V6.5-attn-v2 cleanup: remove legacy v6_5_7ds_attn_training_metrics.json

V6.5-attn-v2 cleanup: remove legacy v6_5_7ds_attn_report.json

V6.5-attn-v2 cleanup: remove legacy scripts/upload_v6_5_7ds.py

V6.5-attn-v2 cleanup: remove legacy scripts/train_v6_5_7ds.py

V6.5-attn-v2 cleanup: remove legacy v6_5_7ds_upload_report.json

V6.5-attn-v2 cleanup: remove legacy v6_5_7ds_w8a8_compression.json

V6.5-attn-v2 cleanup: remove legacy v6_5_7ds_reasoning_eval.json

V6.5-attn-v2 cleanup: remove legacy v6_5_7ds_ewc_w8a8_benchmark.json

V6.5-attn-v2 cleanup: remove legacy v6_5_7ds_script_activity.json

V6.5-attn-v2 cleanup: remove legacy v6_5_7ds_module_analysis.json

V6.5-attn-v2 cleanup: remove legacy v6_5_7ds_training_metrics.json

V6.5-attn-v2 cleanup: remove legacy v6_5_7ds_report.json

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v3/v4/v5/v6_1/v6_2/v6_3/v6_progressive + old v6_5_*/v6_5_final_*/v6_5_7ds_* + v6_5_7ds_attn_* v1 reports/scripts (superseded by v2)

V6.5-attn: add upload report (post-upload artifact)

V6.5-attn cleanup: remove legacy scripts/upload_v6_5_7ds.py

V6.5-attn cleanup: remove legacy scripts/train_v6_5_7ds.py

V6.5-attn cleanup: remove legacy v6_5_7ds_upload_report.json

V6.5-attn cleanup: remove legacy v6_5_7ds_w8a8_compression.json

V6.5-attn cleanup: remove legacy v6_5_7ds_reasoning_eval.json

V6.5-attn cleanup: remove legacy v6_5_7ds_ewc_w8a8_benchmark.json

V6.5-attn cleanup: remove legacy v6_5_7ds_script_activity.json

V6.5-attn cleanup: remove legacy v6_5_7ds_module_analysis.json

V6.5-attn cleanup: remove legacy v6_5_7ds_training_metrics.json

V6.5-attn cleanup: remove legacy v6_5_7ds_report.json

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: add upload report (post-cleanup verification)

V6.5-7ds cleanup: remove legacy scripts/xeon_runtime.py

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

V6.5-7ds cleanup: remove legacy tokenizer/tokenizer.json

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

V6.5-7ds cleanup: remove legacy scripts/upload_v6_5_resilient.py

V6.5-7ds cleanup: remove legacy scripts/upload_v6_4_resilient.py

V6.5-7ds cleanup: remove legacy scripts/upload_v6_3_resilient.py

V6.5-7ds cleanup: remove legacy scripts/upload_v6_2_resilient.py

V6.5-7ds cleanup: remove legacy scripts/upload_v6_1_resilient.py

V6.5-7ds cleanup: remove legacy scripts/upload_to_hf.py

V6.5-7ds cleanup: remove legacy scripts/train_v6_5_final.py

V6.5-7ds cleanup: remove legacy scripts/train_v6_5.py

V6.5-7ds cleanup: remove legacy scripts/train_v6_progressive.py

V6.5-7ds cleanup: remove legacy scripts/train_v6_3.py

V6.5-7ds cleanup: remove legacy scripts/train_v6_2.py

V6.5-7ds cleanup: remove legacy scripts/train_v6_1.py

V6.5-7ds cleanup: remove legacy scripts/train_v2.py

V6.5-7ds cleanup: remove legacy scripts/train_fast.py

V6.5-7ds cleanup: remove legacy scripts/train.py

V6.5-7ds cleanup: remove legacy scripts/smoke_test.py

V6.5-7ds cleanup: remove legacy scripts/parse_v6_log.py

V6.5-7ds cleanup: remove legacy v6_5_final_w8a8_compression.json

V6.5-7ds cleanup: remove legacy v6_5_final_reasoning_eval.json

V6.5-7ds cleanup: remove legacy v6_5_final_ewc_w8a8_benchmark.json