{ "schemaVersion": 1, "model": { "repo": "henry1477/translategemma-27b-it-NVFP4A16", "baseRepo": "google/translategemma-27b-it", "baseRevision": "7d10f0b72f89a2d0f268cea30727d8b77c0d25c2", "scheme": "NVFP4A16", "architecture": "Gemma3ForCausalLM", "checkpointSha256": "a636a4d1b71c6e0c7d8450e0d70c2ed494fa74594b4a8652c0da2f24b7f92f5c", "parametersBefore": 27432406640, "parametersAfter": 27009346304 }, "calibration": { "prompts": 512, "cues": 10240, "sourceLanguages": [ "ar", "bg", "ca", "cs", "da", "de", "el", "es", "fi", "fr", "he", "hi", "hu", "id", "it", "ja", "ko", "ms", "nl", "no", "pl", "pt", "ro", "ru", "sv", "th", "tr", "uk", "vi", "zh" ], "targetLanguages": [ "en", "es-MX" ], "sha256": "d5e42cebbf1e5c9f05e04c84751bac3076ca8886c98cad42442115075625159c", "maxSequenceLength": 2048, "rtnFallbackModules": 62, "rtnFallbackPattern": "model.layers.{0..61}.mlp.down_proj" }, "productionProfile": { "maxModelLen": 4096, "constrainedJson": true, "gpuMemoryUtilization": 0.78, "maxNumSeqs": 4, "waveConcurrency": 2, "kvAllocatorHeadroom": true }, "baseline": { "repo": "henry1477/translategemma-12b-it-NVFP4A16", "revision": "a4afd9372aaad181f97ba2ba057524ea95d281e7", "succeeded": true, "structuralPass": true, "metrics": { "engine": "vllm", "label": "12b-real-corpus-production-recovery", "model": "/models/huggingface/models--henry1477--translategemma-12b-it-NVFP4A16/snapshots/a4afd9372aaad181f97ba2ba057524ea95d281e7", "timestamp": "2026-08-28T04:51:20Z", "load_seconds": 97.9, "generate_seconds": 20.5, "first_token_seconds": null, "output_tokens": 10146, "generation_requests": 18, "recovery_splits": 2, "output_tokens_per_second": 494.1, "scenes_per_minute": 40.91, "peak_vram_mib": 30456, "max_num_seqs": 16, "max_model_len": 4096, "constrained_json": true, "clock_drift_pct": 1395.9, "scenes": 14, "validated": 14, "validation_rate": 100.0, "cues": 261, "copy_rate": 1.9157088122605364, "empty_cues": 0, "length_ratio_median": 1.091, "chrf_vs_reference": 95.86, "chrf_vs_int8": 95.86, "chrf_samples": 261 } }, "candidate": { "modelLoaded": true, "structuralPass": true, "qualityRegression": false, "releaseStable": true, "waves": [ { "number": 1, "executed": true, "exitCode": 0, "structuralPass": true, "generationCalls": 8, "elapsedSeconds": 195.98844933509827, "releaseStable": true, "remainingGpuProcesses": "" }, { "number": 2, "executed": true, "exitCode": 0, "structuralPass": true, "generationCalls": 8, "elapsedSeconds": 53.89741849899292, "releaseStable": true, "remainingGpuProcesses": "" } ], "realCorpusWaves": [ { "engine": "vllm", "label": "27b-real-corpus-wave-1", "model": "/out/translategemma-27b-it-NVFP4A16", "timestamp": "2026-08-28T04:55:26Z", "load_seconds": 187.3, "generate_seconds": 38.7, "first_token_seconds": null, "output_tokens": 8292, "generation_requests": 14, "recovery_splits": 0, "output_tokens_per_second": 214.52, "scenes_per_minute": 21.73, "peak_vram_mib": 24800, "max_num_seqs": 4, "max_model_len": 4096, "constrained_json": true, "clock_drift_pct": 180.5, "scenes": 14, "validated": 14, "validation_rate": 100.0, "cues": 261, "copy_rate": 2.681992337164751, "empty_cues": 0, "length_ratio_median": 1.061, "chrf_vs_reference": 65.19, "chrf_vs_int8": 65.19, "chrf_samples": 261 }, { "engine": "vllm", "label": "27b-real-corpus-wave-2", "model": "/out/translategemma-27b-it-NVFP4A16", "timestamp": "2026-08-28T05:00:06Z", "load_seconds": 135.0, "generate_seconds": 37.7, "first_token_seconds": null, "output_tokens": 8276, "generation_requests": 14, "recovery_splits": 0, "output_tokens_per_second": 219.65, "scenes_per_minute": 22.29, "peak_vram_mib": 26618, "max_num_seqs": 4, "max_model_len": 4096, "constrained_json": true, "clock_drift_pct": 1392.3, "scenes": 14, "validated": 14, "validation_rate": 100.0, "cues": 261, "copy_rate": 2.681992337164751, "empty_cues": 0, "length_ratio_median": 1.062, "chrf_vs_reference": 64.86, "chrf_vs_int8": 64.86, "chrf_samples": 261 } ], "sourceConditionedQuality": { "mode": "reference-free-QE", "lowerIsBetter": true, "cues": 261, "evaluator": { "repo": "google/metricx-24-hybrid-large-v2p6", "revision": "51e875ba5c525c81627cfd135ee10f43c87dce00", "codeRevision": "fc4978eb064670f7cc33e93ea4f52d38396b8ae6" }, "baselineMeanError": 5.573672558992773, "candidateMeanError": 4.607441142943627, "candidateWins": 140, "baselineWins": 104, "ties": 17, "inputSha256": "728959634edee1956351111a951b0c9112a37c43780ae76db9b73ebbace9153a", "outputSha256": "6654017948d897bd135ab9841a10c18c3c36c0b40bb1c3315b572242c1ff01a2" }, "manualReview": { "reviewerType": "Codex bilingual source-grounded manual audit", "reviewedAt": "2026-08-28T05:08:00Z", "method": "Adversarial sample: the 20 largest MetricX candidate-minus-baseline error deltas plus systematic every-eighth-cue coverage to 50 unique cues. Each Spanish ASR fragment was compared directly with both English outputs.", "sampledCues": 50, "passed": true, "candidateMajorErrorCueIds": [ "a1-c000071", "a1-c000193" ], "baselineMajorErrorCueIds": [ "a1-c000031", "a1-c000129", "a1-c000137" ], "limitations": "Source ASR contains many incomplete fragments; judgments assess faithfulness at the durable cue boundary and explicitly retain ambiguous cases as equivalent rather than guessing missing context. This is an AI-assisted manual audit, not a human review.", "counts": { "candidate_better": 10, "baseline_better": 9, "equivalent_or_no_material_regression": 31 } }, "multilingual": { "schemaVersion": 1, "label": "27b-multilingual", "model": "/out/translategemma-27b-it-NVFP4A16", "timestamp": "2026-08-28T05:17:11Z", "productionProfile": { "maxModelLen": 4096, "constrainedJson": true, "gpuMemoryUtilization": 0.78, "maxNumSeqs": 4 }, "sourceLanguages": [ "ar", "bg", "ca", "cs", "da", "de", "el", "es", "fi", "fr", "he", "hi", "hu", "id", "it", "ja", "ko", "ms", "nl", "no", "pl", "pt", "ro", "ru", "sv", "th", "tr", "uk", "vi", "zh" ], "targets": [ "en", "es-MX" ], "loadSeconds": 131.22, "generationSeconds": 143.34, "peakVramMiB": 26625, "scenes": 60, "cues": 1200, "structuralScenes": 60, "structuralPassRate": 100.0, "emptyCues": 0, "sourceCopyRate": 2.92, "chrfVs12BMean": 75.55, "chrfVs12BMedian": 83.23, "chrfVs12BBySource": { "ar": 72.42, "bg": 76.13, "ca": 77.91, "cs": 74.33, "da": 86.96, "de": 70.92, "el": 81.63, "es": 88.2, "fi": 85.81, "fr": 81.35, "he": 75.67, "hi": 70.25, "hu": 84.41, "id": 77.8, "it": 83.87, "ja": 58.54, "ko": 59.12, "ms": 60.5, "nl": 83.55, "no": 81.41, "pl": 79.38, "pt": 75.32, "ro": 82.33, "ru": 80.34, "sv": 79.61, "th": 59.11, "tr": 71.0, "uk": 69.63, "vi": 76.03, "zh": 63.02 } } }, "multilingualBaseline": { "schemaVersion": 1, "label": "12b-multilingual", "model": "/models/huggingface/models--henry1477--translategemma-12b-it-NVFP4A16/snapshots/a4afd9372aaad181f97ba2ba057524ea95d281e7", "timestamp": "2026-08-28T05:12:18Z", "productionProfile": { "maxModelLen": 4096, "constrainedJson": true, "gpuMemoryUtilization": 0.88, "maxNumSeqs": 16 }, "sourceLanguages": [ "ar", "bg", "ca", "cs", "da", "de", "el", "es", "fi", "fr", "he", "hi", "hu", "id", "it", "ja", "ko", "ms", "nl", "no", "pl", "pt", "ro", "ru", "sv", "th", "tr", "uk", "vi", "zh" ], "targets": [ "en", "es-MX" ], "loadSeconds": 114.06, "generationSeconds": 36.6, "peakVramMiB": 30993, "scenes": 60, "cues": 1200, "structuralScenes": 60, "structuralPassRate": 100.0, "emptyCues": 0, "sourceCopyRate": 2.92, "chrfVs12BMean": null, "chrfVs12BMedian": null, "chrfVs12BBySource": {} }, "qualityDecision": { "present": true, "matchingRevisions": true, "baselineStructuralPass": true, "candidateStructuralPass": true, "chrfVs12B": 65.19, "minimumChrfVs12B": 80.0, "lexicalAgreementPass": false, "sourceConditionedQualityPass": true, "qualityMetricPass": true, "copyRatePass": true, "manualReviewPass": true, "humanReviewPass": true, "noStructuralRegression": true, "noQualityRegression": true }, "environment": { "gpuUuid": "GPU-4bd4db57-095d-d266-8453-a4d9dc822610", "gpuName": "NVIDIA GeForce RTX 5090", "vramMiB": 32607, "driverVersion": "595.79", "cudaRuntime": "13.2", "vllmVersion": "0.27.1", "torchVersion": "2.13.0+cu130", "pipelineCommit": "7cde44cede87fa97cf5e57125c002ea33af3aee9" }, "artifacts": { "real-12b.json": "69e6e69d8594f5250a3b3e199ed45798fca35f94b8a373da351b69413c29709f", "real-27b-wave1.json": "0d148ac727dfb3fd51c61599d235dcd2a10718a26e166fe43a4a8813059c9db6", "real-27b-wave2.json": "334e59c75deba46a47ce3da607bad7cb639925fb208ad660bfe3523569b61d75", "multi-12b.json": "393a466316c496f138ca6a3000e34ac49f1770becc40ba5a5d7f728f67f868aa", "multi-27b.json": "d6802aae0ec472ad4db06d95248e60e04c0426f7d634ebcd3f6de2f01e8ffe58", "metricx-quality.json": "865adfd33054d57f8fb1ac40f3d016d66c5c46d65b31aaad0985c503411254b6", "manual-quality-audit.json": "d00f8c6afbbff1d5d1dcc904ddf9248057fdbd6df23ebe4600d0e5cef3c5b59d", "production-waves.json": "31f28efa6a4d3424f21241026dd3f32935c67fa41c4d3417b4f7a402da1dc8cf" }, "approval": { "passed": true, "reason": "All structural, two-wave release, multilingual, source-conditioned QE, and adversarial manual-audit gates passed." } }