Hugging Face's logo

PowerMachine
/
BiGRU_T_version

Model card Files
xet
 Community
BiGRU_T_version / src

Commit History

  1. Delete src/bigru_t/training/elastic_weight_consolidation.py

    PowerMachine
    Verified signature
    a4ebe65

  2. Delete src/bigru_t/model/kohonen_refactored

    PowerMachine
    Verified signature
    57be76f

  3. Delete src/bigru_t/model/kohonen_refactored/kohonen_learning_system.py

    PowerMachine
    Verified signature
    6ab683e

  4. Delete src/bigru_t/model/unified_model.py

    PowerMachine
    Verified signature
    7e0516f

  5. Delete src/bigru_t/model/u8cell_t.py

    PowerMachine
    Verified signature
    a35c145

  6. Delete src/bigru_t/model/transformer_unit.py

    PowerMachine
    Verified signature
    69a2f5a

  7. Delete src/bigru_t/model/orq_cell.py

    PowerMachine
    Verified signature
    4e7f6ee

  8. Delete src/bigru_t/model/kohonen_learning_system.py.bak_v65fix

    PowerMachine
    Verified signature
    f4432a5

  9. Delete src/bigru_t/model/gru_hierarchy.py

    PowerMachine
    Verified signature
    459b339

  10. Delete src/bigru_t/model/bigru4.py

    PowerMachine
    Verified signature
    61edc96

  11. 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 Removed legacy v2 reports/scripts (superseded by v3).

    PowerMachine
    Verified signature
    507c431

  12. 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

    PowerMachine
    Verified signature
    1fc607e

  13. V6.5-7ds cleanup: remove legacy src/bigru_t/data/data_augmentation.py

    PowerMachine
    Verified signature
    b714048

  14. 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

    PowerMachine
    Verified signature
    00432a9

  15. 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

    PowerMachine
    Verified signature
    f3fea40

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

    PowerMachine
    Verified signature
    c2992d0

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

    PowerMachine
    Verified signature
    f90a477

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

    PowerMachine
    Verified signature
    f64aac8

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

    PowerMachine
    Verified signature
    0d4bcbe

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

    PowerMachine
    Verified signature
    34fad27

  1. V6: Kohonen 4D SOM + EWC per-neuron + MTP+entropy + Xeon V6⁠

    PowerMachine
    Verified signature
    79e8e52

  2. V5: W8A8 aprimorado (α aprendível via STE) + bug fix apply_w8a8_to_model + 4 hiperparâmetros auto-ajustáveis (T, τ, λ_ent, init_gate) + OOM-Killer fixes + num_layers_hyp=8 fixo

    PowerMachine
    Verified signature
    70ae8f3

  3. V6: KohonenSOM4D 4D em orq_cell (8 BiGRU × 4 sem × 4x4 grid = 512 protótipos) + WindowContext 2M (ToMe + KNN IVF) + MTP (K=4) + MTPAdaptiveAttention + DynamicRepetitionPenalty + ElasticWeightConsolidation + data_augmentation + RLHF Possibility Mapping (Φ = Θ + η·r·σ(trust·τ_T)·Σwᵢgᵢ) + ReasoningEngine 8-fase + Tools (cache + mutation + agent) + optimized_pipeline + langchain_adapter

    PowerMachine
    Verified signature
    e383cb5

  4. V5: W8A8 aprimorado (α aprendível via STE) + bug fix apply_w8a8_to_model + 4 hiperparâmetros auto-ajustáveis (T, τ, λ_ent, init_gate) + OOM-Killer fixes + num_layers_hyp=8 fixo

    PowerMachine
    Verified signature
    cbf308e

  5. V3.2: corrigir 6 bugs + meta_T_moved (T_tracking_loss) + re-teste com Xeon IPEX 2.8 + AMX

    PowerMachine
    Verified signature
    0cee009

  6. V3.2: corrigir 6 bugs + meta_T_moved (T_tracking_loss) + re-teste com Xeon IPEX 2.8 + AMX

    PowerMachine
    Verified signature
    a22ed76

  7. V2: 12.97M params, HW optimizer, parallel BBPE, DPO, reasoning, inference, 10 bugs fixed

    PowerMachine
    Verified signature
    8594de8

  1. Upload folder using huggingface_hub

    PowerMachine
    Verified signature
    3275441