Download docs/H1B_VALIDATION.json from codemaivanngu/ctopd: direct link, hf CLI and curl.
- Browser
- Download file 3.49 kB
-
https://huggingface.co/codemaivanngu/ctopd/resolve/main/docs/H1B_VALIDATION.json
- Command line
-
hf download hf://codemaivanngu/ctopd/docs/H1B_VALIDATION.json
-
curl -L -o H1B_VALIDATION.json https://huggingface.co/codemaivanngu/ctopd/resolve/main/docs/H1B_VALIDATION.json
3.49 kB
| { | |
| "date": "2026-10-19", | |
| "baseline_commit": "0eeed4ca2b0d7b07dd50076e35d81f030a3b9f2d", | |
| "platform": "WSL Linux, existing CPU environment; no package installation", | |
| "python": "3.12.3", | |
| "torch": "2.14.0+cpu", | |
| "full_suite": { | |
| "command": "TORCH_COMPILE_DISABLE=1 OMP_NUM_THREADS=1 python -m unittest discover -s tests -v", | |
| "passed": 104, | |
| "skipped": 0, | |
| "elapsed_seconds": 72.46 | |
| }, | |
| "verified": [ | |
| "2000 cover-prefix/brute-force queries, duplicate byte IDs and 0xff bounds", | |
| "Strict-group fixture parity including EOS and flattened response offsets", | |
| "30-token toy LM on 50 strings: one-exit enumeration equals trunk; exhaustive probability >= trunk >= canonical path", | |
| "Exact search duplicate branches, pruning/node-budget omitted-mass bounds", | |
| "Same-tokenizer fixture: all five arms have identical loss and zero span term", | |
| "Previous-window baseline, state restore and no evaluation/no-grad mutation", | |
| "Arm b student gradients equal autograd span MSE; arm a loss/all student gradients equal Strict on accepted fixtures", | |
| "Tile/checkpoint gradient invariance; whole-response mismatch exclusion and connected zero backward", | |
| "Actual actor fit/evaluate bodies with CPU SGD: window hook after one optimizer update and no hook during evaluation", | |
| "Actual rollout tokenizer method: EOS policy and raw re-encoding match field", | |
| "Actual math evaluation sampling expression: independent eval top-p and unchanged rollout kwargs", | |
| "Window moments weight chunks directly rather than microbatch means", | |
| "CountSketch chunk invariance, fixture norm error <1 percent and cosine error <0.01", | |
| "End-to-end saved sketch analysis CLI, known noise curve and undefined zero-vector handling", | |
| "KV oracle versus full-prefix fixture with deliberately mutating cache and sibling branches", | |
| "Five full-workload launcher dry-run plans; separate five-step diagnostic preview", | |
| "New source hashes verified; six frozen Strict sources match baseline Git blobs", | |
| "All existing Strict/SimCT/MP/ALIGN/TRUST regression tests", | |
| "git diff --check", | |
| "Old archive teacher-prompt recovery: exact unambiguous dataset/template match, no sampled-ID fabrication" | |
| ], | |
| "test_isolation": "CPU suite bypasses utility package tokenizer-factory initialization using a test-only namespace; real algorithm/loss/logging numerical source is executed", | |
| "not_measured": [ | |
| "T1 on 10000 real texts with both real tokenizers", | |
| "T3/T9 on 500 real archived responses", | |
| "M2 real model trunk table and M3 exact/trunk gate at checkpoints 0 and 60", | |
| "T10 five-preset B200/FSDP canaries and parquet validation", | |
| "Real HF KV cache compatibility, head-tile throughput and memory", | |
| "T11 on two full-model gradient groups; real replay curves", | |
| "Full training, task accuracy, bias-versus-variance decision or paper reproduction" | |
| ], | |
| "deliberately_not_implemented": [ | |
| "Batched KV frontier expansion; current checker uses depth-bounded DFS cache with full-prefix fallback", | |
| "Conditional depth-2 training estimator before a failed measured trunk gate", | |
| "Optional Adam-preconditioned replay and optimizer-state exports", | |
| "Fresh 4096-response generation; replay requires a supplied fixed archive", | |
| "Automatic causal decision-table classification or optional c-plus experiments" | |
| ], | |
| "compute": "No new GPU job, model/dataset download, remote build or training launched", | |
| "h1b_tests_in_full_suite": 21 | |
| } | |