Skip to page content
SAVRN
Search Plan a project

Open-weight model

programmatic-attention-checkpoints

by Laura Gomezjurado LauraGG/programmatic-attention-checkpoints

programmatic-attention-checkpoints is an open-weight model from Laura Gomezjurado. Its published files total 246.4 GB.

Parameters—
Context—
Weights246.4 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
LauraGG/programmatic-attention-checkpoints
Publisher
Laura Gomezjurado
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
40379b4b1f4da0b2aad011ac619ba895cad5365c
First published
2026-09-30
Last updated
2026-10-05

Files and Weights

417 files, 246.4 GB in total. The weights are 73 files totalling 246.4 GB in npz, pt, safetensors.

Weights73 files · 246.4 GB
Configuration242 files · 23.2 MB
Other101 files · 4.6 MB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
t10/checkpoints/auto_S16_tinyllama_ft_greedy_s0/final/model.safetensorsWeights3.9 GB 6f03135ff453
t10/checkpoints/auto_S16_tinyllama_ft_ioutop_s0/final/model.safetensorsWeights3.9 GB 0f43c015ded2
t10/checkpoints/auto_S16_tinyllama_random_fixedrand25_s0/final/model.safetensorsWeights3.9 GB 58d56d7e33dc
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_regtrivial144_lam1_s0/final/model.safetensorsWeights3.9 GB b48867030f09
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_s0/final/model.safetensorsWeights3.9 GB 91919ba116ef
t10/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/final/model.safetensorsWeights3.9 GB addb15667536
t10/checkpoints/auto_S16_tinyllama_random_regshuffle25_lam1_s0/final/model.safetensorsWeights3.9 GB 02316973aeb6
t10/checkpoints/auto_S16_tinyllama_random_zero25_s1/final/model.safetensorsWeights3.9 GB 3e38f12595c0
t10/checkpoints/auto_S16_tinyllama_random_zerotask32_s0/final/model.safetensorsWeights3.9 GB bbf098239829
t5/checkpoints/auto_S16_tinyllama_ft_dense_s0/final/model.safetensorsWeights3.9 GB 2d745e971762
t5/checkpoints/auto_S16_tinyllama_random_dense_s1/final/model.safetensorsWeights3.9 GB f33525b78dce
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s0/final/model.safetensorsWeights3.9 GB 6054b3b445c6
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s1/final/model.safetensorsWeights3.9 GB 82252d764df0
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s2/final/model.safetensorsWeights3.9 GB 5699fc884480
t7/checkpoints/invalid_leak_ft_fixed25_s0/final/model.safetensorsWeights4.4 GB ae9f608401ba
t7/checkpoints/invalid_leak_random_fixed25_s0/last/model.safetensorsWeights4.4 GB 99863ed1d91d
t7/checkpoints/wikitext_tinyllama250m_lrsweep_1e-3_s0/final/model.safetensorsWeights983.7 MB 13696c20bdc4
t7/checkpoints/wikitext_tinyllama250m_lrsweep_1e-3_s0/last/model.safetensorsWeights983.7 MB 3a7bd9be34c3
t7/checkpoints/wikitext_tinyllama250m_lrsweep_1e-3_s0/last/optim.ptWeights2.0 GB 4f7482897843
t7/checkpoints/wikitext_tinyllama250m_lrsweep_3e-4_s0/final/model.safetensorsWeights983.7 MB 740828617838
t7/checkpoints/wikitext_tinyllama250m_lrsweep_3e-4_s0/last/model.safetensorsWeights983.7 MB 5cbe64704dd7
t7/checkpoints/wikitext_tinyllama250m_lrsweep_3e-4_s0/last/optim.ptWeights2.0 GB 9265576d6636
t7/checkpoints/wikitext_tinyllama250m_lrsweep_6e-4_s0/final/model.safetensorsWeights983.7 MB a1bea7f32207
t7/checkpoints/wikitext_tinyllama250m_random_dense_s0/last/model.safetensorsWeights983.7 MB dbf50e9685c2
t7/checkpoints/wikitext_tinyllama250m_random_dense_s0/last/optim.ptWeights2.0 GB 93129f28a44a
t7/checkpoints/wikitext_tinyllama_ft1p_dense_s0/final/model.safetensorsWeights4.4 GB 2e2c84a1121a
t7/checkpoints/wikitext_tinyllama_ft1p_dense_s0/last/model.safetensorsWeights4.4 GB 141a8d9ebbcb
t7/checkpoints/wikitext_tinyllama_ft1p_dense_s0/last/optim.ptWeights8.8 GB 0c9bb3ce3160
t7/checkpoints/wikitext_tinyllama_ft1p_fixed25_s0/final/model.safetensorsWeights4.4 GB 8f7d12849ae5
t7/checkpoints/wikitext_tinyllama_ft1p_fixed25_s0/last/model.safetensorsWeights4.4 GB a99e558d6b10
t7/checkpoints/wikitext_tinyllama_ft1p_fixed25_s0/last/optim.ptWeights8.8 GB ef2050fc23e2
t7/checkpoints/wikitext_tinyllama_random2p_dense_s0/last/model.safetensorsWeights4.4 GB b32d8dc32eeb
t7/checkpoints/wikitext_tinyllama_random2p_dense_s0/last/optim.ptWeights8.8 GB d7aceb0cc35d
t7/checkpoints/wikitext_tinyllama_random2p_fixed25_s0/final/model.safetensorsWeights4.4 GB 931821f45b39
t7/checkpoints/wikitext_tinyllama_random2p_fixed25_s0/last/model.safetensorsWeights4.4 GB f114d8df8294
t7/checkpoints/wikitext_tinyllama_random2p_fixed25_s0/last/optim.ptWeights8.8 GB 876a738ef7b5
t7/results/t7_head_fits_tinyllama_wikitext_raw.npzWeights55.4 MB 55db6bd9dc73
t7/results/t7_head_fits_tinyllama_wikitext_scores.npzWeights1.8 MB 23d473dfaf30
t8/checkpoints/auto_S16_tinyllama_ft_fixed100_s0/final/model.safetensorsWeights3.9 GB 89e5e51b326c
t8/checkpoints/auto_S16_tinyllama_ft_fixed25_s0/final/model.safetensorsWeights3.9 GB 32d563c10449
t8/checkpoints/auto_S16_tinyllama_ft_freezeqk25_s0/final/model.safetensorsWeights3.9 GB baa51862f5cf
t8/checkpoints/auto_S16_tinyllama_ft_freezeqk25_s0/frozen_qk.ptWeights184.6 MB b1a80b843873
t8/checkpoints/auto_S16_tinyllama_ft_iter100_s0/final/model.safetensorsWeights3.9 GB 515380dbf84e
t8/checkpoints/auto_S16_tinyllama_ft_iter50_s0/final/model.safetensorsWeights3.9 GB 53429ed4c447
t8/checkpoints/auto_S16_tinyllama_ft_iter75_s0/final/model.safetensorsWeights3.9 GB a1a222d3df50
t8/checkpoints/auto_S16_tinyllama_ft_shuffle25_s0/final/model.safetensorsWeights3.9 GB 74a29f43c8ee
t8/checkpoints/auto_S16_tinyllama_ft_zero25_s0/final/model.safetensorsWeights3.9 GB 425fca5f5c05
t8/checkpoints/auto_S16_tinyllama_random_dense_s0/final/model.safetensorsWeights3.9 GB d9b6a3457de7
t8/checkpoints/auto_S16_tinyllama_random_dense_s0/last/model.safetensorsWeights3.9 GB 8c85ddcc162c
t8/checkpoints/auto_S16_tinyllama_random_dense_s0/last/optim.ptWeights7.8 GB 543d199a8628
t8/checkpoints/auto_S16_tinyllama_random_fixed100_s0/final/model.safetensorsWeights3.9 GB eb9edca3bd10
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/final/model.safetensorsWeights3.9 GB 8f4b24a534ed
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/frozen_qk.ptWeights184.6 MB 50e5f98799f9
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/last/model.safetensorsWeights3.9 GB 317d130286f4
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/last/optim.ptWeights7.8 GB 14a730ca9e45
t8/checkpoints/auto_S16_tinyllama_random_shuffle25_s0/final/model.safetensorsWeights3.9 GB 1a74f4480cab
t8/checkpoints/auto_S16_tinyllama_random_shuffle25_s0/last/model.safetensorsWeights3.9 GB 7959c60a3839
t8/checkpoints/auto_S16_tinyllama_random_shuffle25_s0/last/optim.ptWeights7.8 GB eaabe0ec09eb
t8/checkpoints/auto_S16_tinyllama_random_zero25_s0/final/model.safetensorsWeights3.9 GB e0a601675238
t8/results/t5_attn_auto_S16_tinyllama_ft_fixed100_s0.npzWeights40.0 MB 67cfe5393014
t8/results/t5_attn_auto_S16_tinyllama_ft_freezeqk25_s0.npzWeights28.8 MB 2542883a5fe2
t8/results/t5_attn_auto_S16_tinyllama_ft_iter100_s0.npzWeights38.1 MB 18ff951196e0
t8/results/t5_attn_auto_S16_tinyllama_ft_iter50_s0.npzWeights28.2 MB 1acbf219621f
t8/results/t5_attn_auto_S16_tinyllama_ft_iter75_s0.npzWeights28.8 MB f5e4cfbf997d
t8/results/t5_attn_auto_S16_tinyllama_ft_shuffle25_s0.npzWeights36.7 MB 88d709825eb4
t8/results/t5_attn_auto_S16_tinyllama_ft_zero25_s0.npzWeights32.4 MB 3a15ccb6c45f
t8/results/t5_attn_auto_S16_tinyllama_random_fixed100_s0.npzWeights114.8 MB 2c4081f5644c
t8/results/t5_attn_auto_S16_tinyllama_random_zero25_s0.npzWeights62.1 MB 9381a8ea6d8b
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_rel2000_s0/final/model.safetensorsWeights3.9 GB 4dcd0f195e07
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_s0/final/model.safetensorsWeights3.9 GB d777c559f838
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_rel2000_s0/final/model.safetensorsWeights3.9 GB f8dbc2076da1
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s0/final/model.safetensorsWeights3.9 GB bf73e37dc272
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/final/model.safetensorsWeights3.9 GB addb15667536
t10/checkpoints/auto_S16_tinyllama_ft_greedy_s0/assignments.jsonConfiguration25.7 KB —
t10/checkpoints/auto_S16_tinyllama_ft_greedy_s0/final/config.jsonConfiguration676 B —
t10/checkpoints/auto_S16_tinyllama_ft_greedy_s0/final/generation_config.jsonConfiguration91 B —
t10/checkpoints/auto_S16_tinyllama_ft_greedy_s0/final/progattn.jsonConfiguration28.8 KB —
t10/checkpoints/auto_S16_tinyllama_ft_ioutop_s0/assignments.jsonConfiguration25.8 KB —
t10/checkpoints/auto_S16_tinyllama_ft_ioutop_s0/final/config.jsonConfiguration676 B —
t10/checkpoints/auto_S16_tinyllama_ft_ioutop_s0/final/generation_config.jsonConfiguration91 B —
t10/checkpoints/auto_S16_tinyllama_ft_ioutop_s0/final/progattn.jsonConfiguration28.9 KB —
t10/checkpoints/auto_S16_tinyllama_random_fixedrand25_s0/assignments.jsonConfiguration19.8 KB —
t10/checkpoints/auto_S16_tinyllama_random_fixedrand25_s0/final/config.jsonConfiguration676 B —
t10/checkpoints/auto_S16_tinyllama_random_fixedrand25_s0/final/generation_config.jsonConfiguration91 B —
t10/checkpoints/auto_S16_tinyllama_random_fixedrand25_s0/final/progattn.jsonConfiguration22.6 KB —
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_regtrivial144_lam1_s0/assignments.jsonConfiguration20.4 KB —
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_regtrivial144_lam1_s0/final/config.jsonConfiguration676 B —
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_regtrivial144_lam1_s0/final/generation_config.jsonConfiguration91 B —
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_regtrivial144_lam1_s0/final/progattn.jsonConfiguration42.0 KB —
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_s0/assignments.jsonConfiguration8.6 KB —
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_s0/final/config.jsonConfiguration676 B —
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_s0/final/generation_config.jsonConfiguration91 B —
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_s0/final/progattn.jsonConfiguration11.4 KB —
t10/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/assignments.jsonConfiguration20.3 KB —
t10/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/final/config.jsonConfiguration676 B —
t10/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/final/generation_config.jsonConfiguration91 B —
t10/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/final/progattn.jsonConfiguration46.2 KB —
t10/checkpoints/auto_S16_tinyllama_random_regshuffle25_lam1_s0/assignments.jsonConfiguration20.8 KB —
t10/checkpoints/auto_S16_tinyllama_random_regshuffle25_lam1_s0/final/config.jsonConfiguration676 B —
t10/checkpoints/auto_S16_tinyllama_random_regshuffle25_lam1_s0/final/generation_config.jsonConfiguration91 B —
t10/checkpoints/auto_S16_tinyllama_random_regshuffle25_lam1_s0/final/progattn.jsonConfiguration46.8 KB —
t10/checkpoints/auto_S16_tinyllama_random_zero25_s1/assignments.jsonConfiguration20.2 KB —
t10/checkpoints/auto_S16_tinyllama_random_zero25_s1/final/config.jsonConfiguration676 B —
t10/checkpoints/auto_S16_tinyllama_random_zero25_s1/final/generation_config.jsonConfiguration91 B —
t10/checkpoints/auto_S16_tinyllama_random_zero25_s1/final/progattn.jsonConfiguration23.1 KB —
t10/checkpoints/auto_S16_tinyllama_random_zerotask32_s0/assignments.jsonConfiguration8.6 KB —
t10/checkpoints/auto_S16_tinyllama_random_zerotask32_s0/final/config.jsonConfiguration676 B —
t10/checkpoints/auto_S16_tinyllama_random_zerotask32_s0/final/generation_config.jsonConfiguration91 B —
t10/checkpoints/auto_S16_tinyllama_random_zerotask32_s0/final/progattn.jsonConfiguration11.4 KB —
t10/results/t10_group_ablation.jsonConfiguration7.3 KB —
t10/results/t10_swap_eval_all.jsonConfiguration10.1 KB —
t10/results/t5_auto_S16_tinyllama_ft_greedy_s0.jsonConfiguration586.0 KB —
t10/results/t5_auto_S16_tinyllama_ft_ioutop_s0.jsonConfiguration609.6 KB —
t10/results/t5_auto_S16_tinyllama_random_fixedrand25_s0.jsonConfiguration781.5 KB —
t10/results/t5_auto_S16_tinyllama_random_fixedtask32_regtrivial144_lam1_s0.jsonConfiguration774.8 KB —
t10/results/t5_auto_S16_tinyllama_random_fixedtask32_s0.jsonConfiguration673.2 KB —
t10/results/t5_auto_S16_tinyllama_random_reg25_lam1_s1.jsonConfiguration875.0 KB —
t10/results/t5_auto_S16_tinyllama_random_regshuffle25_lam1_s0.jsonConfiguration830.4 KB —
t10/results/t5_auto_S16_tinyllama_random_zero25_s1.jsonConfiguration780.6 KB —
t10/results/t5_auto_S16_tinyllama_random_zerotask32_s0.jsonConfiguration718.2 KB —
t5/checkpoints/auto_S16_tinyllama_ft_dense_s0/final/config.jsonConfiguration676 B —
t5/checkpoints/auto_S16_tinyllama_ft_dense_s0/final/generation_config.jsonConfiguration91 B —
t5/checkpoints/auto_S16_tinyllama_ft_dense_s0/final/progattn.jsonConfiguration8.3 KB —
t5/checkpoints/auto_S16_tinyllama_random_dense_s1/final/config.jsonConfiguration676 B —
t5/checkpoints/auto_S16_tinyllama_random_dense_s1/final/generation_config.jsonConfiguration91 B —
t5/checkpoints/auto_S16_tinyllama_random_dense_s1/final/progattn.jsonConfiguration8.1 KB —
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s0/final/config.jsonConfiguration676 B —
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s0/final/generation_config.jsonConfiguration91 B —
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s0/final/progattn.jsonConfiguration22.7 KB —
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s1/final/config.jsonConfiguration676 B —
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s1/final/generation_config.jsonConfiguration91 B —
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s1/final/progattn.jsonConfiguration22.7 KB —
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s2/final/config.jsonConfiguration676 B —
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s2/final/generation_config.jsonConfiguration91 B —
t5/checkpoints/auto_S16_tinyllama_random_fixed25_s2/final/progattn.jsonConfiguration22.7 KB —
t7/checkpoints/invalid_leak_ft_fixed25_s0/assignments.jsonConfiguration16.3 KB —
t7/checkpoints/invalid_leak_ft_fixed25_s0/final/config.jsonConfiguration675 B —
t7/checkpoints/invalid_leak_ft_fixed25_s0/final/generation_config.jsonConfiguration124 B —
t7/checkpoints/invalid_leak_ft_fixed25_s0/final/progattn.jsonConfiguration17.3 KB —
t7/checkpoints/invalid_leak_random_fixed25_s0/assignments.jsonConfiguration16.3 KB —
t7/checkpoints/invalid_leak_random_fixed25_s0/last/config.jsonConfiguration675 B —
t7/checkpoints/invalid_leak_random_fixed25_s0/last/generation_config.jsonConfiguration111 B —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_1e-3_s0/assignments.jsonConfiguration2.2 KB —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_1e-3_s0/final/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_1e-3_s0/final/generation_config.jsonConfiguration111 B —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_1e-3_s0/final/progattn.jsonConfiguration3.1 KB —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_1e-3_s0/last/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_1e-3_s0/last/generation_config.jsonConfiguration111 B —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_1e-3_s0/last/progattn.jsonConfiguration2.2 KB —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_3e-4_s0/assignments.jsonConfiguration2.2 KB —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_3e-4_s0/final/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_3e-4_s0/final/generation_config.jsonConfiguration111 B —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_3e-4_s0/final/progattn.jsonConfiguration3.1 KB —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_3e-4_s0/last/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_3e-4_s0/last/generation_config.jsonConfiguration111 B —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_3e-4_s0/last/progattn.jsonConfiguration2.2 KB —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_6e-4_s0/assignments.jsonConfiguration2.2 KB —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_6e-4_s0/final/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_6e-4_s0/final/generation_config.jsonConfiguration111 B —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_6e-4_s0/final/progattn.jsonConfiguration3.1 KB —
t7/checkpoints/wikitext_tinyllama250m_random_dense_s0/assignments.jsonConfiguration2.2 KB —
t7/checkpoints/wikitext_tinyllama250m_random_dense_s0/last/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama250m_random_dense_s0/last/generation_config.jsonConfiguration111 B —
t7/checkpoints/wikitext_tinyllama250m_random_dense_s0/last/progattn.jsonConfiguration2.2 KB —
t7/checkpoints/wikitext_tinyllama_ft1p_dense_s0/assignments.jsonConfiguration2.1 KB —
t7/checkpoints/wikitext_tinyllama_ft1p_dense_s0/final/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama_ft1p_dense_s0/final/generation_config.jsonConfiguration124 B —
t7/checkpoints/wikitext_tinyllama_ft1p_dense_s0/final/progattn.jsonConfiguration3.0 KB —
t7/checkpoints/wikitext_tinyllama_ft1p_dense_s0/last/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama_ft1p_dense_s0/last/generation_config.jsonConfiguration124 B —
t7/checkpoints/wikitext_tinyllama_ft1p_dense_s0/last/progattn.jsonConfiguration2.2 KB —
t7/checkpoints/wikitext_tinyllama_ft1p_fixed25_s0/assignments.jsonConfiguration16.3 KB —
t7/checkpoints/wikitext_tinyllama_ft1p_fixed25_s0/final/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama_ft1p_fixed25_s0/final/generation_config.jsonConfiguration124 B —
t7/checkpoints/wikitext_tinyllama_ft1p_fixed25_s0/final/progattn.jsonConfiguration17.3 KB —
t7/checkpoints/wikitext_tinyllama_ft1p_fixed25_s0/last/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama_ft1p_fixed25_s0/last/generation_config.jsonConfiguration124 B —
t7/checkpoints/wikitext_tinyllama_ft1p_fixed25_s0/last/progattn.jsonConfiguration16.4 KB —
t7/checkpoints/wikitext_tinyllama_random2p_dense_s0/assignments.jsonConfiguration2.1 KB —
t7/checkpoints/wikitext_tinyllama_random2p_dense_s0/last/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama_random2p_dense_s0/last/generation_config.jsonConfiguration111 B —
t7/checkpoints/wikitext_tinyllama_random2p_dense_s0/last/progattn.jsonConfiguration2.2 KB —
t7/checkpoints/wikitext_tinyllama_random2p_fixed25_s0/assignments.jsonConfiguration16.3 KB —
t7/checkpoints/wikitext_tinyllama_random2p_fixed25_s0/final/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama_random2p_fixed25_s0/final/generation_config.jsonConfiguration111 B —
t7/checkpoints/wikitext_tinyllama_random2p_fixed25_s0/final/progattn.jsonConfiguration17.3 KB —
t7/checkpoints/wikitext_tinyllama_random2p_fixed25_s0/last/config.jsonConfiguration675 B —
t7/checkpoints/wikitext_tinyllama_random2p_fixed25_s0/last/generation_config.jsonConfiguration111 B —
t7/checkpoints/wikitext_tinyllama_random2p_fixed25_s0/last/progattn.jsonConfiguration16.4 KB —
t7/checkpoints/wikitext_tinyllama_random_drop10_dense_s0/assignments.jsonConfiguration2.1 KB —
t7/code/t7_causal_select.pyConfiguration7.3 KB —
t7/code/t7_score_heads.pyConfiguration10.8 KB —
t7/code/t7_wikitext_train.pyConfiguration20.2 KB —
t7/logs/leak_test.pyConfiguration1.3 KB —
t7/results/invalid_leak/t7_assignments_wikitext_frac25_uncausal.jsonConfiguration11.9 KB —
t7/results/invalid_leak/t7_wikitext_tinyllama_ft_fixed25_s0.jsonConfiguration168.7 KB —
t7/results/t7_assignments_wikitext_frac25.jsonConfiguration14.6 KB —
t7/results/t7_assignments_wikitext_frac25_causal.jsonConfiguration14.6 KB —
t7/results/t7_head_fits_tinyllama_wikitext.jsonConfiguration299.9 KB —
t7/results/t7_wikitext_tinyllama250m_lrsweep_1e-3_s0.jsonConfiguration51.8 KB —
t7/results/t7_wikitext_tinyllama250m_lrsweep_3e-4_s0.jsonConfiguration52.6 KB —
t7/results/t7_wikitext_tinyllama250m_lrsweep_6e-4_s0.jsonConfiguration52.6 KB —
t7/results/t7_wikitext_tinyllama_ft1p_dense_s0.jsonConfiguration53.7 KB —
t7/results/t7_wikitext_tinyllama_ft1p_fixed25_s0.jsonConfiguration67.9 KB —
t7/results/t7_wikitext_tinyllama_ft_dense_s0.jsonConfiguration92.1 KB —
t7/results/t7_wikitext_tinyllama_random2p_fixed25_s0.jsonConfiguration —
t7/results/t7_wikitext_tinyllama_random_dense_s0.jsonConfiguration213.0 KB —
t8/checkpoints/auto_S16_tinyllama_ft_fixed100_s0/assignments.jsonConfiguration64.1 KB —
t8/checkpoints/auto_S16_tinyllama_ft_fixed100_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_ft_fixed100_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_ft_fixed100_s0/final/progattn.jsonConfiguration66.9 KB —
t8/checkpoints/auto_S16_tinyllama_ft_fixed25_s0/assignments.jsonConfiguration20.5 KB —
t8/checkpoints/auto_S16_tinyllama_ft_fixed25_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_ft_fixed25_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_ft_fixed25_s0/final/progattn.jsonConfiguration23.0 KB —
t8/checkpoints/auto_S16_tinyllama_ft_freezeqk25_s0/assignments.jsonConfiguration20.3 KB —
t8/checkpoints/auto_S16_tinyllama_ft_freezeqk25_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_ft_freezeqk25_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_ft_freezeqk25_s0/final/progattn.jsonConfiguration23.1 KB —
t8/checkpoints/auto_S16_tinyllama_ft_iter100_s0/assignments.jsonConfiguration63.7 KB —
t8/checkpoints/auto_S16_tinyllama_ft_iter100_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_ft_iter100_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_ft_iter100_s0/final/progattn.jsonConfiguration66.5 KB —
t8/checkpoints/auto_S16_tinyllama_ft_iter50_s0/assignments.jsonConfiguration34.5 KB —
t8/checkpoints/auto_S16_tinyllama_ft_iter50_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_ft_iter50_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_ft_iter50_s0/final/progattn.jsonConfiguration37.3 KB —
t8/checkpoints/auto_S16_tinyllama_ft_iter75_s0/assignments.jsonConfiguration49.0 KB —
t8/checkpoints/auto_S16_tinyllama_ft_iter75_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_ft_iter75_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_ft_iter75_s0/final/progattn.jsonConfiguration51.8 KB —
t8/checkpoints/auto_S16_tinyllama_ft_shuffle25_s0/assignments.jsonConfiguration20.8 KB —
t8/checkpoints/auto_S16_tinyllama_ft_shuffle25_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_ft_shuffle25_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_ft_shuffle25_s0/final/progattn.jsonConfiguration23.7 KB —
t8/checkpoints/auto_S16_tinyllama_ft_zero25_s0/assignments.jsonConfiguration20.3 KB —
t8/checkpoints/auto_S16_tinyllama_ft_zero25_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_ft_zero25_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_ft_zero25_s0/final/progattn.jsonConfiguration23.1 KB —
t8/checkpoints/auto_S16_tinyllama_random_dense_s0/assignments.jsonConfiguration5.6 KB —
t8/checkpoints/auto_S16_tinyllama_random_dense_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_random_dense_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_random_dense_s0/final/progattn.jsonConfiguration8.1 KB —
t8/checkpoints/auto_S16_tinyllama_random_dense_s0/last/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_random_dense_s0/last/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_random_dense_s0/last/progattn.jsonConfiguration5.6 KB —
t8/checkpoints/auto_S16_tinyllama_random_fixed100_s0/assignments.jsonConfiguration63.9 KB —
t8/checkpoints/auto_S16_tinyllama_random_fixed100_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_random_fixed100_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_random_fixed100_s0/final/progattn.jsonConfiguration66.7 KB —
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/assignments.jsonConfiguration20.1 KB —
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/final/progattn.jsonConfiguration22.9 KB —
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/last/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/last/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/last/progattn.jsonConfiguration20.2 KB —
t8/checkpoints/auto_S16_tinyllama_random_shuffle25_s0/assignments.jsonConfiguration20.7 KB —
t8/checkpoints/auto_S16_tinyllama_random_shuffle25_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_random_shuffle25_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_random_shuffle25_s0/final/progattn.jsonConfiguration23.5 KB —
t8/checkpoints/auto_S16_tinyllama_random_shuffle25_s0/last/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_random_shuffle25_s0/last/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_random_shuffle25_s0/last/progattn.jsonConfiguration20.7 KB —
t8/checkpoints/auto_S16_tinyllama_random_zero25_s0/assignments.jsonConfiguration20.1 KB —
t8/checkpoints/auto_S16_tinyllama_random_zero25_s0/final/config.jsonConfiguration676 B —
t8/checkpoints/auto_S16_tinyllama_random_zero25_s0/final/generation_config.jsonConfiguration91 B —
t8/checkpoints/auto_S16_tinyllama_random_zero25_s0/final/progattn.jsonConfiguration22.9 KB —
t8/checkpoints/t8_heads/all704.jsonConfiguration58.5 KB —
t8/checkpoints/t8_heads/amiri25.jsonConfiguration14.7 KB —
t8/checkpoints/t8_heads/iter100.jsonConfiguration58.2 KB —
t8/checkpoints/t8_heads/iter50.jsonConfiguration28.9 KB —
t8/checkpoints/t8_heads/iter75.jsonConfiguration43.4 KB —
t8/checkpoints/t8_heads/shuffle25_seed0.jsonConfiguration15.1 KB —
t8/code/t5_automata_train.pyConfiguration26.5 KB —
t8/code/t8_assignments.pyConfiguration4.8 KB —
t8/code/t8_swap_eval.pyConfiguration4.0 KB —
t8/results/t5_auto_S16_tinyllama_ft_fixed100_s0.jsonConfiguration680.6 KB —
t8/results/t5_auto_S16_tinyllama_ft_fixed25_s0.jsonConfiguration606.7 KB —
t8/results/t5_auto_S16_tinyllama_ft_freezeqk25_s0.jsonConfiguration579.8 KB —
t8/results/t5_auto_S16_tinyllama_ft_iter100_s0.jsonConfiguration667.1 KB —
t8/results/t5_auto_S16_tinyllama_ft_iter50_s0.jsonConfiguration596.4 KB —
t8/results/t5_auto_S16_tinyllama_ft_iter75_s0.jsonConfiguration609.8 KB —
t8/results/t5_auto_S16_tinyllama_ft_shuffle25_s0.jsonConfiguration748.5 KB —
t8/results/t5_auto_S16_tinyllama_ft_zero25_s0.jsonConfiguration728.0 KB —
t8/results/t5_auto_S16_tinyllama_random_dense_s0.jsonConfiguration806.5 KB —
t8/results/t5_auto_S16_tinyllama_random_fixed100_s0.jsonConfiguration721.2 KB —
t8/results/t5_auto_S16_tinyllama_random_freezeqk25_s0.jsonConfiguration790.0 KB —
t8/results/t5_auto_S16_tinyllama_random_shuffle25_s0.jsonConfiguration667.8 KB —
t8/results/t5_auto_S16_tinyllama_random_zero25_s0.jsonConfiguration793.0 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_rel2000_s0/assignments.jsonConfiguration20.3 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_rel2000_s0/final/config.jsonConfiguration676 B —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_rel2000_s0/final/generation_config.jsonConfiguration91 B —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_rel2000_s0/final/progattn.jsonConfiguration45.3 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_s0/assignments.jsonConfiguration20.3 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_s0/final/config.jsonConfiguration676 B —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_s0/final/generation_config.jsonConfiguration91 B —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_s0/final/progattn.jsonConfiguration45.9 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_rel2000_s0/assignments.jsonConfiguration20.3 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_rel2000_s0/final/config.jsonConfiguration676 B —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_rel2000_s0/final/generation_config.jsonConfiguration91 B —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_rel2000_s0/final/progattn.jsonConfiguration45.3 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s0/assignments.jsonConfiguration20.3 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s0/final/config.jsonConfiguration676 B —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s0/final/generation_config.jsonConfiguration91 B —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s0/final/progattn.jsonConfiguration45.8 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/assignments.jsonConfiguration20.3 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/final/config.jsonConfiguration676 B —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/final/generation_config.jsonConfiguration91 B —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/final/progattn.jsonConfiguration46.2 KB —
t9/results/t5_auto_S16_tinyllama_random_reg25_lam0p1_rel2000_s0.jsonConfiguration777.2 KB —
t9/results/t5_auto_S16_tinyllama_random_reg25_lam0p1_s0.jsonConfiguration823.0 KB —
t9/results/t5_auto_S16_tinyllama_random_reg25_lam1_rel2000_s0.jsonConfiguration831.5 KB —
t9/results/t5_auto_S16_tinyllama_random_reg25_lam1_s0.jsonConfiguration894.7 KB —
t9/results/t5_auto_S16_tinyllama_random_reg25_lam1_s1.jsonConfiguration875.0 KB —
t10/checkpoints/auto_S16_tinyllama_ft_greedy_s0/log.jsonlOther22.0 KB —
t10/checkpoints/auto_S16_tinyllama_ft_ioutop_s0/log.jsonlOther40.2 KB —
t10/checkpoints/auto_S16_tinyllama_random_fixedrand25_s0/log.jsonlOther176.1 KB —
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_regtrivial144_lam1_s0/log.jsonlOther158.2 KB —
t10/checkpoints/auto_S16_tinyllama_random_fixedtask32_s0/log.jsonlOther101.5 KB —
t10/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/log.jsonlOther232.4 KB —
t10/checkpoints/auto_S16_tinyllama_random_regshuffle25_lam1_s0/log.jsonlOther197.1 KB —
t10/checkpoints/auto_S16_tinyllama_random_zero25_s1/log.jsonlOther175.0 KB —
t10/checkpoints/auto_S16_tinyllama_random_zerotask32_s0/log.jsonlOther135.9 KB —
t10/logs/run_t10_series.logOther5.4 KB —
t10/logs/t10_group_ablation.logOther2.3 KB —
t10/logs/t10_swap_eval_all.logOther2.8 KB —
t10/logs/t10_swap_lam1.logOther193 B —
t7/checkpoints/invalid_leak_ft_fixed25_s0/log.jsonlOther116.0 KB —
t7/checkpoints/invalid_leak_random_fixed25_s0/log.jsonlOther11.7 KB —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_1e-3_s0/log.jsonlOther36.8 KB —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_3e-4_s0/log.jsonlOther37.6 KB —
t7/checkpoints/wikitext_tinyllama250m_lrsweep_6e-4_s0/log.jsonlOther37.5 KB —
t7/checkpoints/wikitext_tinyllama250m_random_dense_s0/log.jsonlOther —
t7/checkpoints/wikitext_tinyllama_ft1p_dense_s0/log.jsonlOther38.4 KB —
t7/checkpoints/wikitext_tinyllama_ft1p_fixed25_s0/log.jsonlOther38.4 KB —
t7/checkpoints/wikitext_tinyllama_random2p_dense_s0/log.jsonlOther31.2 KB —
t7/checkpoints/wikitext_tinyllama_random2p_fixed25_s0/log.jsonlOther78.3 KB —
t7/checkpoints/wikitext_tinyllama_random_drop10_dense_s0/log.jsonlOther451 B —
t7/code/run_t7_wikitext.shOther3.2 KB —
t7/logs/invalid_leak_ft_fixed25_s0.logOther51.6 KB —
t7/logs/invalid_leak_random_fixed25_s0.logOther5.5 KB —
t7/logs/pip.logOther1.4 KB —
t7/logs/requeue_t7.shOther356 B —
t7/logs/run_t7_wikitext.logOther899 B —
t7/logs/run_t7_wikitext.pod.shOther2.7 KB —
t7/logs/t7_ft_fixed25_s0_aborted_8workers.logOther522 B —
t7/logs/t7_score_heads.logOther1.1 KB —
t7/logs/t7_store.logOther1.2 KB —
t7/logs/t7_wikitext_tinyllama_ft_dense_s0.logOther30.5 KB —
t7/logs/t7_wikitext_tinyllama_random_dense_s0.logOther71.4 KB —
t7/logs_pod2/run_t7_wikitext.logOther1.0 KB —
t7/logs_pod3/run_t7_wikitext.logOther —
t7/logs_pod3/t7_wikitext_tinyllama250m_lrsweep_1e-3_s0.logOther17.1 KB —
t7/logs_pod3/t7_wikitext_tinyllama250m_lrsweep_3e-4_s0.logOther17.1 KB —
t7/logs_pod3/t7_wikitext_tinyllama250m_lrsweep_6e-4_s0.logOther17.1 KB —
t7/logs_pod3/t7_wikitext_tinyllama250m_random_dense_s0.logOther —
t7/logs_pod3/t7_wikitext_tinyllama_ft1p_dense_s0.logOther17.4 KB —
t7/logs_pod3/t7_wikitext_tinyllama_ft1p_fixed25_s0.logOther17.4 KB —
t7/logs_pod3/t7_wikitext_tinyllama_random2p_dense_s0.logOther16.0 KB —
t7/logs_pod3/t7_wikitext_tinyllama_random2p_fixed25_s0.logOther34.5 KB —
t7/logs_pod3/t7_wikitext_tinyllama_random_drop10_dense_s0.logOther1.8 KB —
t8/checkpoints/auto_S16_tinyllama_ft_fixed100_s0/log.jsonlOther65.4 KB —
t8/checkpoints/auto_S16_tinyllama_ft_freezeqk25_s0/log.jsonlOther21.2 KB —
t8/checkpoints/auto_S16_tinyllama_ft_iter100_s0/log.jsonlOther55.5 KB —
t8/checkpoints/auto_S16_tinyllama_ft_iter50_s0/log.jsonlOther23.6 KB —
t8/checkpoints/auto_S16_tinyllama_ft_iter75_s0/log.jsonlOther22.8 KB —
t8/checkpoints/auto_S16_tinyllama_ft_shuffle25_s0/log.jsonlOther150.0 KB —
t8/checkpoints/auto_S16_tinyllama_ft_zero25_s0/log.jsonlOther134.7 KB —
t8/checkpoints/auto_S16_tinyllama_random_dense_s0/log.jsonlOther206.4 KB —
t8/checkpoints/auto_S16_tinyllama_random_fixed100_s0/log.jsonlOther98.4 KB —
t8/checkpoints/auto_S16_tinyllama_random_freezeqk25_s0/log.jsonlOther182.8 KB —
t8/checkpoints/auto_S16_tinyllama_random_shuffle25_s0/log.jsonlOther89.3 KB —
t8/checkpoints/auto_S16_tinyllama_random_zero25_s0/log.jsonlOther185.0 KB —
t8/code/run_t8_series.shOther4.3 KB —
t8/code/run_t8_series_v2.shOther4.3 KB —
t8/logs/reorder_t8.shOther629 B —
t8/logs/run_t8_series.logOther2.6 KB —
t8/logs/t5_auto_S16_tinyllama_ft_fixed100_s0.logOther8.6 KB —
t8/logs/t5_auto_S16_tinyllama_ft_freezeqk25_s0.logOther3.4 KB —
t8/logs/t5_auto_S16_tinyllama_ft_iter100_s0.logOther7.4 KB —
t8/logs/t5_auto_S16_tinyllama_ft_iter50_s0.logOther3.7 KB —
t8/logs/t5_auto_S16_tinyllama_ft_iter75_s0.logOther3.6 KB —
t8/logs/t5_auto_S16_tinyllama_ft_shuffle25_s0.logOther18.4 KB —
t8/logs/t5_auto_S16_tinyllama_ft_zero25_s0.logOther16.7 KB —
t8/logs/t5_auto_S16_tinyllama_random_fixed100_s0.logOther12.4 KB —
t8/logs/t5_auto_S16_tinyllama_random_freezeqk25_s0.logOther3.8 KB —
t8/logs/t5_auto_S16_tinyllama_random_zero25_s0.logOther22.6 KB —
t8/logs_pod2/run_t8_series.logOther3.4 KB —
t8/logs_pod2/t5_auto_S16_tinyllama_ft_fixed100_s0.logOther8.6 KB —
t8/logs_pod2/t5_auto_S16_tinyllama_ft_freezeqk25_s0.logOther3.4 KB —
t8/logs_pod2/t5_auto_S16_tinyllama_ft_iter100_s0.logOther7.4 KB —
t8/logs_pod2/t5_auto_S16_tinyllama_ft_iter50_s0.logOther3.7 KB —
t8/logs_pod2/t5_auto_S16_tinyllama_ft_iter75_s0.logOther3.6 KB —
t8/logs_pod2/t5_auto_S16_tinyllama_ft_shuffle25_s0.logOther18.4 KB —
t8/logs_pod2/t5_auto_S16_tinyllama_ft_zero25_s0.logOther16.7 KB —
t8/logs_pod2/t5_auto_S16_tinyllama_random_fixed100_s0.logOther12.4 KB —
t8/logs_pod2/t5_auto_S16_tinyllama_random_freezeqk25_s0.logOther11.5 KB —
t8/logs_pod2/t5_auto_S16_tinyllama_random_zero25_s0.logOther22.6 KB —
t8/logs_pod3/run_t8_series.logOther4.5 KB —
t8/logs_pod3/t5_auto_S16_tinyllama_random_fixed100_s0.logOther12.4 KB —
t8/logs_pod3/t5_auto_S16_tinyllama_random_freezeqk25_s0.logOther23.3 KB —
t8/logs_pod3/t5_auto_S16_tinyllama_random_shuffle25_s0.logOther11.3 KB —
t8/logs_pod3/t5_auto_S16_tinyllama_random_zero25_s0.logOther22.6 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_rel2000_s0/log.jsonlOther156.9 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam0p1_s0/log.jsonlOther192.5 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_rel2000_s0/log.jsonlOther198.4 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s0/log.jsonlOther248.0 KB —
t9/checkpoints/auto_S16_tinyllama_random_reg25_lam1_s1/log.jsonlOther232.4 KB —
t9/logs/run_t9_series.logOther816 B —
t9/logs/t5_auto_S16_tinyllama_random_reg25_lam0p1_rel2000_s0.logOther15.2 KB —
t9/logs/t5_auto_S16_tinyllama_random_reg25_lam0p1_s0.logOther18.3 KB —
t9/logs/t5_auto_S16_tinyllama_random_reg25_lam1_rel2000_s0.logOther19.0 KB —
t9/logs/t5_auto_S16_tinyllama_random_reg25_lam1_s0.logOther23.2 KB —
t9/logs/t5_auto_S16_tinyllama_random_reg25_lam1_s1.logOther22.3 KB —
t9/logs/t5_auto_S16_tinyllama_random_reg25_lam1_s2.logOther —
.gitattributesRepository1.5 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
246.4 GB
Download from Laura Gomezjurado

Released by Laura Gomezjurado through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published246.4 GB

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