V6.5-7ds cleanup: remove legacy v6_5_final_script_activity.json

V6.5-7ds cleanup: remove legacy v6_5_final_module_analysis.json

V6.5-7ds cleanup: remove legacy v6_5_final_training_metrics.json

V6.5-7ds cleanup: remove legacy v6_5_final_report.json

V6.5-7ds cleanup: remove legacy v6_5_upload_report.json

V6.5-7ds cleanup: remove legacy v6_5_reasoning_eval.json

V6.5-7ds cleanup: remove legacy v6_5_ewc_w8a8_benchmark.json

V6.5-7ds cleanup: remove legacy v6_5_script_activity.json

V6.5-7ds cleanup: remove legacy v6_5_module_analysis.json

V6.5-7ds cleanup: remove legacy v6_5_training_metrics.json

V6.5-7ds cleanup: remove legacy v6_5_report.json

V6.5-7ds cleanup: remove legacy v6_3_training_metrics.json

V6.5-7ds cleanup: remove legacy v6_3_report.json

V6.5-7ds cleanup: remove legacy v6_2_upload_report.json

V6.5-7ds cleanup: remove legacy v6_2_report.json

V6.5-7ds cleanup: remove legacy v6_1_upload_report.json

V6.5-7ds cleanup: remove legacy v6_1_report.json

V6.5-7ds cleanup: remove legacy v6_progressive_train.log

V6.5-7ds cleanup: remove legacy v6_progressive_report.json

V6.5-7ds cleanup: remove legacy v6_upload_report.json

V6.5-7ds cleanup: remove legacy v6_report.json

V6.5-7ds cleanup: remove legacy training_report.json

V6.5-7ds cleanup: remove legacy v32_upload_report.json

V6.5-7ds cleanup: remove legacy v32_test_report.json

V6.5-7ds cleanup: remove legacy v5_upload_report.json

V6.5-7ds cleanup: remove legacy v5_report.json

V6.5-7ds cleanup: remove legacy v4_report.json

V6.5-7ds cleanup: remove legacy v3_report.json

V6.5-7ds cleanup: remove legacy bug_hunt_v3_report.json

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+: add v6_progressive_train.log

V6+: add v6_progressive_report.json

V6+: add scripts/parse_v6_log.py

V6+: add scripts/train_v6_progressive.py

V6+: add xeon_runtime.py with IPEX/AMX/AVX512 + FP16/BF16 benchmark

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

Delete _temp_checkpoints/temp_step3_epoch1.pt

Delete pytorch_model.bin

Delete model_final/pytorch_model.bin