s PRO

semran1 's models 329

Sort:  Recently updated

semran1/1b_0.0001_cadamw_baseline_20B

1B • Updated Nov 2, 2025 • 1

semran1/cmoun0.01_64_imbalance_1B

0.5B • Updated Nov 2, 2025 • 2

semran1/imbalance_model_base

0.5B • Updated Nov 1, 2025 • 3

semran1/baseline_adamw_0.0001_15B

1B • Updated Nov 1, 2025 • 9

semran1/baseline_adamw_0.0001_10B

1B • Updated Nov 1, 2025 • 2

semran1/gentinst

2B • Updated Oct 31, 2025 • 2

semran1/pretrain_q

2B • Updated Oct 30, 2025 • 4

semran1/base_halfbs_interleaved

16B • Updated Oct 30, 2025 • 1

semran1/interleaved

Updated Oct 30, 2025

semran1/ckpt45k

2B • Updated Oct 30, 2025 • 4

semran1/test40k2

2B • Updated Oct 30, 2025 • 4

semran1/test35k2

2B • Updated Oct 30, 2025 • 4

semran1/testestest

2B • Updated Oct 29, 2025 • 5

semran1/testnew13

Text Generation • 1B • Updated Oct 29, 2025 • 9

semran1/for_prune

2B • Updated Oct 29, 2025 • 3

semran1/test25kt

2B • Updated Oct 29, 2025 • 3

semran1/test20kv3

2B • Updated Oct 29, 2025 • 2

semran1/test20k2

2B • Updated Oct 29, 2025 • 3

semran1/testdd25k

2B • Updated Oct 28, 2025 • 3

semran1/testdd15k

2B • Updated Oct 28, 2025 • 2

semran1/testdd20k

2B • Updated Oct 28, 2025 • 3

semran1/test1.5b5k

2B • Updated Oct 28, 2025 • 2

semran1/1bq210k

2B • Updated Oct 27, 2025 • 5

semran1/test5k_32

16B • Updated Oct 27, 2025 • 4

semran1/testdiffckpt

16B • Updated Oct 26, 2025 • 4

semran1/4btest

4B • Updated Oct 25, 2025 • 2

semran1/4b6ktest

4B • Updated Oct 25, 2025 • 4

semran1/4b5ktest

4B • Updated Oct 25, 2025 • 3

semran1/tests_5000

16B • Updated Oct 22, 2025 • 2

semran1/ffweb_own

Updated Oct 22, 2025