20 days ago
-
Publish final model documentation with measured results and limitations
-
Publish final model documentation with measured results and limitations
-
Keep model artifacts on Hub; link code and evaluation evidence on GitHub
-
Document recovered experiment sources, saved configurations and dataset limitations
22 days ago
-
Rebuild model card from reproducible CPU audit; include evidence and limitations
-
Rebuild model card from reproducible CPU audit; include evidence and limitations
-
Rebuild model card from reproducible CPU audit; include evidence and limitations
-
Rebuild model card from reproducible CPU audit; include evidence and limitations
-
Update README: computed val_loss for missing runs 2026-06-13
-
Update README: recalculated metrics 2026-06-12
-
Update README: recalculated metrics 2026-06-12
-
Update README: recalculated metrics 2026-06-12
-
Update README: recalculated metrics 2026-06-12
-
Update README: recalculated metrics 2026-06-12
-
Update README: add V3 Val Loss/PPL results table, bf16+lr_scale finding
-
Upload README.md with huggingface_hub
-
Upload README.md with huggingface_hub
-
Add run_15_v3 (float32, unpacked) from run_15/checkpoint_run_15_step2350.pt
-
Add run_14_v3 (float32, unpacked) from run_14/checkpoint_run_14_step9775.pt
-
Add run_13_v3 (float32, unpacked) from run_13/checkpoint_run_13_step9290.pt
-
Add run_08_v3 (float32, unpacked) from run_08/checkpoint_run_08_step3858.pt
-
Add run_06_v3 (float32, unpacked) from run_06/checkpoint_run_06_step4237.pt
-
Add run_05b_kernel_strict_v3 (float32, unpacked) from run_05b_kernel_strict/checkpoint_run_05b_kernel_strict_step2573.pt
-
Add run_05_v3 (float32, unpacked) from run_05/checkpoint_run_05_step4390.pt
-
Add run_04_v3 (float32, unpacked) from run_04/checkpoint_run_04_step6074.pt
-
Add run_03_v3 (float32, unpacked) from run_03/checkpoint_run_03_step6187.pt
-
Add run_02a_byte_only_heads_v3 (float32, unpacked) from run_02a_byte_only_heads/checkpoint_run_02a_byte_only_heads_step16327.pt
-
Add run_02_v3 (float32, unpacked) from run_02/checkpoint_run_02_step10963.pt
-
Add run_01_v3 (float32, unpacked) from run_01/checkpoint_run_01_step12173.pt
-
Restore original ablations grid from local disk
-
Add run_15 (float32, unpacked) from run_15/checkpoint_run_15_step2350.pt
-
Add run_14 (float32, unpacked) from run_14/checkpoint_run_14_step9775.pt
-
Add run_13 (float32, unpacked) from run_13/checkpoint_run_13_step9290.pt
-
Add run_08 (float32, unpacked) from run_08/checkpoint_run_08_step3858.pt
-
Add run_06 (float32, unpacked) from run_06/checkpoint_run_06_step4237.pt
-
Add run_05b_kernel_strict (float32, unpacked) from run_05b_kernel_strict/checkpoint_run_05b_kernel_strict_step2573.pt
-
Add run_05 (float32, unpacked) from run_05/checkpoint_run_05_step4390.pt
-
Add run_04 (float32, unpacked) from run_04/checkpoint_run_04_step6074.pt
-
Add run_03 (float32, unpacked) from run_03/checkpoint_run_03_step6187.pt
-
Add run_02a_byte_only_heads (float32, unpacked) from run_02a_byte_only_heads/checkpoint_run_02a_byte_only_heads_step16327.pt
-
Add run_02 (float32, unpacked) from run_02/checkpoint_run_02_step10963.pt
-
Add run_01 (float32, unpacked) from run_01/checkpoint_run_01_step12173.pt
-
Add run_01 (float32, unpacked) from run_01/checkpoint_run_01_step10434.pt
-
Add run_01 (float32, unpacked) from run_01/checkpoint_run_01_step10260.pt
-
Add run_01 (float32, unpacked) from run_01/checkpoint_run_01_step10146.pt
-
Add run_01 (float32, unpacked) from run_01/checkpoint_run_01_step10.pt
-
Add run_07_r2 (float32, unpacked)
-
Add run_04_r2 (float32, unpacked)
-
Add README
-
Upload README.md with huggingface_hub