{ "schema": "wald-q4b-release-check/1", "release": "Wald-Q4B v1.2", "revision": "v1.2", "commit": "db376d325c9eeb884d172e8ca9f3502d104936bb", "date": "2026-10-01", "weights": { "hub_lfs_sha256": { "model-00001-of-00002.safetensors": "0b15067f769e7388bd598aabafa2ea3211a3a0c4e49e47d07c4f65c65ffc25dd", "model-00002-of-00002.safetensors": "7cff102b314edeb3dc5abfa7063f72ad3e888884da237601239dc3582074120a" }, "equal_to_recorded_merged_checkpoint": true }, "tree": { "files": 69, "bytes": 8432242541, "unchanged_from_main_at_1f960412": 54, "new_files": [ "evaluation/v1.2/summary.json" ] }, "anonymous_download": { "route": "hf-mirror.com, no token", "files": 69, "manifest_entries_checked": 60, "manifest_sha256_mismatches": 0 }, "jevbench_public_231_effort_none": { "how": "JevBench CLI (fstandhartinger/jevbench@9ec6f15a, typesafe adapter, serial, loopback) against wald-serve 0.1.0 + vLLM 0.30.0 on one RTX 5090; effort none taken from the release serving.json (/health: effort none)", "pre_release_read_2026-09-30": { "correct": 204, "of": 231, "tiers": { "easy": "48/48", "original": "72/72", "hard": "84/111" }, "ece": 0.045, "brier": 0.191, "generated_tokens": 0 }, "download_model_files_only": { "correct": 204, "of": 231, "tiers": { "easy": "48/48", "original": "72/72", "hard": "84/111" }, "ece": 0.045, "brier": 0.191, "generated_tokens": 0, "same_option_as_pre_release_read": 231, "max_abs_probability_difference": 0.0083, "directory": "only config, tokenizer, chat template, the two weight shards, temperature.json and serving.json of the download" }, "download_complete_directory_read_1": { "correct": 204, "of": 231, "tiers": { "easy": "48/48", "original": "72/72", "hard": "84/111" }, "ece": 0.053, "brier": 0.191, "generated_tokens": 0, "same_option_as_pre_release_read": 229, "max_abs_probability_difference": 0.0271, "directory": "the complete downloaded repository" }, "download_complete_directory_read_2": { "correct": 205, "of": 231, "tiers": { "easy": "48/48", "original": "72/72", "hard": "85/111" }, "ece": 0.053, "brier": 0.191, "generated_tokens": 0, "same_option_as_pre_release_read": 230, "max_abs_probability_difference": 0.0217, "directory": "the complete downloaded repository, separate server start" }, "note": "The model files are byte-identical in all reads. From the complete repository directory almost every probability moves slightly (mean absolute difference 0.0013) and one or two near-tied items change option; from a directory with only the model files the pre-release read is reproduced. The cause of this difference is not yet explained." } }