state: generation 32076 (cycle)

This commit is contained in:
CoolBoy committed 2026-11-14 02:50:26 +00:00
1 parent b25b2bc1d5
commit 2ac69e4b73
7 files changed
+869 -869

No files matched your search

+7 -7
View File
@@ -377,7 +377,7 @@
{"framework": null, "lastOutcomeReconcileAt": "2026-11-14T02:16:50.341083+00:00", "lastSyncTime": "2026-11-14T02:16:53.248056+00:00", "modelId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "5699676", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:55:01.760458+00:00", "lastSyncTime": "2026-11-13T21:55:04.664250+00:00", "modelId": "cyankiwi/Jan-v1-4B-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5698916", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T23:18:33.059014+00:00", "lastSyncTime": "2026-11-13T23:18:36.154111+00:00", "modelId": "cyankiwi/Trinity-Mini-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697424", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882891+00:00", "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5694815", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-14T02:50:06.231800+00:00", "lastSyncTime": "2026-11-14T02:50:08.550497+00:00", "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5694815", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-14T00:05:09.414693+00:00", "lastSyncTime": "2026-11-14T00:05:12.179121+00:00", "modelId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "5691062", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T23:51:46.910814+00:00", "lastSyncTime": "2026-11-13T23:51:50.056651+00:00", "modelId": "hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5645467", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T20:52:29.590242+00:00", "lastSyncTime": "2026-11-13T20:52:32.365853+00:00", "modelId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5572093", "taskType": "text-generation", "verifyResult": null}
@@ -580,7 +580,7 @@
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:54:19.911839+00:00", "lastSyncTime": "2026-11-13T22:54:22.952526+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5716393", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:45:41.188711+00:00", "lastSyncTime": "2026-11-13T22:45:43.455784+00:00", "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5716024", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:15:44.996059+00:00", "lastSyncTime": "2026-11-13T22:15:47.457718+00:00", "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5701875", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882898+00:00", "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697435", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-14T02:50:06.231800+00:00", "lastSyncTime": "2026-11-14T02:50:08.550504+00:00", "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697435", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:58:03.285283+00:00", "lastSyncTime": "2026-11-13T22:58:06.152697+00:00", "modelId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697423", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:17:01.552484+00:00", "lastSyncTime": "2026-11-13T21:17:04.657375+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5688915", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T19:33:02.140259+00:00", "lastSyncTime": "2026-11-13T19:33:05.529108+00:00", "modelId": "OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5687537", "taskType": "text-generation", "verifyResult": null}
@@ -946,12 +946,12 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455253+00:00", "modelId": "cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038369021, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038369021, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038369021, "repositoryOnDiskBytes": 29038369021}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T10:49:59.501022+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5844817", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:22:45.636663+00:00", "lastSyncTime": "2026-11-13T20:22:48.274512+00:00", "modelId": "XHToken/Spark-X2.6-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1d153f006310de4a64f8c5ec9c0a4875a6af2dfc403b09509ed2b227a47b4002", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820113440, "estimatedRequiredGiB": 7.834, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7010046444, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7010046444, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7010046444, "repositoryOnDiskBytes": 7010046444}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T13:34:09.462874+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5847555", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:22:45.636663+00:00", "lastSyncTime": "2026-11-13T20:22:48.274477+00:00", "modelId": "XHToken/Spark-X2.6-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "ee7d3f741e15635edb6a7aaff8a36f09b08e64fc64c26a9e83971ebf3d3ac190", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820113440, "estimatedRequiredGiB": 7.834, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7010046444, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7010046444, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7010046444, "repositoryOnDiskBytes": 7010046444}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T13:49:57.249364+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5847754", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882876+00:00", "modelId": "Haodong07/Qwen3-14B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12610178368, "estimatedRequiredGiB": 14.106, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10550492288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 12621681247, "repositoryOnDiskBytes": 12621681247}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:05:45.083117+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5847970", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-14T02:50:06.231800+00:00", "lastSyncTime": "2026-11-14T02:50:08.550482+00:00", "modelId": "Haodong07/Qwen3-14B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12610178368, "estimatedRequiredGiB": 14.106, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10550492288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 12621681247, "repositoryOnDiskBytes": 12621681247}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:05:45.083117+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5847970", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882913+00:00", "modelId": "Haodong07/Qwen3-8B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7490808664, "estimatedRequiredGiB": 8.384, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 7502305637, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5970162816, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7502305637, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7502305637, "repositoryOnDiskBytes": 7502305637}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:05:45.084902+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5847969", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882868+00:00", "modelId": "Haodong07/Llama-3.1-8B-Instruct-TwinQuant-W4A4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7150927928, "estimatedRequiredGiB": 8.011, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "llama3.1", "modelscopeParams": 5823795328, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "task:text-generation", "custom_tag:llama", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7168201505, "repositoryOnDiskBytes": 7168201505}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:21:39.090816+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5848463", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882884+00:00", "modelId": "Haodong07/Qwen3-14B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12610178368, "estimatedRequiredGiB": 14.106, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10550492288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 12621681247, "repositoryOnDiskBytes": 12621681247}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:21:39.092587+00:00", "targetGpu": "Vastai_va16", "taskId": "5848462", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-14T02:50:06.231800+00:00", "lastSyncTime": "2026-11-14T02:50:08.550466+00:00", "modelId": "Haodong07/Llama-3.1-8B-Instruct-TwinQuant-W4A4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7150927928, "estimatedRequiredGiB": 8.011, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "llama3.1", "modelscopeParams": 5823795328, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "task:text-generation", "custom_tag:llama", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7168201505, "repositoryOnDiskBytes": 7168201505}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:21:39.090816+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5848463", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-14T02:50:06.231800+00:00", "lastSyncTime": "2026-11-14T02:50:08.550490+00:00", "modelId": "Haodong07/Qwen3-14B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12610178368, "estimatedRequiredGiB": 14.106, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10550492288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 12621681247, "repositoryOnDiskBytes": 12621681247}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:21:39.092587+00:00", "targetGpu": "Vastai_va16", "taskId": "5848462", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882906+00:00", "modelId": "Haodong07/Qwen3-8B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7490808664, "estimatedRequiredGiB": 8.384, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 7502305637, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5970162816, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7502305637, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7502305637, "repositoryOnDiskBytes": 7502305637}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:21:39.081188+00:00", "targetGpu": "Vastai_va16", "taskId": "5848461", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882848+00:00", "modelId": "Haodong07/Llama-3.1-8B-Instruct-TwinQuant-W4A4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7150927928, "estimatedRequiredGiB": 8.011, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "llama3.1", "modelscopeParams": 5823795328, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "task:text-generation", "custom_tag:llama", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7168201505, "repositoryOnDiskBytes": 7168201505}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:37:27.556834+00:00", "targetGpu": "Vastai_va16", "taskId": "5848878", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-14T02:50:06.231800+00:00", "lastSyncTime": "2026-11-14T02:50:08.550475+00:00", "modelId": "Haodong07/Llama-3.1-8B-Instruct-TwinQuant-W4A4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7150927928, "estimatedRequiredGiB": 8.011, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "llama3.1", "modelscopeParams": 5823795328, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "task:text-generation", "custom_tag:llama", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7168201505, "repositoryOnDiskBytes": 7168201505}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:37:27.556834+00:00", "targetGpu": "Vastai_va16", "taskId": "5848878", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T21:58:46.915729+00:00", "lastSyncTime": "2026-11-13T21:58:49.760785+00:00", "modelId": "cyankiwi/KAT-V1-40B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883677, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883677, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883677, "repositoryOnDiskBytes": 23398883677}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:53:18.503287+00:00", "targetGpu": "Vastai_va16", "taskId": "5849746", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T21:58:46.915729+00:00", "lastSyncTime": "2026-11-13T21:58:49.760795+00:00", "modelId": "cyankiwi/KAT-V1-40B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883677, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883677, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883677, "repositoryOnDiskBytes": 23398883677}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T15:33:50.799119+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5850377", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-14T02:16:50.341083+00:00", "lastSyncTime": "2026-11-14T02:16:53.248062+00:00", "modelId": "AtomicChat/gemma-4-E2B-it-assistant-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "40dcc0aedc42018347616f1d86a660896e0a6c687386f177ae81a2b5bf197a7e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 97817696, "estimatedRequiredGiB": 0.558, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 499499907, "modelscopeLicense": "apache-2.0", "modelscopeParams": 77207300, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:atomic-chat", "custom_tag:gemma", "custom_tag:gemma4", "custom_tag:google", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 499499907, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 499499907, "repositoryOnDiskBytes": 499499907}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T17:29:23.456146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5852178", "taskType": "text-generation", "verifyResult": null}
@@ -1067,7 +1067,7 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:01:17.208396+00:00", "lastSyncTime": "2026-11-13T20:01:19.878939+00:00", "modelId": "RedHatAI/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65827374264, "estimatedRequiredGiB": 73.588, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 65845709151, "modelscopeLicense": "other", "modelscopeParams": 32913266240, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 65845709151, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 65845709151, "repositoryOnDiskBytes": 65845709151}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:46:28.352131+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6164872", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-14T02:28:46.910755+00:00", "lastSyncTime": "2026-11-14T02:28:49.358300+00:00", "modelId": "DavidAU/ERNIE-4.5-37B-A3B-Thinking-Brainstorm20x", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 74371252464, "estimatedRequiredGiB": 83.131, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 74384704412, "modelscopeLicense": "apache-2.0", "modelscopeParams": 37185044864, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:programming", "custom_tag:code generation", "custom_tag:code", "custom_tag:coding", "custom_tag:coder", "custom_tag:chat", "custom_tag:brainstorm 20x", "custom_tag:creative", "custom_tag:all uses cases", "custom_tag:benchmarks", "custom_tag:128k context", "custom_tag:creative writing", "custom_tag:fiction", "custom_tag:finetune", "custom_tag:thinking", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 74384704412, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 74384704412, "repositoryOnDiskBytes": 74384704412}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:46:28.353539+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6164871", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-14T02:41:20.446896+00:00", "lastSyncTime": "2026-11-14T02:41:23.350831+00:00", "modelId": "DavidAU/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-III", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 84743899928, "estimatedRequiredGiB": 94.728, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 84761107200, "modelscopeLicense": "apache-2.0", "modelscopeParams": 42370321152, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:programming", "custom_tag:code generation", "custom_tag:code", "custom_tag:codeqwen", "custom_tag:moe", "custom_tag:coding", "custom_tag:coder", "custom_tag:qwen2", "custom_tag:chat", "custom_tag:qwen", "custom_tag:qwen-coder", "custom_tag:Qwen3-Coder-30B-A3B-Instruct", "custom_tag:Qwen3-30B-A3B", "custom_tag:mixture of experts", "custom_tag:128 experts", "custom_tag:8 active experts", "custom_tag:1 million context", "custom_tag:qwen3", "custom_tag:finetune", "custom_tag:brainstorm 20x", "custom_tag:brainstorm", "custom_tag:optional thinking", "custom_tag:qwen3_moe", "custom_tag:unsloth"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 84761107200, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 84761107200, "repositoryOnDiskBytes": 84761107200}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:46:28.350368+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6164868", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:22:39.566339+00:00", "lastSyncTime": "2026-11-13T18:22:42.569273+00:00", "modelId": "Gryphe/Gemma-4-31B-StyleTune", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65364910736, "estimatedRequiredGiB": 73.088, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 65398028234, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32682375020, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:gemma4", "custom_tag:conversational", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:roleplay", "custom_tag:creative-writing", "custom_tag:style-tune"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 65398028234, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 65398028234, "repositoryOnDiskBytes": 65398028234}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:59:03.495827+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6165089", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-14T02:50:06.231800+00:00", "lastSyncTime": "2026-11-14T02:50:08.550443+00:00", "modelId": "Gryphe/Gemma-4-31B-StyleTune", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65364910736, "estimatedRequiredGiB": 73.088, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 65398028234, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32682375020, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:gemma4", "custom_tag:conversational", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:roleplay", "custom_tag:creative-writing", "custom_tag:style-tune"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 65398028234, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 65398028234, "repositoryOnDiskBytes": 65398028234}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:59:03.495827+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6165089", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-14T02:16:50.341083+00:00", "lastSyncTime": "2026-11-14T02:16:53.248030+00:00", "modelId": "AtomicChat/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9db497a9b0994b19d766a4f358090ea4120d3ef03c5344dd599fb0d095c0d944", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8031245312, "estimatedRequiredGiB": 39.623, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 35453857167, "modelscopeLicense": "other", "modelscopeParams": 7518069290, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:atomic-dynamic", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:nvidia", "custom_tag:gemma4", "custom_tag:imatrix", "custom_tag:quantized", "custom_tag:conversational", "custom_tag:atomic-chat", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 35453857167, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 35453857167, "repositoryOnDiskBytes": 35453857167}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:22:10.820730+00:00", "targetGpu": "hygon_k100-ai", "taskId": "6165396", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-14T01:42:35.832984+00:00", "lastSyncTime": "2026-11-14T01:42:39.283956+00:00", "modelId": "security-serch/Sec-sft-AT-4B", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8822894448, "estimatedRequiredGiB": 9.878, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8838816961, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:reinforcement-learning"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8838816961, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 8838816961, "repositoryOnDiskBytes": 8838816961}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:31:20.406937+00:00", "targetGpu": "Ascend_910-b4", "taskId": "6165528", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455325+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-8bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10634065360, "estimatedRequiredGiB": 11.89, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 10639191747, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 10639191747, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f3ec6d4095e60bda", "recursiveRepositoryBytes": 10639191747, "repositoryOnDiskBytes": 10639191747}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:39:10.635643+00:00", "targetGpu": "MetaX_c-500", "taskId": "6165649", "taskType": "text-generation", "verifyResult": null}