —
runs/p2_A_final_f4/config.yamlConfiguration577 B —
runs/p2_A_final_f4/summary.jsonConfiguration671 B —
runs/p2_A_full_bigru_f0/config.yamlConfiguration378 B —
runs/p2_A_full_bigru_f0/summary.jsonConfiguration643 B —
runs/p2_A_full_f0/config.yamlConfiguration365 B —
runs/p2_A_full_f0/summary.jsonConfiguration637 B —
runs/p2_B_adapters_all/config.yamlConfiguration602 B —
runs/p2_B_adapters_all/summary.jsonConfiguration482 B —
runs/p2_B_adapters_f0/config.yamlConfiguration600 B —
runs/p2_B_adapters_f0/summary.jsonConfiguration697 B —
runs/p2_B_adapters_f1/config.yamlConfiguration600 B —
runs/p2_B_adapters_f1/summary.jsonConfiguration699 B —
runs/p2_B_adapters_f2/config.yamlConfiguration600 B —
runs/p2_B_adapters_f2/summary.jsonConfiguration698 B —
runs/p2_B_adapters_f3/config.yamlConfiguration600 B —
runs/p2_B_adapters_f3/summary.jsonConfiguration696 B —
runs/p2_B_adapters_f4/config.yamlConfiguration600 B —
runs/p2_B_adapters_f4/summary.jsonConfiguration694 B —
runs/p2_B_bigru_aug_f0/config.yamlConfiguration575 B —
runs/p2_B_bigru_aug_f0/summary.jsonConfiguration660 B —
runs/p2_B_bigru_aug_f1/config.yamlConfiguration575 B —
runs/p2_B_bigru_aug_f1/summary.jsonConfiguration660 B —
runs/p2_B_bigru_dec_f0/config.yamlConfiguration575 B —
runs/p2_B_bigru_dec_f0/summary.jsonConfiguration660 B —
runs/p2_B_bigru_dec_f1/config.yamlConfiguration575 B —
runs/p2_B_bigru_dec_f1/summary.jsonConfiguration658 B —
runs/p2_B_bigru_drop_aug_e15_f0/config.yamlConfiguration574 B —
runs/p2_B_bigru_drop_aug_e15_f0/summary.jsonConfiguration667 B —
runs/p2_B_bigru_drop_aug_e15_f1/config.yamlConfiguration574 B —
runs/p2_B_bigru_drop_aug_e15_f1/summary.jsonConfiguration669 B —
runs/p2_B_bigru_drop_aug_f0/config.yamlConfiguration574 B —
runs/p2_B_bigru_drop_aug_f0/summary.jsonConfiguration667 B —
runs/p2_B_bigru_drop_aug_f1/config.yamlConfiguration574 B —
runs/p2_B_bigru_drop_aug_f1/summary.jsonConfiguration664 B —
runs/p2_B_bigru_drop_e15_f0/config.yamlConfiguration574 B —
runs/p2_B_bigru_drop_e15_f0/summary.jsonConfiguration682 B —
runs/p2_B_bigru_drop_e15_f1/config.yamlConfiguration574 B —
runs/p2_B_bigru_drop_e15_f1/summary.jsonConfiguration679 B —
runs/p2_B_bigru_drop_f0/config.yamlConfiguration574 B —
runs/p2_B_bigru_drop_f0/summary.jsonConfiguration662 B —
runs/p2_B_bigru_drop_f1/config.yamlConfiguration574 B —
runs/p2_B_bigru_drop_f1/summary.jsonConfiguration658 B —
runs/p2_B_bigru_lr2e5_f0/config.yamlConfiguration575 B —
runs/p2_B_bigru_lr2e5_f0/summary.jsonConfiguration660 B —
runs/p2_B_bigru_lr2e5_f1/config.yamlConfiguration575 B —
runs/p2_B_bigru_lr2e5_f1/summary.jsonConfiguration662 B —
runs/p2_B_final_all/config.yamlConfiguration576 B —
runs/p2_B_final_all/summary.jsonConfiguration456 B —
runs/p2_B_final_f0/config.yamlConfiguration574 B —
runs/p2_B_final_f0/summary.jsonConfiguration713 B —
runs/p2_B_final_f1/config.yamlConfiguration574 B —
runs/p2_B_final_f1/summary.jsonConfiguration715 B —
runs/p2_B_final_f2/config.yamlConfiguration574 B —
runs/p2_B_final_f2/summary.jsonConfiguration717 B —
runs/p2_B_final_f3/config.yamlConfiguration574 B —
runs/p2_B_final_f3/summary.jsonConfiguration713 B —
runs/p2_B_final_f4/config.yamlConfiguration574 B —
runs/p2_B_final_f4/summary.jsonConfiguration710 B —
runs/p2_B_full_bigru_f0/config.yamlConfiguration375 B —
runs/p2_B_full_bigru_f0/summary.jsonConfiguration641 B —
runs/p2_B_full_f0/config.yamlConfiguration362 B —
runs/p2_B_full_f0/summary.jsonConfiguration631 B —
runs/p2_B_header_all/config.yamlConfiguration590 B —
runs/p2_B_header_all/summary.jsonConfiguration458 B —
runs/p2_B_header_f0/config.yamlConfiguration588 B —
runs/p2_B_header_f0/summary.jsonConfiguration718 B —
runs/p2_B_header_f1/config.yamlConfiguration588 B —
runs/p2_B_header_f1/summary.jsonConfiguration716 B —
runs/p2_B_header_f2/config.yamlConfiguration588 B —
runs/p2_B_header_f2/summary.jsonConfiguration717 B —
runs/p2_B_header_f3/config.yamlConfiguration588 B —
runs/p2_B_header_f3/summary.jsonConfiguration715 B —
runs/p2_B_header_f4/config.yamlConfiguration588 B —
runs/p2_B_header_f4/summary.jsonConfiguration718 B —
runs/p2_B_lora_all/config.yamlConfiguration641 B —
runs/p2_B_lora_all/summary.jsonConfiguration555 B —
runs/p2_B_lora_f0/config.yamlConfiguration639 B —
runs/p2_B_lora_f0/summary.jsonConfiguration766 B —
runs/p2_B_lora_f1/config.yamlConfiguration639 B —
runs/p2_B_lora_f1/summary.jsonConfiguration770 B —
runs/p2_B_lora_f2/config.yamlConfiguration639 B —
runs/p2_B_lora_f2/summary.jsonConfiguration769 B —
runs/p2_B_lora_f3/config.yamlConfiguration639 B —
runs/p2_B_lora_f3/summary.jsonConfiguration771 B —
runs/p2_B_lora_f4/config.yamlConfiguration639 B —
runs/p2_B_lora_f4/summary.jsonConfiguration770 B —
runs/p2_B_lorma_all/config.yamlConfiguration642 B —
runs/p2_B_lorma_all/summary.jsonConfiguration557 B —
runs/p2_B_lorma_f0/config.yamlConfiguration640 B —
runs/p2_B_lorma_f0/summary.jsonConfiguration775 B —
runs/p2_B_lorma_f1/config.yamlConfiguration640 B —
runs/p2_B_lorma_f1/summary.jsonConfiguration773 B —
runs/p2_B_lorma_f2/config.yamlConfiguration640 B —
runs/p2_B_lorma_f2/summary.jsonConfiguration772 B —
runs/p2_B_lorma_f3/config.yamlConfiguration640 B —
runs/p2_B_lorma_f3/summary.jsonConfiguration772 B —
runs/p2_B_lorma_f4/config.yamlConfiguration640 B —
runs/p2_B_lorma_f4/summary.jsonConfiguration774 B —
runs/p2_B_partial_all/config.yamlConfiguration601 B —
runs/p2_B_partial_all/summary.jsonConfiguration481 B —
runs/p2_B_partial_f0/config.yamlConfiguration599 B —
runs/p2_B_partial_f0/summary.jsonConfiguration695 B —
runs/p2_B_partial_f1/config.yamlConfiguration599 B —
runs/p2_B_partial_f1/summary.jsonConfiguration698 B —
runs/p2_B_partial_f2/config.yamlConfiguration599 B —
runs/p2_B_partial_f2/summary.jsonConfiguration694 B —
runs/p2_B_partial_f3/config.yamlConfiguration599 B —
runs/p2_B_partial_f3/summary.jsonConfiguration697 B —
runs/p2_B_partial_f4/config.yamlConfiguration599 B —
runs/p2_B_partial_f4/summary.jsonConfiguration694 B —
runs/p2_C_final_all/config.yamlConfiguration574 B —
runs/p2_C_final_all/summary.jsonConfiguration452 B —
runs/p2_C_final_f0/config.yamlConfiguration572 B —
runs/p2_C_final_f0/summary.jsonConfiguration669 B —
runs/p2_C_final_f1/config.yamlConfiguration572 B —
runs/p2_C_final_f1/summary.jsonConfiguration666 B —
runs/p2_C_final_f2/config.yamlConfiguration572 B —
runs/p2_C_final_f2/summary.jsonConfiguration670 B —
runs/p2_C_final_f3/config.yamlConfiguration572 B —
runs/p2_C_final_f3/summary.jsonConfiguration670 B —
runs/p2_C_final_f4/config.yamlConfiguration572 B —
runs/p2_C_final_f4/summary.jsonConfiguration665 B —
runs/p2_C_full_bigru_f0/config.yamlConfiguration373 B —
runs/p2_C_full_bigru_f0/summary.jsonConfiguration625 B —
runs/p2_C_full_f0/config.yamlConfiguration360 B —
runs/p2_C_full_f0/summary.jsonConfiguration616 B —
runs/p2_D_final_all/config.yamlConfiguration576 B —
runs/p2_D_final_all/summary.jsonConfiguration456 B —
runs/p2_D_final_f0/config.yamlConfiguration574 B —
runs/p2_D_final_f0/summary.jsonConfiguration670 B —
runs/p2_D_final_f1/config.yamlConfiguration574 B —
runs/p2_D_final_f1/summary.jsonConfiguration667 B —
runs/p2_D_final_f2/config.yamlConfiguration574 B —
runs/p2_D_final_f2/summary.jsonConfiguration669 B —
runs/p2_D_final_f3/config.yamlConfiguration574 B —
runs/p2_D_final_f3/summary.jsonConfiguration672 B —
runs/p2_D_final_f4/config.yamlConfiguration574 B —
runs/p2_D_final_f4/summary.jsonConfiguration671 B —
runs/p2_D_full_f0/config.yamlConfiguration375 B —
runs/p2_D_full_f0/summary.jsonConfiguration634 B —
runs/p2_D_full_linear_f0/config.yamlConfiguration362 B —
runs/p2_D_full_linear_f0/summary.jsonConfiguration641 B —
runs/p2_E_final_f0/config.yamlConfiguration576 B —
runs/p2_E_final_f0/summary.jsonConfiguration718 B —
runs/p2_E_final_f1/config.yamlConfiguration576 B —
runs/p2_E_final_f1/summary.jsonConfiguration710 B —
runs/p2_E_final_f2/config.yamlConfiguration576 B —
runs/p2_E_final_f2/summary.jsonConfiguration715 B —
runs/p2_E_final_f3/config.yamlConfiguration576 B —
runs/p2_E_final_f3/summary.jsonConfiguration717 B —
runs/p2_E_final_f4/config.yamlConfiguration576 B —
runs/p2_E_final_f4/summary.jsonConfiguration715 B —
runs/p2_E_kd_all/config.yamlConfiguration644 B —
runs/p2_E_kd_all/summary.jsonConfiguration532 B —
runs/p2_E_kd_f0/config.yamlConfiguration642 B —
runs/p2_E_kd_f0/summary.jsonConfiguration792 B —
runs/p2_E_kd_f1/config.yamlConfiguration642 B —
runs/p2_E_kd_f1/summary.jsonConfiguration789 B —
runs/p2_E_kd_f2/config.yamlConfiguration642 B —
runs/p2_E_kd_f2/summary.jsonConfiguration792 B —
runs/p2_E_kd_f3/config.yamlConfiguration642 B —
runs/p2_E_kd_f3/summary.jsonConfiguration791 B —
runs/p2_E_kd_f4/config.yamlConfiguration642 B —
runs/p2_E_kd_f4/summary.jsonConfiguration793 B —
runs/p3_B_cw_f0/config.yamlConfiguration471 B —
runs/p3_B_full_f0/config.yamlConfiguration471 B —
runs/p3_B_full_f0/summary.jsonConfiguration1.1 KB —
runs/p3_B_full_f1/config.yamlConfiguration471 B —
runs/p3_B_full_f1/summary.jsonConfiguration1.1 KB —
runs/p3_B_full_f2/config.yamlConfiguration471 B —
runs/p3_B_full_f2/summary.jsonConfiguration1.1 KB —
runs/p3_B_full_f3/config.yamlConfiguration471 B —
runs/p3_B_full_f3/summary.jsonConfiguration1.1 KB —
runs/p3_B_full_f4/config.yamlConfiguration471 B —
runs/p3_B_full_f4/summary.jsonConfiguration1.1 KB —
runs/p3_B_sentonly_f1/config.yamlConfiguration473 B —
runs/p3_B_sentonly_f1/summary.jsonConfiguration1.1 KB —
runs/p3_B_sentonly_f2/config.yamlConfiguration473 B —
runs/p3_B_sentonly_f2/summary.jsonConfiguration1.1 KB —
runs/p3_B_sentonly_f3/config.yamlConfiguration495 B —
runs/p3_B_window_f0/config.yamlConfiguration472 B —
runs/p3_B_window_f0/summary.jsonConfiguration1.1 KB —
runs/p3_B_window_f1/config.yamlConfiguration472 B —
runs/p3_B_window_f1/summary.jsonConfiguration1.1 KB —
runs/p3_B_window_f2/config.yamlConfiguration472 B —
runs/p3_B_window_f2/summary.jsonConfiguration1.1 KB —
runs/p3_B_window_f3/config.yamlConfiguration472 B —
runs/p3_B_window_f3/summary.jsonConfiguration1.1 KB —
runs/p3_B_window_f4/config.yamlConfiguration472 B —
runs/p3_B_window_f4/summary.jsonConfiguration1.1 KB —
runs/proxy_ctx2048/config.yamlConfiguration834 B —
runs/proxy_ctx2048/summary.jsonConfiguration522 B —
runs/proxy_ctx512/config.yamlConfiguration833 B —
runs/proxy_ctx512/summary.jsonConfiguration526 B —
runs/proxy_mix_natural/config.yamlConfiguration765 B —
runs/proxy_mix_natural/summary.jsonConfiguration530 B —
runs/proxy_mix_sc_heavy/config.yamlConfiguration834 B —
runs/proxy_mix_sc_heavy/summary.jsonConfiguration528 B —
runs/proxy_mix_sc_only/config.yamlConfiguration834 B —
runs/proxy_mix_sc_only/summary.jsonConfiguration529 B —
phase2/predictions/ens_BDE/submission.zipOther31.8 KB 5764e59d1551
phase2/predictions/ens_HDE/submission.zipOther31.9 KB 83d4bc388295
phase2/predictions/p2_A_final_all/submission.zipOther32.5 KB e47c6ba8cc1e
phase2/predictions/p2_B_adapters_all/submission.zipOther31.8 KB a43b2744a967
phase2/predictions/p2_B_final_all/submission.zipOther32.1 KB 548bb6aa3cf0
phase2/predictions/p2_B_header_all/submission.zipOther31.8 KB 8c2744798144
phase2/predictions/p2_B_lora_all/submission.zipOther31.0 KB b3dd76f7b4c5
phase2/predictions/p2_B_lorma_all/submission.zipOther31.2 KB 4a255734df2c
phase2/predictions/p2_B_partial_all/submission.zipOther31.2 KB 9cc810887969
phase2/predictions/p2_C_final_all/submission.zipOther31.4 KB 366abcc282e2
phase2/predictions/p2_D_final_all/submission.zipOther33.4 KB 6c20109c3f00
phase2/predictions/p2_E_kd_all/submission.zipOther33.0 KB e6a1644fab55
runs/A_decoder/log.jsonlOther61.7 KB —
runs/A_decoder_ext/log.jsonlOther43.9 KB —
runs/B_prefixlm/log.jsonlOther61.4 KB —
runs/C_encdec/log.jsonlOther61.6 KB —
runs/D_retnet/log.jsonlOther62.7 KB —
runs/E_student_kd/log.jsonlOther30.9 KB —
runs/E_student_nokd/log.jsonlOther31.2 KB —
runs/p2_A_final_all/log.jsonlOther1.8 KB —
runs/p2_A_final_f0/log.jsonlOther6.4 KB —
runs/p2_A_final_f1/log.jsonlOther6.4 KB —
runs/p2_A_final_f2/log.jsonlOther6.4 KB —
runs/p2_A_final_f3/log.jsonlOther6.4 KB —
runs/p2_A_final_f4/log.jsonlOther6.4 KB —
runs/p2_A_full_bigru_f0/log.jsonlOther4.2 KB —
runs/p2_A_full_f0/log.jsonlOther4.2 KB —
runs/p2_B_adapters_all/log.jsonlOther1.8 KB —
runs/p2_B_adapters_f0/log.jsonlOther6.4 KB —
runs/p2_B_adapters_f1/log.jsonlOther6.4 KB —
runs/p2_B_adapters_f2/log.jsonlOther6.4 KB —
runs/p2_B_adapters_f3/log.jsonlOther6.4 KB —
runs/p2_B_adapters_f4/log.jsonlOther6.4 KB —
runs/p2_B_bigru_aug_f0/log.jsonlOther4.2 KB —
runs/p2_B_bigru_aug_f1/log.jsonlOther4.2 KB —
runs/p2_B_bigru_dec_f0/log.jsonlOther4.2 KB —
runs/p2_B_bigru_dec_f1/log.jsonlOther4.3 KB —
runs/p2_B_bigru_drop_aug_e15_f0/log.jsonlOther6.4 KB —
runs/p2_B_bigru_drop_aug_e15_f1/log.jsonlOther6.4 KB —
runs/p2_B_bigru_drop_aug_f0/log.jsonlOther4.2 KB —
runs/p2_B_bigru_drop_aug_f1/log.jsonlOther4.3 KB —
runs/p2_B_bigru_drop_e15_f0/log.jsonlOther6.4 KB —
runs/p2_B_bigru_drop_e15_f1/log.jsonlOther6.4 KB —
runs/p2_B_bigru_drop_f0/log.jsonlOther4.2 KB —
runs/p2_B_bigru_drop_f1/log.jsonlOther4.2 KB —
runs/p2_B_bigru_lr2e5_f0/log.jsonlOther4.2 KB —
runs/p2_B_bigru_lr2e5_f1/log.jsonlOther4.2 KB —
runs/p2_B_final_all/log.jsonlOther1.8 KB —
runs/p2_B_final_f0/log.jsonlOther6.4 KB —
runs/p2_B_final_f1/log.jsonlOther6.4 KB —
runs/p2_B_final_f2/log.jsonlOther6.4 KB —
runs/p2_B_final_f3/log.jsonlOther6.7 KB —
runs/p2_B_final_f4/log.jsonlOther6.4 KB —
runs/p2_B_full_bigru_f0/log.jsonlOther4.2 KB —
runs/p2_B_full_f0/log.jsonlOther4.2 KB —
runs/p2_B_header_all/log.jsonlOther1.8 KB —
runs/p2_B_header_f0/log.jsonlOther6.8 KB —
runs/p2_B_header_f1/log.jsonlOther6.8 KB —
runs/p2_B_header_f2/log.jsonlOther6.8 KB —
runs/p2_B_header_f3/log.jsonlOther6.8 KB —
runs/p2_B_header_f4/log.jsonlOther6.8 KB —
runs/p2_B_lora_all/log.jsonlOther1.8 KB —
runs/p2_B_lora_f0/log.jsonlOther6.4 KB —
runs/p2_B_lora_f1/log.jsonlOther6.4 KB —
runs/p2_B_lora_f2/log.jsonlOther6.4 KB —
runs/p2_B_lora_f3/log.jsonlOther6.4 KB —
runs/p2_B_lora_f4/log.jsonlOther6.4 KB —
runs/p2_B_lorma_all/log.jsonlOther1.8 KB —
runs/p2_B_lorma_f0/log.jsonlOther6.4 KB —
runs/p2_B_lorma_f1/log.jsonlOther6.4 KB —
runs/p2_B_lorma_f2/log.jsonlOther6.4 KB —
runs/p2_B_lorma_f3/log.jsonlOther6.4 KB —
runs/p2_B_lorma_f4/log.jsonlOther6.4 KB —
runs/p2_B_partial_all/log.jsonlOther1.8 KB —
runs/p2_B_partial_f0/log.jsonlOther6.4 KB —
runs/p2_B_partial_f1/log.jsonlOther6.4 KB —
runs/p2_B_partial_f2/log.jsonlOther6.4 KB —
runs/p2_B_partial_f3/log.jsonlOther6.4 KB —
runs/p2_B_partial_f4/log.jsonlOther6.4 KB —
runs/p2_C_final_all/log.jsonlOther1.8 KB —
runs/p2_C_final_f0/log.jsonlOther6.3 KB —
runs/p2_C_final_f1/log.jsonlOther6.3 KB —
runs/p2_C_final_f2/log.jsonlOther6.3 KB —
runs/p2_C_final_f3/log.jsonlOther6.3 KB —
runs/p2_C_final_f4/log.jsonlOther6.3 KB —
runs/p2_C_full_bigru_f0/log.jsonlOther4.1 KB —
runs/p2_C_full_f0/log.jsonlOther4.0 KB —
runs/p2_D_final_all/log.jsonlOther1.8 KB —
runs/p2_D_final_f0/log.jsonlOther6.4 KB —
runs/p2_D_final_f1/log.jsonlOther6.4 KB —
runs/p2_D_final_f2/log.jsonlOther6.4 KB —
runs/p2_D_final_f3/log.jsonlOther6.4 KB —
runs/p2_D_final_f4/log.jsonlOther6.4 KB —
runs/p2_D_full_f0/log.jsonlOther4.2 KB —
runs/p2_D_full_linear_f0/log.jsonlOther4.2 KB —
runs/p2_E_final_f0/log.jsonlOther6.8 KB —
runs/p2_E_final_f1/log.jsonlOther6.7 KB —
runs/p2_E_final_f2/log.jsonlOther6.8 KB —
runs/p2_E_final_f3/log.jsonlOther6.7 KB —
runs/p2_E_final_f4/log.jsonlOther6.7 KB —
runs/p2_E_kd_all/log.jsonlOther1.8 KB —
runs/p2_E_kd_f0/log.jsonlOther6.7 KB —
runs/p2_E_kd_f1/log.jsonlOther6.7 KB —
runs/p2_E_kd_f2/log.jsonlOther6.7 KB —
runs/p2_E_kd_f3/log.jsonlOther6.7 KB —
runs/p2_E_kd_f4/log.jsonlOther6.7 KB —
runs/p3_B_cw_f0/log.jsonlOther612 B —
runs/p3_B_full_f0/log.jsonlOther6.3 KB —
runs/p3_B_full_f1/log.jsonlOther6.3 KB —
runs/p3_B_full_f2/log.jsonlOther6.3 KB —
runs/p3_B_full_f3/log.jsonlOther6.3 KB —
runs/p3_B_full_f4/log.jsonlOther6.3 KB —
runs/p3_B_sentonly_f1/log.jsonlOther6.3 KB —
runs/p3_B_sentonly_f2/log.jsonlOther6.3 KB —
runs/p3_B_sentonly_f3/log.jsonlOther5.0 KB —
runs/p3_B_window_f0/log.jsonlOther6.3 KB —
runs/p3_B_window_f1/log.jsonlOther6.3 KB —
runs/p3_B_window_f2/log.jsonlOther6.3 KB —
runs/p3_B_window_f3/log.jsonlOther6.3 KB —
runs/p3_B_window_f4/log.jsonlOther6.3 KB —
runs/proxy_ctx2048/log.jsonlOther23.7 KB —
runs/proxy_ctx512/log.jsonlOther23.7 KB —
runs/proxy_mix_natural/log.jsonlOther23.8 KB —
runs/proxy_mix_sc_heavy/log.jsonlOther23.8 KB —
runs/proxy_mix_sc_only/log.jsonlOther23.8 KB —
runs/zz_upload_test/test.txtOther5 B —
.gitattributesRepository1.5 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
49.8 GB
Download from Dev Sachan

Released by Dev Sachan through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published49.8 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.