state: generation 6983 (cycle)
This commit is contained in:
@@ -1496,7 +1496,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-14T01:54:35.127721+00:00",
|
||||
"generatedAt": "2026-09-14T01:57:23.064215+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 75,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
"10": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 507,
|
||||
"listingErrors": 508,
|
||||
"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": "2026-09-14T01:54:35.103106+00:00",
|
||||
"updatedAt": "2026-09-14T01:57:23.034259+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-14T01:52:52.083846+00:00",
|
||||
"generatedAt": "2026-09-14T01:55:42.337385+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-14T00:51:56.686083+00:00",
|
||||
"lastSyncTime": "2026-09-14T00:51:56.404636+00:00",
|
||||
"generatedAt": "2026-09-14T01:55:36.274651+00:00",
|
||||
"lastSyncTime": "2026-09-14T01:55:36.007099+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1929,26 +1929,27 @@
|
||||
"unresolvedFailureCount": 32
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
|
||||
"attributableFailureCount": 6,
|
||||
"decisionFailureRate": 0.75,
|
||||
"decisionSuccessRate": 0.25,
|
||||
"decisionTotal": 8,
|
||||
"attributableFailureCount": 7,
|
||||
"decisionFailureRate": 0.7778,
|
||||
"decisionSuccessRate": 0.2222,
|
||||
"decisionTotal": 9,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 3
|
||||
"framework_architecture_unsupported": 3,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 10,
|
||||
"failureRate": 0.8333,
|
||||
"failureCount": 11,
|
||||
"failureRate": 0.8462,
|
||||
"framework": "vllm_0_17_0_corex_4_4_0",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.1667,
|
||||
"successRate": 0.1538,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 12,
|
||||
"total": 13,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Iluvatar_bi-150|vllm|text-generation": {
|
||||
@@ -2598,23 +2599,24 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"vllm_0_17_0_corex_4_4_0": {
|
||||
"attributableFailureCount": 6,
|
||||
"decisionFailureRate": 0.75,
|
||||
"decisionSuccessRate": 0.25,
|
||||
"decisionTotal": 8,
|
||||
"attributableFailureCount": 7,
|
||||
"decisionFailureRate": 0.7778,
|
||||
"decisionSuccessRate": 0.2222,
|
||||
"decisionTotal": 9,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 3
|
||||
"framework_architecture_unsupported": 3,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 10,
|
||||
"failureRate": 0.8333,
|
||||
"failureCount": 11,
|
||||
"failureRate": 0.8462,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.1667,
|
||||
"total": 12,
|
||||
"successRate": 0.1538,
|
||||
"total": 13,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
@@ -2660,7 +2662,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-14T00:51:56.681297+00:00",
|
||||
"generatedAt": "2026-09-14T01:55:36.269841+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 31,
|
||||
@@ -2799,28 +2801,28 @@
|
||||
"unresolvedFailureCount": 29
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"attributableFailureCount": 33,
|
||||
"decisionFailureRate": 0.8049,
|
||||
"decisionSuccessRate": 0.1951,
|
||||
"decisionTotal": 41,
|
||||
"attributableFailureCount": 34,
|
||||
"decisionFailureRate": 0.8095,
|
||||
"decisionSuccessRate": 0.1905,
|
||||
"decisionTotal": 42,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"backend_operator": 6,
|
||||
"framework_architecture_unsupported": 17,
|
||||
"model_load": 7,
|
||||
"model_load": 8,
|
||||
"repository_structure": 1,
|
||||
"runtime_memory": 2,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 30
|
||||
},
|
||||
"failureCount": 77,
|
||||
"failureRate": 0.9059,
|
||||
"failureCount": 78,
|
||||
"failureRate": 0.907,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 8,
|
||||
"successRate": 0.0941,
|
||||
"total": 85,
|
||||
"successRate": 0.093,
|
||||
"total": 86,
|
||||
"unresolvedFailureCount": 44
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
@@ -3447,6 +3449,29 @@
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gpt_oss|mxfp4": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_0_17_0_corex_4_4_0",
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "mxfp4",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 0.75,
|
||||
@@ -5875,6 +5900,30 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gpt_oss|mxfp4|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_0_17_0_corex_4_4_0",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "mxfp4",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors|28": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -7694,19 +7743,19 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1793,
|
||||
"totalRecords": 1886,
|
||||
"terminalRecords": 1794,
|
||||
"totalRecords": 1887,
|
||||
"totals": {
|
||||
"attributableFailureCount": 533,
|
||||
"decisionFailureRate": 0.9003,
|
||||
"decisionSuccessRate": 0.0997,
|
||||
"decisionTotal": 592,
|
||||
"attributableFailureCount": 534,
|
||||
"decisionFailureRate": 0.9005,
|
||||
"decisionSuccessRate": 0.0995,
|
||||
"decisionTotal": 593,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 419,
|
||||
"backend_operator": 43,
|
||||
"framework_architecture_unsupported": 338,
|
||||
"memory_capacity": 12,
|
||||
"model_load": 74,
|
||||
"model_load": 75,
|
||||
"platform_infrastructure": 6,
|
||||
"repository_structure": 8,
|
||||
"runtime_memory": 6,
|
||||
@@ -7714,14 +7763,14 @@
|
||||
"参数/模板问题": 103,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1734,
|
||||
"failureCount": 1735,
|
||||
"failureRate": 0.9671,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 6,
|
||||
"successCount": 59,
|
||||
"successRate": 0.0329,
|
||||
"total": 1793,
|
||||
"total": 1794,
|
||||
"unresolvedFailureCount": 1195
|
||||
},
|
||||
"warnings": [
|
||||
@@ -7760,6 +7809,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1886,
|
||||
"summarizedRecords": 1887,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "ee6070e0c82c3bf232883b16deac8234bb9aa0345a0d97cd5f0abffe6e3ec4a6",
|
||||
".modelhub_state/architecture_history_backfill.json": "110e7e6b78283492d3cbae84dded30bc68387be32e0ad4c79ea8fb4637ef3f8c",
|
||||
".modelhub_state/market_intelligence.json": "1d6cb678ffd70834a8d4f05be63b1f446bd9b70866c3e6e003b53a620de7596c",
|
||||
".modelhub_state/official_capabilities.json": "480b6cb4d2cb81e36955a7ea2fb5f65cabf24c5fa95822d4dfa3298dfb9f5560",
|
||||
".modelhub_state/outcome_checkpoint.json": "03f8730187daa96b7153c325a77c15cd5f8e335e65f0bc4e00ed1207576423a9",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "d4d81fcacbd4471d7e9b7bc6519bcd085059120cab20c1e42c5c106247cb1019",
|
||||
".modelhub_state/architecture_history_backfill.json": "938c3165dfccd733be03f3161d0be4a74adb46ef2f4c9619f0540d7c56fe8575",
|
||||
".modelhub_state/market_intelligence.json": "e4d126c09d316352a1d6fae1ee1978202d569baf872f94742ed5bbdbde62601b",
|
||||
".modelhub_state/official_capabilities.json": "b70cdaafaa648abc7873492973d849482a32d327ff72dbf4c41217b75f21c6dc",
|
||||
".modelhub_state/outcome_checkpoint.json": "53b9391fe99f83fec9adac21fb606a509946ca58662f444dd48636c43a952a46",
|
||||
".modelhub_state/queue_cleanup_latest.json": "0ca25e7a552999a61b0e5c18fc5c08134dd7fe9caf89eaa601a60afcccac2b45",
|
||||
".modelhub_state/recent_outcomes.jsonl": "9a12f770ad59aa29b4229f185f956a8a46289e3d3588d3aabcf33a1498b1bf2a",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "2e98a4ac4e6107bc08f6b0ed7eea24116fea4bc9ce1dc39f793e5efdc858df58",
|
||||
".modelhub_state/recovery_intents.jsonl": "eb623fe4131094ec8387d55a7b9ca94fe6066c19f5dc5d80b7acc00cdcaa0a6d",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "07c0166f4b1f2af3fb68212a15aa5b032435142ecf30972afa3331c975dcff6b",
|
||||
".modelhub_state/recovery_intents.jsonl": "18cbb0f27a6f831768598b22da61bd2473148924cd14990c88e0e33055cb9765",
|
||||
".modelhub_state/routing_intelligence.json": "f57ee2e18ed0ace5dc075009569f92659c48337959476d9eab19e2dfed2e4296",
|
||||
".modelhub_state/submission_exclusions.jsonl": "75ddc8b4d313a8cecec2f373afc57298143d78e0eb907ca44f420d7bf9c55263",
|
||||
".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
|
||||
"ledger/submissions.jsonl": "4139e1fffdbeaf8b047b83f95810a3dcfa1c69a732ed04126a45fb3fa7b951b9",
|
||||
"outcomes/submissions.jsonl": "68a695df38a9ef7b51df5600d2270817bc59e42f71aeaed95aa75c18242012af"
|
||||
"outcomes/submissions.jsonl": "67c2d83dbf8984feb307c9191b79e1dcddebdb25673a6a101824b1b8224eb444"
|
||||
},
|
||||
"generation": 6982,
|
||||
"generation": 6983,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-14T01:54:35.227913+00:00",
|
||||
"updatedAt": "2026-09-14T01:57:23.726433+00:00",
|
||||
"writerId": "69701e73196b4ac2b3fad0f412335168"
|
||||
}
|
||||
|
||||
@@ -63,7 +63,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:05:43.096396+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998609696, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020499228, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020499228}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:03:47.678567+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632579", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:32:15.596901+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:29:42.987166+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632974", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T04:28:47.207692+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T20:26:01.012898+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4633732", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T04:35:49.427693+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22109595640, "estimatedRequiredGiB": 24.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22137550529, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 20921584848, "modelscopeTags": ["license:Apache License 2.0", "model_type:gpt_oss", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "mxfp4", "repositoryOnDiskBytes": 22137550529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T20:33:07.760826+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4633843", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T04:35:49.427716+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306305296, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19329225494, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "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": 19329225494}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T20:34:23.419555+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4633876", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-05T04:45:59.433680+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:15"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T20:40:58.592221+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4633953", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T04:49:26.595714+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T20:48:49.542529+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4634053", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user