Models

locuslab/base-smollm2-1.7b-score0_mix_rephrased_from_beginning_metadata-600B

Updated Feb 25 • 3

locuslab/mix_ift_v4-smollm2-1.7b-meta-llama-Llama-3.2-1B-lr2e-05-gbs16600B

1B • Updated Feb 25 • 3

locuslab/mix_ift_v4-smollm2-1.7b-score0_mix_rephrased_from_beginning-600B

2B • Updated Feb 26 • 8

locuslab/mix_ift_v4-smollm2-1.7b-score0_mix_rephrased_from_beginning_metadata-600B

2B • Updated Feb 26 • 6

locuslab/mix_ift_v4-smollm2-1.7b-all_raw_folders_baseline-600B

2B • Updated Feb 26 • 8

locuslab/mix_ift_v4-smollm2-1.7b-all_raw_folders_metadata-600B

2B • Updated Feb 26 • 4

locuslab/ift_then_gsm-smollm2-1.7b-all_raw_folders_baseline-600B

2B • Updated Feb 26 • 5

locuslab/ift_then_gsm-smollm2-1.7b-all_raw_folders_metadata-600B

2B • Updated Feb 26 • 3

locuslab/ift_then_gsm-smollm2-1.7b-meta-llama-Llama-3.2-1B-lr2e-05-gbs16600B

1B • Updated Feb 26 • 3

locuslab/ift_then_gsm-smollm2-1.7b-score0_mix_rephrased_from_beginning-600B

2B • Updated Feb 26 • 2

locuslab/ift_then_gsm-smollm2-1.7b-score0_mix_rephrased_from_beginning_metadata-600B

2B • Updated Feb 26 • 6

locuslab/base-smollm2-1.7bscore0_only-600B-mbs8-gbs1024-16feb_step-00240000

Updated Feb 26 • 3

ridger/Transformer-32768-baseline

1B • Updated Feb 27 • 4

locuslab/base-smollm2-1.7bscore0_baseline60p_then_mix_rephrase_with_refusal-600B

Updated Mar 2 • 9

locuslab/base-smollm2-1.7bscore0_only-600B

Updated Mar 2 • 25

locuslab/mix_ift_v4-smollm2-1.7b-score0_baseline60p_then_mix_rephrase_with_refusal-600B

2B • Updated Mar 2 • 3

locuslab/ift_then_gsm-smollm2-1.7b-score0_baseline60p_then_mix_rephrase_with_refusal-600B

2B • Updated Mar 2 • 3

locuslab/base-smollm2-1.7b-score0_baseline60p_then_mix_rephrase-600B

Updated Mar 3 • 3

locuslab/mix_ift_v4-smollm2-1.7b-score0_baseline60p_then_mix_rephrase-600B

2B • Updated Mar 3 • 4

locuslab/ift_then_gsm-smollm2-1.7b-score0_baseline60p_then_mix_rephrase-600B

2B • Updated Mar 3 • 7

locuslab/mix_ift_v4-smollm2-1.7b-score0_only-600B

2B • Updated Mar 3 • 5

locuslab/ift_then_gsm-smollm2-1.7b-score0_only-600B

2B • Updated Mar 3 • 3

locuslab/base-smollm2-1.7b-score0_baseline60p_then_mix_rephrase_with_refusal_and_metadata_5p-600B

Updated Mar 3 • 3

locuslab/base-smollm2-1.7b-score0_baseline60p_then_mix_rephrase_with_metadata-600B

Updated Mar 3 • 3

locuslab/base-smollm2-1.7b-score0_with_123rephrase_with_45refusal-600B-mbs8-gbs1024-03mar_step-00030000

Updated Mar 4 • 3

locuslab/base-smollm2-1.7b-score0_mix_rephrased_from_beginning-600B-mbs8-gbs1024-17feb_step-00030000

Updated Mar 4 • 3

locuslab/base-smollm2-1.7b-score0_only-600B-mbs8-gbs1024-16feb_step-00060000

Updated Mar 4 • 3

locuslab/base-smollm2-1.7b-all_raw_folders_baseline-600B-mbs8-gbs1024-16feb_step-00060000

Updated Mar 4 • 3

duonlabs/apogee-nano-2.4M-base

Updated Mar 19

locuslab/base-smollm2-1.7b-score0_with_123rephrase_with_45refusal-600B-mbs8-gbs1024-03mar_step-00060000

Updated Mar 4 • 4