state: generation 8289 (cycle)

This commit is contained in:
2026-09-16 16:44:47 +00:00
parent dedf1d69bf
commit 7e9719873f
9 changed files with 1945 additions and 1947 deletions

View File

@@ -1695,7 +1695,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-16T16:41:45.046517+00:00",
"generatedAt": "2026-09-16T16:44:46.862290+00:00",
"summary": {
"activeBlockCount": 82,
"byGpuFramework": {

View File

@@ -19,7 +19,7 @@
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 604,
"listingErrors": 605,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 10,
"nextAccountIndex": 11,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-16T16:41:45.020811+00:00",
"updatedAt": "2026-09-16T16:44:46.831918+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-16T16:39:46.696912+00:00",
"generatedAt": "2026-09-16T16:42:55.581567+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-16T16:08:21.811082+00:00",
"lastSyncTime": "2026-09-16T16:08:21.748785+00:00",
"generatedAt": "2026-09-16T16:42:47.816275+00:00",
"lastSyncTime": "2026-09-16T16:42:46.012489+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1928,25 +1928,25 @@
"unresolvedFailureCount": 59
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 13,
"decisionFailureRate": 0.9286,
"decisionSuccessRate": 0.0714,
"decisionTotal": 14,
"attributableFailureCount": 14,
"decisionFailureRate": 0.9333,
"decisionSuccessRate": 0.0667,
"decisionTotal": 15,
"failureBreakdown": {
"framework_architecture_unsupported": 8,
"framework_architecture_unsupported": 9,
"model_load": 5
},
"failureCount": 13,
"failureRate": 0.9286,
"failureCount": 14,
"failureRate": 0.9333,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0714,
"successRate": 0.0667,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 14,
"total": 15,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2786,14 +2786,14 @@
"unresolvedFailureCount": 903
},
"vllm": {
"attributableFailureCount": 366,
"decisionFailureRate": 0.9606,
"decisionSuccessRate": 0.0394,
"decisionTotal": 381,
"attributableFailureCount": 367,
"decisionFailureRate": 0.9607,
"decisionSuccessRate": 0.0393,
"decisionTotal": 382,
"failureBreakdown": {
"ambiguous_runtime": 222,
"backend_operator": 35,
"framework_architecture_unsupported": 270,
"framework_architecture_unsupported": 271,
"memory_capacity": 7,
"model_load": 31,
"platform_infrastructure": 2,
@@ -2802,14 +2802,14 @@
"tokenizer_compatibility": 9,
"参数/模板问题": 31
},
"failureCount": 621,
"failureRate": 0.9764,
"failureCount": 622,
"failureRate": 0.9765,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0236,
"total": 636,
"successRate": 0.0235,
"total": 637,
"unresolvedFailureCount": 253
},
"vllm-mlu": {
@@ -2920,7 +2920,7 @@
"unresolvedFailureCount": 5
}
},
"generatedAt": "2026-09-16T16:08:21.805748+00:00",
"generatedAt": "2026-09-16T16:42:47.811297+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 49,
@@ -2971,28 +2971,28 @@
"unresolvedFailureCount": 231
},
"Biren_166m": {
"attributableFailureCount": 49,
"decisionFailureRate": 0.9423,
"decisionSuccessRate": 0.0577,
"decisionTotal": 52,
"attributableFailureCount": 50,
"decisionFailureRate": 0.9434,
"decisionSuccessRate": 0.0566,
"decisionTotal": 53,
"failureBreakdown": {
"ambiguous_runtime": 31,
"backend_operator": 4,
"framework_architecture_unsupported": 35,
"framework_architecture_unsupported": 36,
"memory_capacity": 1,
"model_load": 8,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 108,
"failureRate": 0.973,
"failureCount": 109,
"failureRate": 0.9732,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.027,
"total": 111,
"successRate": 0.0268,
"total": 112,
"unresolvedFailureCount": 59
},
"Cambricon_mlu-370-x4": {
@@ -3526,14 +3526,14 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
@@ -3545,7 +3545,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|escha": {
@@ -7143,14 +7143,14 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors|33": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
@@ -7163,7 +7163,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors|34": {
@@ -10969,17 +10969,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2030,
"totalRecords": 2124,
"terminalRecords": 2031,
"totalRecords": 2125,
"totals": {
"attributableFailureCount": 652,
"decisionFailureRate": 0.8919,
"decisionSuccessRate": 0.1081,
"decisionTotal": 731,
"attributableFailureCount": 653,
"decisionFailureRate": 0.8921,
"decisionSuccessRate": 0.1079,
"decisionTotal": 732,
"failureBreakdown": {
"ambiguous_runtime": 492,
"backend_operator": 45,
"framework_architecture_unsupported": 427,
"framework_architecture_unsupported": 428,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
@@ -10989,29 +10989,29 @@
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1951,
"failureCount": 1952,
"failureRate": 0.9611,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 79,
"successRate": 0.0389,
"total": 2030,
"total": 2031,
"unresolvedFailureCount": 1289
},
"warnings": [
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -11036,6 +11036,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2124,
"summarizedRecords": 2125,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "d80565598353a1176f1ac399db2193f7fd982ca5bc3e25fe2e031663376cd6de",
".modelhub_state/architecture_history_backfill.json": "83654b4f0b92599aa518065c7fe9eb59215bd6f3159761a1246c4eb7afaa0387",
".modelhub_state/market_intelligence.json": "2f216944c012a66a507bf7ded353ecb7bb1a5eb358b90019d5903adf1908224c",
".modelhub_state/official_capabilities.json": "43e093948f9ed41ef027a9deb55974794488e68c3c3d578d09c1733dd6783074",
".modelhub_state/outcome_checkpoint.json": "469a988db25a6d906e73879f41b99f3e68813bc6938137b8c46510693f6d3379",
".modelhub_state/architecture_compatibility_blacklist.json": "f4e9f089839ec9901fe3ef6ea2ad803e6155783b13a54a134fa0f2a8c65474c5",
".modelhub_state/architecture_history_backfill.json": "bdded39ef38bb519626d796c32e9f62cbddfefeb07152c20ce85f9139dadaa82",
".modelhub_state/market_intelligence.json": "7a9290c7ca07b87124fa1b12d1f63fe2fdfd37fe1b2811224d6ecdc546d6f5e0",
".modelhub_state/official_capabilities.json": "5a1c3a20ba172d6699245884b389140ab5c311b3e17c4a6fc29bf4d73668683d",
".modelhub_state/outcome_checkpoint.json": "60eaa667fa40eb15abde2f1e0a53aafce3965aca13e0655bf46c6ea7a6f1377c",
".modelhub_state/queue_cleanup_latest.json": "057079282bc277b3a97c1805915c45464c12312f8ee3ba54d0366d05f34f4466",
".modelhub_state/recent_outcomes.jsonl": "c62a5bc6c77924d26b6d570266710b5821207f6232b6da4c617a15c450ac244c",
".modelhub_state/recovery_active_tasks.jsonl": "0c4ff5e674d8d5e47292e23ed5b607caaf4aeb7295292e26a18de6b63d7f983c",
".modelhub_state/recovery_intents.jsonl": "2446dfb489788318d9da10e4b85d858b420723a4f54a2538a3ab1027bf54e6fd",
".modelhub_state/recovery_active_tasks.jsonl": "4dea122aa88f21c87ac89204ca0bd2ef7424de918bd451d56ec384e3caefc746",
".modelhub_state/recovery_intents.jsonl": "add5ef996527dca63d0ab49e6f7899d1823180b4944b7ad33a00cc5d5d1e05fa",
".modelhub_state/routing_intelligence.json": "4275c8de18746877d1962058e46f20f3f955ef5e9cbd029bc9834e7f0c421846",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "aedfc79c1f642afd6cbecfd2e225d91b4fd7d6f46bce98744cf07a275d1037cf",
"outcomes/submissions.jsonl": "472039df51b56482603171f5729ac23afe31f5df8e234f81daa1ec1d1173ce15"
"outcomes/submissions.jsonl": "767174c63029ce4fc6cead45c3ba09c5f505f5fc816795df3004a0c6eb4ad2eb"
},
"generation": 8288,
"generation": 8289,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-16T16:41:45.208945+00:00",
"updatedAt": "2026-09-16T16:44:47.632686+00:00",
"writerId": "eccb3e0018f640d19e578c271a207b5c"
}

View File

@@ -143,7 +143,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903644+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:16.487544+00:00", "targetGpu": "Biren_166m", "taskId": "4713228", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903614+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:16.515462+00:00", "targetGpu": "Biren_166m", "taskId": "4713229", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903599+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21921675140, "estimatedRequiredGiB": 24.525, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 21944922993, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18589348592, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:vllm", "custom_tag:sm121", "custom_tag:gb10", "custom_tag:dgx-spark", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:modelopt"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21944922993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:16.516825+00:00", "targetGpu": "Biren_166m", "taskId": "4713224", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903621+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:24.345690+00:00", "targetGpu": "Biren_166m", "taskId": "4713233", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903627+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:24.160342+00:00", "targetGpu": "Biren_166m", "taskId": "4713232", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T15:30:55.706707+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:30:11.995863+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4713445", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T17:15:48.506915+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426226990, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T09:15:31.168687+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4715997", "taskType": "text-generation", "verifyResult": null}