ExeaLM / checkpoints

2.52 GB

Ctrl+K

1 contributor

Overnight runs of 2026-11-12: the 18M model with gated attention and QK-norm (1.393 against 1.419), with the circuit search (1.431), the 0.1B model at step 3,000, the 8,000-step wide fine-tune, and their result files

ce2a9da verified about 9 hours ago

100m
Overnight runs of 2026-11-12: the 18M model with gated attention and QK-norm (1.393 against 1.419), with the circuit search (1.431), the 0.1B model at step 3,000, the 8,000-step wide fine-tune, and their result files about 9 hours ago
17m
Overnight runs of 2026-11-12: the 18M model with gated attention and QK-norm (1.393 against 1.419), with the circuit search (1.431), the 0.1B model at step 3,000, the 8,000-step wide fine-tune, and their result files about 9 hours ago