PowerMachine
/

BiGRU_T_version

Model card Files Files and versions

BiGRU_T_version / scripts

778 kB

Ctrl+K

Ctrl+K

1 contributor

History: 78 commits

PowerMachine's picture

V6.7: upload scripts/test_bbpe_refit_serial.py (10.3KB) — FASE1+FASE2 training results

4d57997 verified about 2 months ago

deprecated
V6.7: deprecated → scripts/deprecated/upload_v6_5_7ds_attn_v3.py about 2 months ago
tests
V6.5-V4-canonical-256: buffer=256 + grid=(4,4,4,4)=256 + BBPE serial fix about 2 months ago
fix_bbpe_refit_oom.py

20.1 kB
V6.7: upload scripts/fix_bbpe_refit_oom.py (19.6KB) — FASE1+FASE2 training results about 2 months ago
run_v67_fase2_only.py

8.44 kB
V6.7: upload scripts/run_v67_fase2_only.py (8.2KB) — FASE1+FASE2 training results about 2 months ago
run_v67_train_quick.py

16.1 kB
V6.7: upload scripts/run_v67_train_quick.py (15.7KB) — FASE1+FASE2 training results about 2 months ago
som_auto_adjust_runner.py

18.8 kB
V6.7: upload scripts/som_auto_adjust_runner.py (som_auto_adjust_runner + train script V6.7) about 2 months ago
test_bbpe_refit_serial.py

10.6 kB
V6.7: upload scripts/test_bbpe_refit_serial.py (10.3KB) — FASE1+FASE2 training results about 2 months ago
train_v6_5_v2.py

183 kB
V6.7: upload scripts/train_v6_5_v2.py (som_auto_adjust_runner + train script V6.7) about 2 months ago
upload_v67_to_hf.py

13.5 kB
V6.7: scrub literal HF_TOKEN from upload script (security) about 2 months ago