Hippius
maincontainerPublic

tired-cascade/gen-d4871f4eba85-top8_v2

sha256:cf7835f2f62cb63054e545357a4be097b624059d279ba8fd5b287e366179a732·Indexed 26d ago

Layers

6

Total size

65.7 KB

Files

6

Quantization

README.md

1.5 KB

gen-d4871f4eba85-top8_v2

Top-eight fork of gen-d4871f4eba85. It applies the pruning idea from forever-real_tired3-5-top8, but selects families from this parent's own configured weights.

Active top-level families:

  • k14: parent weight 0.310099
  • k15: parent weight 0.210951
  • k03: parent weight 0.185441
  • k00: parent weight 0.042055
  • k21: parent weight 0.040000
  • k22: parent weight 0.040000
  • k10: parent weight 0.033967
  • k01: parent weight 0.032350

Their parent weights sum to 0.894863 and are renormalized to one without changing their relative proportions.

The variable-length update from forever-real_tired3-3-variable-lengh is applied as a cyclic 2048/3072/4096 schedule. Full 4096 context remains the default; two smooth pulses expose 0.5% 2048 and 1% 3072 rows at their peaks. min_length = 64 calibrates schedule progress to the trainer request contract, while emitted rows stay in the three configured buckets. The parent's family curriculum remains disabled.

Unselected kernel functions remain only where useful as implementation helpers (for example, k10 and k14 use k07 internally); they are absent from _FAMILIES, dispatch, and configured weights, so they cannot be selected as top-level training families.

The throughput-only update from generators/07-27/proven_speed_up.md is also applied. Numba compiles the AR(1), AR(2), and threshold-AR recurrences with fastmath=False; deterministic warm-up runs before corpus RNG creation. The optimized kernels are bitwise-equivalent to the original SciPy/NumPy paths and do not change the generated corpus.

Files

6 items
  • generator.py

    4692124be439

    53.6 KB

  • tests/test_top8.py

    259bbcbbf213

    4.1 KB

  • tests/test_exact_recurrence_kernels.py

    d056698d62f6

    3.8 KB

  • config.json

    754c634d5aba

    2.4 KB

  • README.md

    ea177b9f7d3a

    1.5 KB

  • requirements.txt

    101d40006778

    279 B