OpenModelStats

gpjt AI Models

Tracked by OpenModelStats since Sep 3, 2026 · View on Hugging Face ↗

Tracked models
25
Downloads 30D
6,467
Total downloads
6,467
Total likes
1
Gained 7D
1,242

Most downloaded

  1. 1jax-with-mha-bias-fw-fwedu-simplewiki-DEPRECATEDSep 28, 2026797
  2. 2jax-with-mha-bias-fw-fwedu-simplewikiSep 28, 2026793
  3. 31xrtx3090-moe-1Sep 14, 2026484
  4. 4jax-with-mha-bias-fw-fwedu-5050Sep 28, 2026420
  5. 5jax-with-mha-bias-fw-fwedu-5050-DEPRECATEDSep 28, 2026417
  6. 6jax-no-mha-bias-no-dropoutSep 3, 2026274
  7. 7jax-with-mha-bias-fineweb-eduSep 14, 2026257
  8. 8jax-with-mha-bias-no-dropoutSep 3, 2026239
  9. 9jax-with-mha-bias-larger-chinchilla-1Sep 3, 2026237
  10. 10jax-with-mha-bias-larger-chinchilla-2Sep 3, 2026225

Fastest growing

  1. 1jax-with-mha-bias-fw-fwedu-simplewiki+525 in 7D793
  2. 21xrtx3090-moe-1+277 in 7D484
  3. 3jax-with-mha-bias-fw-fwedu-5050+183 in 7D420

Recently updated

  1. 18xa100m40-lore-9-new-seed-output-onlyOct 3, 2026155
  2. 28xa100m40-lore-8-new-seed-both-smart-initOct 3, 2026151
  3. 38xa100m40-lore-7-new-seed-input-onlyOct 3, 2026145
  4. 48xa100m40-lore-6-new-seed-baseline-disabledOct 3, 2026141
  5. 58xa100m40-lore-5-output-onlyOct 3, 2026140
  6. 68xa100m40-lore-4-input-onlyOct 3, 2026141
  7. 78xa100m40-lore-3-both-smart-initOct 3, 2026145
  8. 88xa100m40-lore-2-both-ordinary-initOct 3, 2026139
  9. 98xa100m40-lore-11-output-only-corrected-smart-initOct 3, 2026128
  10. 108xa100m40-lore-10-both-corrected-smart-initOct 3, 2026121

All models

All tracked models published by gpjt
ModelDL 30D7D
jax-with-mha-bias-fw-fwedu-simplewiki-DEPRECATEDgpjt/jax-with-mha-bias-fw-fwedu-simplewiki-deprecated797—
jax-with-mha-bias-fw-fwedu-simplewikigpjt/jax-with-mha-bias-fw-fwedu-simplewiki793+525
1xrtx3090-moe-1gpjt/1xrtx3090-moe-1484+277
jax-with-mha-bias-fw-fwedu-5050gpjt/jax-with-mha-bias-fw-fwedu-5050420+183
jax-with-mha-bias-fw-fwedu-5050-DEPRECATEDgpjt/jax-with-mha-bias-fw-fwedu-5050-deprecated417—
jax-no-mha-bias-no-dropoutgpjt/jax-no-mha-bias-no-dropout274+0
jax-with-mha-bias-fineweb-edugpjt/jax-with-mha-bias-fineweb-edu257+257
jax-with-mha-bias-no-dropoutgpjt/jax-with-mha-bias-no-dropout239+0
jax-with-mha-bias-larger-chinchilla-1gpjt/jax-with-mha-bias-larger-chinchilla-1237+0
jax-with-mha-bias-larger-chinchilla-2gpjt/jax-with-mha-bias-larger-chinchilla-2225+0
jax-no-mha-bias-with-dropoutgpjt/jax-no-mha-bias-with-dropout211+0
jax-with-mha-bias-no-dropout-extendedgpjt/jax-with-mha-bias-no-dropout-extended209+0
jax-with-mha-bias-openwebtextgpjt/jax-with-mha-bias-openwebtext189—
jax-with-mha-bias-no-dropout-2-epochgpjt/jax-with-mha-bias-no-dropout-2-epoch189+0
8xa100m40-lore-9-new-seed-output-onlygpjt/8xa100m40-lore-9-new-seed-output-only155—
8xa100m40-lore-8-new-seed-both-smart-initgpjt/8xa100m40-lore-8-new-seed-both-smart-init151—
8xa100m40-lore-7-new-seed-input-onlygpjt/8xa100m40-lore-7-new-seed-input-only145—
8xa100m40-lore-3-both-smart-initgpjt/8xa100m40-lore-3-both-smart-init145—
8xa100m40-lore-6-new-seed-baseline-disabledgpjt/8xa100m40-lore-6-new-seed-baseline-disabled141—
8xa100m40-lore-4-input-onlygpjt/8xa100m40-lore-4-input-only141—
8xa100m40-lore-5-output-onlygpjt/8xa100m40-lore-5-output-only140—
8xa100m40-lore-2-both-ordinary-initgpjt/8xa100m40-lore-2-both-ordinary-init139—
8xa100m40-lore-11-output-only-corrected-smart-initgpjt/8xa100m40-lore-11-output-only-corrected-smart-init128—
8xa100m40-lore-10-both-corrected-smart-initgpjt/8xa100m40-lore-10-both-corrected-smart-init121—
8xa100m40-lore-1-baseline-disabledgpjt/8xa100m40-lore-1-baseline-disabled120—