6.62 GB

Ctrl+K

1 contributor

History: 357 commits

tchbcb

Upload t4_assets_v5/eval_report_gen17_heldout.json with huggingface_hub

8b86363 verified 29 days ago

agent
QwenJev: multimodal-retrofitted NanoJev for ARC-AGI-3 (initial skeleton) about 1 month ago
configs
Upload configs/train_teach.yaml with huggingface_hub about 1 month ago
data
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified) about 1 month ago
ops
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified) about 1 month ago
qwenjev
v0.4.9: vision-aware pooling (RCA fix) + v4 namespace + eps0.45 collect config about 1 month ago
scripts
v0.4.10: watchdog env-driven checkpoint about 1 month ago
t4_assets
t4_assets README: compile-cache section revised (v2 audit) about 1 month ago
t4_assets_v2
t4_assets_v2: eval via ops/run_eval.py entry (mock-pushbox 300 acts, 601.1s, LoRA merged) about 1 month ago
t4_assets_v3
t4_assets_v3: calib_report.json (real-games run) about 1 month ago
t4_assets_v4
t4_assets_v3: calib_report.json (real-games run) about 1 month ago
t4_assets_v5
Upload t4_assets_v5/eval_report_gen17_heldout.json with huggingface_hub 29 days ago
tests
QwenJev v0.2.0: vision tower on the System-1 inference path (tiny/hf backends, mock env, e2e local run) about 1 month ago
train
Upload train/train_system1.py with huggingface_hub about 1 month ago
.env.example
520 Bytes
QwenJev: multimodal-retrofitted NanoJev for ARC-AGI-3 (initial skeleton) about 1 month ago
.gitattributes
7.03 kB
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified) about 1 month ago
.gitignore
330 Bytes
QwenJev: multimodal-retrofitted NanoJev for ARC-AGI-3 (initial skeleton) about 1 month ago
HANDOVER.md
37.6 kB
Upload HANDOVER.md with huggingface_hub about 1 month ago
LICENSE
1.06 kB
QwenJev: multimodal-retrofitted NanoJev for ARC-AGI-3 (initial skeleton) about 1 month ago
Makefile
2.88 kB
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified) about 1 month ago
README.md
0 Bytes
QwenJev: multimodal-retrofitted NanoJev for ARC-AGI-3 (initial skeleton) about 1 month ago
eval_diag_ar25_v3.jsonl
13.7 kB
v0.4.9: RCA evidence archived + HANDOVER §0.4 about 1 month ago
eval_diag_ar25_v3_summary.json
166 Bytes
v0.4.9: RCA evidence archived + HANDOVER §0.4 about 1 month ago
eval_report.json
122 Bytes
sync: local CPU-run eval record about 1 month ago
eval_report_public25_cpu.json
5.9 kB
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified) about 1 month ago
eval_report_public25_v2_partial.json
1.1 kB
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified) about 1 month ago
eval_report_random_baseline_partial.json
2.48 kB
Upload eval_report_random_baseline_partial.json with huggingface_hub about 1 month ago
eval_report_real_stageB_smoke.json
558 Bytes
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified) about 1 month ago
eval_report_v3_ar25_bp35.json
766 Bytes
v3 comparison eval: ar25+bp35 vs zero-shot baseline (best_level_sum=0, negative result) about 1 month ago
eval_report_v4_ar25_bp35.json
766 Bytes
v4 recovery control eval: ar25+bp35 x150 (negative, best_level_sum=0) about 1 month ago
eval_report_v4b_ar25_600.json
856 Bytes
Upload eval_report_v4b_ar25_600.json with huggingface_hub about 1 month ago
eval_report_v4b_ar25_bp35.json
767 Bytes
Upload eval_report_v4b_ar25_bp35.json with huggingface_hub about 1 month ago
level3_board_snapshot.json
5.04 kB
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified) about 1 month ago
requirements.txt
445 Bytes
QwenJev: multimodal-retrofitted NanoJev for ARC-AGI-3 (initial skeleton) about 1 month ago
train.md
30.8 kB
v0.4.4: train.md §8.3 — v3 real-games round about 1 month ago