V6.7: upload src/bigru_t/utils/oom_guard.py (21.1KB) — FASE1+FASE2 training results

V6.7: upload src/bigru_t/data/streaming_datasets.py (37.9KB) — FASE1+FASE2 training results

V6.7: upload src/bigru_t/model/kohonen_learning_system.py (BBPE serial mode + OomGuard V7)

V6.7: upload src/bigru_t/tokenizer/bbpe_tokenizer.py (BBPE serial mode + OomGuard V7)

V6.5-V2-dynamic: upload batch (scripts + state + model) [80 files]

V7 FINAL: FASE1+FASE2 completed (10000 samples, 20 punishments)

V7: dpo.py + data_augmentation.py + oom_guard.py aprimorados

V6.5-V4-canonical-256: buffer=256 + grid=(4,4,4,4)=256 + BBPE serial fix

V6.5-V3-hyp-synergy: SynergyHypothesisEnsemble (4 pilares: diversidade k-means++, cooperação, competição, ortogonalidade) + testes de validação (7 files)

V6.5-V2-dynamic: upload batch (scripts + state + model) [79 files]

V6.5-V2-dynamic: upload batch (scripts + state + model) [79 files]

V6.5-V2-parallel-reorganize: ParallelSOM4D + ReorganizingSOM4D + OOM-killer guards + unified state (75 files)

V6.5-V2-dynamic: upload batch (scripts + state + model) [79 files]

V6.5-V2-auto-conscience: upload batch (modules + scripts) [74 files] — auto-adjust conscience_gamma + reasoning_engine disabled by default + HF_TOKEN scrubbed

V6.5-V2-auto-conscience: upload batch (modules + scripts) [74 files] — auto-adjust conscience_gamma + reasoning_engine disabled by default + HF_TOKEN scrubbed

V6.5-V2-auto-conscience: upload batch (modules + scripts) [73 files] — auto-adjust conscience_gamma + reasoning_engine disabled by default + HF_TOKEN scrubbed

V6.5-V2-metrics-FIX-2: fix HF organization — remove 9 root-level duplicates, upload 13 files to correct src/bigru_t/ paths

V6.5-V2-metrics-FIX: cleanup batch — remove .pt files + duplicate root-level modules + obsolete modules (17 files)

Delete src/bigru_t/training/elastic_weight_consolidation.py

Delete src/bigru_t/model/kohonen_refactored

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

Delete src/bigru_t/model/unified_model.py

Delete src/bigru_t/model/u8cell_t.py

Delete src/bigru_t/model/transformer_unit.py

Delete src/bigru_t/model/orq_cell.py

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

Delete src/bigru_t/model/gru_hierarchy.py

Delete src/bigru_t/model/bigru4.py

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).

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Upload folder using huggingface_hub