MoS-4B-Checkpoints is an open-weight model from Ryan Wang. Its published files total 104.1 GB.
Parameters—
Context—
Weights12.4 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- ryan-0608/MoS-4B-Checkpoints
- Publisher
- Ryan Wang
- 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
- 5e825ef9f519d28a5ebc1bfe7c9389fce1a6ba06
- First published
- 2026-10-10
- Last updated
- 2026-10-13
Files and Weights
223 files, 104.1 GB in total. The weights are 42 files totalling 12.4 GB in pt, safetensors.
Weights42 files · 12.4 GB
Configuration54 files · 68.0 KB
Other108 files · 91.7 GB
Repository19 files · 1.5 MB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/hf/model.safetensors | Weights | 1.1 GB | 3638c58dc34b |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/rng_rank_00000.pt | Weights | 14.7 KB | 6fd7d0dd4479 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/rng_rank_00001.pt | Weights | 14.7 KB | 7f82e3f66d39 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/rng_rank_00002.pt | Weights | 14.8 KB | 306a7fd13ddf |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/rng_rank_00003.pt | Weights | 14.8 KB | f849553561a9 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/rng_rank_00004.pt | Weights | 14.8 KB | 9442249d488b |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/rng_rank_00005.pt | Weights | 14.7 KB | 7755795b761c |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/hf/model.safetensors | Weights | 1.1 GB | cf182851aa08 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/rng_rank_00000.pt | Weights | 14.7 KB | 78701222adf0 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/rng_rank_00001.pt | Weights | 14.7 KB | 8071fb6c1c0f |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/rng_rank_00002.pt | Weights | 14.8 KB | aa9f41c8ea69 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/rng_rank_00003.pt | Weights | 14.8 KB | 0760f6d9d753 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/rng_rank_00004.pt | Weights | 14.8 KB | 7c3545b52ebb |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/rng_rank_00005.pt | Weights | 14.7 KB | febb249f3894 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/hf/model.safetensors | Weights | 1.1 GB | 4242eb5b7b18 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/rng_rank_00000.pt | Weights | 14.7 KB | 337d9518d85a |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/rng_rank_00001.pt | Weights | 14.7 KB | f7020a716214 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/rng_rank_00002.pt | Weights | 14.8 KB | e2eb247fff5b |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/rng_rank_00003.pt | Weights | 14.8 KB | 9bfcfd216f45 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/rng_rank_00004.pt | Weights | 14.8 KB | f720f7e47179 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/rng_rank_00005.pt | Weights | 14.7 KB | 03f32f4b6ec2 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/hf/model.safetensors | Weights | 1.1 GB | 57b0c4763fa3 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/rng_rank_00000.pt | Weights | 14.7 KB | 423e72a12623 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/rng_rank_00001.pt | Weights | 14.7 KB | 7c9c0de65b2a |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/rng_rank_00002.pt | Weights | 14.8 KB | 65d52730dac1 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/rng_rank_00003.pt | Weights | 14.8 KB | c027eeecec87 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/rng_rank_00004.pt | Weights | 14.8 KB | 7ee86c8dab8f |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/rng_rank_00005.pt | Weights | 14.7 KB | fa96ae65a9e8 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/hf/model.safetensors | Weights | 1.1 GB | 4db18d3a7865 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/rng_rank_00000.pt | Weights | 14.7 KB | f35b922d75a9 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/rng_rank_00001.pt | Weights | 14.7 KB | 8352be08dd55 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/rng_rank_00002.pt | Weights | 14.8 KB | 1043ca255dae |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/rng_rank_00003.pt | Weights | 14.8 KB | 08fd8ab709fd |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/rng_rank_00004.pt | Weights | 14.8 KB | c8d95655edc1 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/rng_rank_00005.pt | Weights | 14.7 KB | c331793d8cb5 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/hf/model.safetensors | Weights | 7.1 GB | 76a90e28e38f |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/rng_rank_00000.pt | Weights | 14.8 KB | 6b0106cb8cb6 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/rng_rank_00001.pt | Weights | 14.8 KB | 5590a1d95e9f |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/rng_rank_00002.pt | Weights | 14.7 KB | 7610f3b9db72 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/rng_rank_00003.pt | Weights | 14.7 KB | 6ad80ddf9fd8 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/rng_rank_00004.pt | Weights | 14.7 KB | caf093ec2400 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/rng_rank_00005.pt | Weights | 14.7 KB | 539f1cd5315c |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/hf/config.json | Configuration | 1.1 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/hf/export_manifest.json | Configuration | 544 B | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/meta.json | Configuration | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/state_fingerprint_rank_00000.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/state_fingerprint_rank_00001.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/state_fingerprint_rank_00002.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/state_fingerprint_rank_00003.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/state_fingerprint_rank_00004.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/state_fingerprint_rank_00005.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/hf/config.json | Configuration | 1.1 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/hf/export_manifest.json | Configuration | 544 B | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/meta.json | Configuration | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/state_fingerprint_rank_00000.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/state_fingerprint_rank_00001.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/state_fingerprint_rank_00002.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/state_fingerprint_rank_00003.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/state_fingerprint_rank_00004.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/state_fingerprint_rank_00005.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/hf/config.json | Configuration | 1.1 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/hf/export_manifest.json | Configuration | 544 B | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/meta.json | Configuration | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/state_fingerprint_rank_00000.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/state_fingerprint_rank_00001.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/state_fingerprint_rank_00002.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/state_fingerprint_rank_00003.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/state_fingerprint_rank_00004.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/state_fingerprint_rank_00005.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/hf/config.json | Configuration | 1.1 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/hf/export_manifest.json | Configuration | 544 B | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/meta.json | Configuration | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/state_fingerprint_rank_00000.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/state_fingerprint_rank_00001.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/state_fingerprint_rank_00002.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/state_fingerprint_rank_00003.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/state_fingerprint_rank_00004.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/state_fingerprint_rank_00005.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/hf/config.json | Configuration | 1.1 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/hf/export_manifest.json | Configuration | 544 B | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/meta.json | Configuration | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/state_fingerprint_rank_00000.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/state_fingerprint_rank_00001.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/state_fingerprint_rank_00002.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/state_fingerprint_rank_00003.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/state_fingerprint_rank_00004.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/state_fingerprint_rank_00005.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/hf/config.json | Configuration | 1.2 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/hf/export_manifest.json | Configuration | 557 B | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/meta.json | Configuration | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/state_fingerprint_rank_00000.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/state_fingerprint_rank_00001.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/state_fingerprint_rank_00002.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/state_fingerprint_rank_00003.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/state_fingerprint_rank_00004.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/state_fingerprint_rank_00005.json | Configuration | 1.0 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/lr_scheduler/__0_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/lr_scheduler/__1_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/lr_scheduler/__2_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/lr_scheduler/__3_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/lr_scheduler/__4_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/lr_scheduler/__5_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/model/__0_0.distcp | Other | 196.6 MB | d623762caef7 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/model/__1_0.distcp | Other | 225.5 MB | b0f43c8697aa |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/model/__2_0.distcp | Other | 777.9 MB | aaa0b5de5fc8 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/model/__3_0.distcp | Other | 191.4 MB | d8106638f879 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/model/__4_0.distcp | Other | 225.5 MB | adb90d092f07 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/model/__5_0.distcp | Other | 236.0 MB | 3818ec5c1f1a |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/optimizer/__0_0.distcp | Other | 1.0 GB | 5ec53dafa7b1 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/optimizer/__1_0.distcp | Other | 1.1 GB | 3551827396dc |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/optimizer/__2_0.distcp | Other | 1.1 GB | 786c4636cb38 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/optimizer/__3_0.distcp | Other | 1.1 GB | 8455b32285c1 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/optimizer/__4_0.distcp | Other | 1.0 GB | b9cfab09e3d5 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/optimizer/__5_0.distcp | Other | 1.0 GB | 7f768f2c49b0 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/lr_scheduler/__0_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/lr_scheduler/__1_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/lr_scheduler/__2_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/lr_scheduler/__3_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/lr_scheduler/__4_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/lr_scheduler/__5_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/model/__0_0.distcp | Other | 196.6 MB | 36544b12f38a |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/model/__1_0.distcp | Other | 225.5 MB | b6fb9881cbdd |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/model/__2_0.distcp | Other | 777.9 MB | aaa0b5de5fc8 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/model/__3_0.distcp | Other | 191.4 MB | 3f4ef163403f |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/model/__4_0.distcp | Other | 225.5 MB | 020c7eca258d |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/model/__5_0.distcp | Other | 236.0 MB | f842e845c560 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/optimizer/__0_0.distcp | Other | 1.0 GB | 4e6f6398cd68 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/optimizer/__1_0.distcp | Other | 1.1 GB | 4577d7c9e63a |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/optimizer/__2_0.distcp | Other | 1.1 GB | 6bd1431e54c7 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/optimizer/__3_0.distcp | Other | 1.1 GB | d23fd2c34771 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/optimizer/__4_0.distcp | Other | 1.0 GB | 213c7f7f57a5 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/optimizer/__5_0.distcp | Other | 1.0 GB | 58633881fd1f |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/lr_scheduler/__0_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/lr_scheduler/__1_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/lr_scheduler/__2_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/lr_scheduler/__3_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/lr_scheduler/__4_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/lr_scheduler/__5_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/model/__0_0.distcp | Other | 196.6 MB | 478c397b89d4 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/model/__1_0.distcp | Other | 225.5 MB | 81b4f1f94455 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/model/__2_0.distcp | Other | 777.9 MB | aaa0b5de5fc8 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/model/__3_0.distcp | Other | 191.4 MB | 1304cf79a822 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/model/__4_0.distcp | Other | 225.5 MB | 9c379063ca50 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/model/__5_0.distcp | Other | 236.0 MB | d3ab815ed47e |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/optimizer/__0_0.distcp | Other | 1.0 GB | f6d9ccafc256 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/optimizer/__1_0.distcp | Other | 1.1 GB | fbb524005202 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/optimizer/__2_0.distcp | Other | 1.1 GB | acba237ffd24 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/optimizer/__3_0.distcp | Other | 1.1 GB | 11f8db4bcf35 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/optimizer/__4_0.distcp | Other | 1.0 GB | 99c27078f253 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/optimizer/__5_0.distcp | Other | 1.0 GB | a36638e186ca |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/lr_scheduler/__0_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/lr_scheduler/__1_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/lr_scheduler/__2_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/lr_scheduler/__3_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/lr_scheduler/__4_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/lr_scheduler/__5_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/model/__0_0.distcp | Other | 196.6 MB | a019fdb19590 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/model/__1_0.distcp | Other | 225.5 MB | 1925928fe2dd |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/model/__2_0.distcp | Other | 777.9 MB | aaa0b5de5fc8 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/model/__3_0.distcp | Other | 191.4 MB | 6e808df63536 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/model/__4_0.distcp | Other | 225.5 MB | 95505f5115b4 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/model/__5_0.distcp | Other | 236.0 MB | 073d980e7984 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/optimizer/__0_0.distcp | Other | 1.0 GB | 7d86bb47eb8e |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/optimizer/__1_0.distcp | Other | 1.1 GB | 521cbc8e4cc4 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/optimizer/__2_0.distcp | Other | 1.1 GB | 66e7fef3932e |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/optimizer/__3_0.distcp | Other | 1.1 GB | 18442d07bf86 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/optimizer/__4_0.distcp | Other | 1.0 GB | 898aef37c27a |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/optimizer/__5_0.distcp | Other | 1.0 GB | 8aa4ecc5a88d |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/lr_scheduler/__0_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/lr_scheduler/__1_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/lr_scheduler/__2_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/lr_scheduler/__3_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/lr_scheduler/__4_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/lr_scheduler/__5_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/model/__0_0.distcp | Other | 196.6 MB | 4b567add71d7 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/model/__1_0.distcp | Other | 225.5 MB | fb3430b1e071 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/model/__2_0.distcp | Other | 777.9 MB | aaa0b5de5fc8 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/model/__3_0.distcp | Other | 191.4 MB | 19602315026e |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/model/__4_0.distcp | Other | 225.5 MB | 4ec09944a1cd |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/model/__5_0.distcp | Other | 236.0 MB | 7e36bd105087 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/optimizer/__0_0.distcp | Other | 1.0 GB | 5c8cf8e870b4 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/optimizer/__1_0.distcp | Other | 1.1 GB | 7c507fd5de41 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/optimizer/__2_0.distcp | Other | 1.1 GB | a1d845b60606 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/optimizer/__3_0.distcp | Other | 1.1 GB | a6292ed80fd6 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/optimizer/__4_0.distcp | Other | 1.0 GB | 6a16e3b75dc8 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/optimizer/__5_0.distcp | Other | 1.0 GB | eba554c42913 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/lr_scheduler/__0_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/lr_scheduler/__1_0.distcp | Other | 3.8 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/lr_scheduler/__2_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/lr_scheduler/__3_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/lr_scheduler/__4_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/lr_scheduler/__5_0.distcp | Other | 2.5 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/model/__0_0.distcp | Other | 1.3 GB | 389dfe570fc1 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/model/__1_0.distcp | Other | 1.3 GB | 31b02e448df9 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/model/__2_0.distcp | Other | 1.3 GB | b66c57e7708d |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/model/__3_0.distcp | Other | 1.3 GB | cec589fa0598 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/model/__4_0.distcp | Other | 1.3 GB | c011b5c20f57 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/model/__5_0.distcp | Other | 1.3 GB | 10e325142975 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/optimizer/__0_0.distcp | Other | 7.1 GB | 4895c8c113f7 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/optimizer/__1_0.distcp | Other | 7.1 GB | e5a549841678 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/optimizer/__2_0.distcp | Other | 7.1 GB | 871f63b1c6e7 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/optimizer/__3_0.distcp | Other | 7.1 GB | 10a1b859551c |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/optimizer/__4_0.distcp | Other | 7.1 GB | e074b2961d2a |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/optimizer/__5_0.distcp | Other | 7.0 GB | 63a72b944df6 |
| .gitattributes | Repository | 12.1 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/lr_scheduler/.metadata | Repository | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/model/.metadata | Repository | 24.9 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0013309/optimizer/.metadata | Repository | 70.9 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/lr_scheduler/.metadata | Repository | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/model/.metadata | Repository | 24.9 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0026618/optimizer/.metadata | Repository | 70.9 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/lr_scheduler/.metadata | Repository | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/model/.metadata | Repository | 24.9 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0039927/optimizer/.metadata | Repository | 70.9 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/lr_scheduler/.metadata | Repository | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/model/.metadata | Repository | 24.9 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0053236/optimizer/.metadata | Repository | 70.9 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/lr_scheduler/.metadata | Repository | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/model/.metadata | Repository | 24.9 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-dense-lr1e3/checkpoints/iter_0066545/optimizer/.metadata | Repository | 70.9 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/lr_scheduler/.metadata | Repository | 3.4 KB | — |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/model/.metadata | Repository | 266.6 KB | 209aad333df7 |
| a3_4b_scratch_lr1e3_20261009/arms/e5self-scratch-x8-lr1e3-mos/checkpoints/iter_0013309/optimizer/.metadata | Repository | 685.4 KB | ec8213d0a17e |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 12.4 GB
Download from Ryan Wang
Released by Ryan Wang through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 12.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.