BiGRU_T_version / scripts

Commit History

  1. V6.5-attn-v2 cleanup: remove legacy scripts/upload_v6_5_7ds_attn_v2.py

    Verified signature
    7254864
  2. V6.5-attn-v2 cleanup: remove legacy scripts/train_v6_5_7ds_attn_v2.py

    Verified signature
    3581b73
  3. V6.5-attn-v2 cleanup: remove legacy scripts/upload_v6_5_7ds_attn.py

    Verified signature
    64465e3
  4. V6.5-attn-v2 cleanup: remove legacy scripts/train_v6_5_7ds_attn.py

    Verified signature
    3a3f374
  5. V6.5-attn-v2 cleanup: remove legacy scripts/upload_v6_5_7ds.py

    Verified signature
    c89c7aa
  6. V6.5-attn-v2 cleanup: remove legacy scripts/train_v6_5_7ds.py

    Verified signature
    cd872c7
  7. V6.5-attn-v3: CORREÇÃO MATEMÁTICA do predict() — rótulos dinâmicos extraídos do label_registry (substitui 'gato'/'cachorro' fixos). NOVO: punish_during_inference() — mirror do protocolo de punição do treinamento (1ª → activate_hypothesis, 2ª → set_ewc_reference). META ≥6000 samples, attention ACTIVE_AND_FUNCTIONAL, SmoothQuant W8A8, 864 neurons, MTP K=6, 3 perguntas reais sem ajuda (Luva de Pedreiro Távila, Lula reserva valor, Amazonas força-tarefa vítimas) + punição na inferência via camada de hipótese. Removed legacy v2 reports/scripts (superseded by v3).

    Verified signature
    507c431
  8. V6.5-attn-v2 cleanup: remove legacy scripts/upload_v6_5_7ds_attn.py

    Verified signature
    554f9bb
  9. V6.5-attn-v2 cleanup: remove legacy scripts/train_v6_5_7ds_attn.py

    Verified signature
    d390677
  10. V6.5-attn-v2 cleanup: remove legacy scripts/upload_v6_5_7ds.py

    Verified signature
    4a3528b
  11. V6.5-attn-v2 cleanup: remove legacy scripts/train_v6_5_7ds.py

    Verified signature
    f2faf9a
  12. V6.5-attn-v2: META ≥6000 samples (6020 REAL), salvar estados do modelo, 3 perguntas reais sem ajuda (Luva de Pedreiro Távila, Lula reserva valor, Amazonas força-tarefa vítimas), attention ACTIVE_AND_FUNCTIONAL (6161 calls/0 err), SmoothQuant W8A8 (final err=0.0056), 864 neurons, MTP K=6, tool_coordinator workers reactivated, 11/11 verification PASS, reasoning GOOD (100% answer/think/plan/decompose), removed legacy v3/v4/v5/v6_1/v6_2/v6_3/v6_progressive + old v6_5_*/v6_5_final_*/v6_5_7ds_* + v6_5_7ds_attn_* v1 reports/scripts (superseded by v2)

    Verified signature
    ccf55a8
  13. V6.5-attn cleanup: remove legacy scripts/upload_v6_5_7ds.py

    Verified signature
    42c43ca
  14. V6.5-attn cleanup: remove legacy scripts/train_v6_5_7ds.py

    Verified signature
    afa2f3d
  15. V6.5-attn: attention integrated to KLS (MultiHeadAttention n_heads=8), 100 samples/batch streaming, 5040 samples REAL (meta ≥5000), 864 neurons, SmoothQuant W8A8 (err=0.020), MTP K=6, tool_coordinator workers reactivated, 11/11 verification PASS, attention ACTIVE_AND_FUNCTIONAL, reasoning GOOD (100% answer/think), removed legacy v3/v4/v5/v6_1/v6_2/v6_3/v6_progressive + old v6_5_* + v6_5_7ds_* reports/scripts

    Verified signature
    1fc607e
  16. V6.5-7ds cleanup: remove legacy scripts/xeon_runtime.py

    Verified signature
    b4c4338
  17. V6.5-7ds cleanup: remove legacy scripts/upload_v6_5_resilient.py

    Verified signature
    2a94ab3
  18. V6.5-7ds cleanup: remove legacy scripts/upload_v6_4_resilient.py

    Verified signature
    c9328c7
  19. V6.5-7ds cleanup: remove legacy scripts/upload_v6_3_resilient.py

    Verified signature
    188d7d7
  20. V6.5-7ds cleanup: remove legacy scripts/upload_v6_2_resilient.py

    Verified signature
    5aa1714
  21. V6.5-7ds cleanup: remove legacy scripts/upload_v6_1_resilient.py

    Verified signature
    831f5ad
  22. V6.5-7ds cleanup: remove legacy scripts/upload_to_hf.py

    Verified signature
    d093cf2
  23. V6.5-7ds cleanup: remove legacy scripts/train_v6_5_final.py

    Verified signature
    5b9aab4
  24. V6.5-7ds cleanup: remove legacy scripts/train_v6_5.py

    Verified signature
    a062271
  25. V6.5-7ds cleanup: remove legacy scripts/train_v6_progressive.py

    Verified signature
    ebd0ba4
  26. V6.5-7ds cleanup: remove legacy scripts/train_v6_3.py

    Verified signature
    c08ff0e
  27. V6.5-7ds cleanup: remove legacy scripts/train_v6_2.py

    Verified signature
    44c8b02
  28. V6.5-7ds cleanup: remove legacy scripts/train_v6_1.py

    Verified signature
    b893208
  29. V6.5-7ds cleanup: remove legacy scripts/train_v2.py

    Verified signature
    17685dc
  30. V6.5-7ds cleanup: remove legacy scripts/train_fast.py

    Verified signature
    01a6b31
  31. V6.5-7ds cleanup: remove legacy scripts/train.py

    Verified signature
    b29c6dc
  32. V6.5-7ds cleanup: remove legacy scripts/smoke_test.py

    Verified signature
    b4d00c8
  33. V6.5-7ds cleanup: remove legacy scripts/parse_v6_log.py

    Verified signature
    be8019c
  34. V6.5-7ds: 7 datasets streaming (1400 samples, 112 steps), 864 neurons, SmoothQuant W8A8 (err=0.022), MTP K=6, tool_coordinator workers reactivated, 10/10 verification PASS, reasoning GOOD, removed legacy v3/v4/v5/v6_1/v6_2/v6_3/v6_progressive files + old v6_5_* reports/scripts

    Verified signature
    00432a9
  35. V6.5-final: removed pre-V6.4 modules/scripts, moved kohonen_learning_system up, activated VQ-VAE-2 in pipeline, integrated reasoning_engine, benchmarked EWC+W8A8 dequant, exhausted 6 datasets

    Verified signature
    f3fea40

  1. V6.5: 1000 samples (500+500), MTP val+entropy, EWC+W8A8 eval investigation, integrate gru-ring modules

    Verified signature
    c2992d0
  2. V6.4: refactored Kohonen SOM 4D (canonical user code, pgvector_lookup REMOVED)

    Verified signature
    f90a477
  3. V6.3: refactored Kohonen Learning System (user code) + xeon_runtime + streaming + bug fix find_bmu

    Verified signature
    f64aac8
  4. V6.2: HypT pgvector_lookup before punishment + BATCH_SIZE=16 + 5 datasets x 50⁠

    Verified signature
    0d4bcbe
  5. V6.1: PGVector-like lookup + EWC math upgrade + 5 datasets x 10 samples⁠

    Verified signature
    34fad27

  1. V6+: add scripts/parse_v6_log.py

    Verified signature
    27ffe62
  2. V6+: add scripts/train_v6_progressive.py

    Verified signature
    43b7b92
  3. V6+: add xeon_runtime.py with IPEX/AMX/AVX512 + FP16/BF16 benchmark

    Verified signature
    e719654
  4. V2: 12.97M params, HW optimizer, parallel BBPE, DPO, reasoning, inference, 10 bugs fixed

    Verified signature
    8594de8

  1. Delete scripts/smoke_test.py

    Verified signature
    b4a2ba0
  2. Upload folder using huggingface_hub

    Verified signature
    d855e28