Distily Project

distily 's models 52

Sort:  Recently updated

distily/distily_smollm_dataset_sweep

0.1B • Updated Sep 30, 2024 • 23

distily/distily_tinyBenchmarks

0.1B • Updated Sep 23, 2024 • 3

distily/distily_learning_params

0.1B • Updated Sep 22, 2024 • 9

distily/distily_seq_len_batch_size

0.1B • Updated Sep 17, 2024 • 8

distily/distily_distsmollm_max_length

0.1B • Updated Sep 14, 2024 • 4

distily/distily_distsmollm_long

0.1B • Updated Sep 14, 2024 • 3

distily/distily_additional_profiling

Updated Sep 13, 2024

distily/distily_profile_smollm_tritoned

0.1B • Updated Sep 12, 2024 • 4

distily/distily_profile_smollm

0.1B • Updated Sep 12, 2024 • 3

distily/distily_verify_new_attns

0.1B • Updated Sep 12, 2024 • 3

distily/distily_verify_new_attns2

0.1B • Updated Sep 12, 2024 • 3

distily/distily_performance_tests

0.1B • Updated Sep 12, 2024 • 3

distily/distily_long_dataset_sweep

0.1B • Updated Sep 11, 2024 • 7

distily/distily_dataset_sweep

0.1B • Updated Sep 9, 2024 • 3

distily/distily_smollm_liger_test

Updated Sep 9, 2024

distily/distily_attn_mlp_sweep

0.1B • Updated Sep 7, 2024 • 5

distily/distily_verify_update9

0.1B • Updated Sep 4, 2024 • 3

distily/distily_verify_update8

0.1B • Updated Sep 4, 2024 • 3

distily/distily_verify_update7

0.1B • Updated Sep 4, 2024 • 3

distily/distily_norm_affine_distilgpt2_sweep2

0.1B • Updated Sep 4, 2024 • 3

distily/distily_norm_affine_distilgpt2_sweep

0.1B • Updated Sep 4, 2024 • 3

distily/distily_grad_log_perf

0.1B • Updated Sep 3, 2024 • 3

distily/distily_norm_distilgpt2_sweep_extended

0.1B • Updated Sep 3, 2024 • 4

distily/distily_validate_extra_grad_stats5

0.1B • Updated Sep 2, 2024 • 3

distily/distily_validate_extra_grad_stats4

0.1B • Updated Sep 2, 2024 • 3

distily/distily_validate_extra_grad_stats3

0.1B • Updated Sep 2, 2024 • 3

distily/distily_validate_extra_grad_stats2

0.1B • Updated Sep 2, 2024 • 3

distily/distily_validate_extra_grad_stats

0.1B • Updated Sep 2, 2024 • 4

distily/distily_dummy

0.1B • Updated Sep 2, 2024 • 2

distily/distily_norm_distilgpt2_sweep

0.1B • Updated Sep 1, 2024 • 3