state: generation 31953 (cycle)
This commit is contained in:
1 parent
488d352ef1
commit
6d2163dcc2
7 files changed
+1068
-1068
No files matched your search
@@ -43,7 +43,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T17:58:50.656439+00:00", "lastSyncTime": "2026-11-13T17:58:53.562510+00:00", "modelId": "ConwayResearch/Underdog-Woof-4B-1.1", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Biren_166m", "taskId": "5374321", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T20:18:54.749701+00:00", "lastSyncTime": "2026-11-13T20:18:57.281898+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Iluvatar_bi-150", "taskId": "5371644", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:53:44.579925+00:00", "lastSyncTime": "2026-11-13T15:53:47.653043+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Iluvatar_bi-150", "taskId": "5363028", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:23:37.688192+00:00", "lastSyncTime": "2026-11-13T15:23:39.976581+00:00", "modelId": "ibm-granite/granite-4.2-30b", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5361267", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T23:56:19.908317+00:00", "lastSyncTime": "2026-11-13T23:56:22.872764+00:00", "modelId": "ibm-granite/granite-4.2-30b", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5361267", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T16:31:48.672809+00:00", "lastSyncTime": "2026-11-13T16:31:51.870567+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5360514", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:53:44.579925+00:00", "lastSyncTime": "2026-11-13T15:53:47.653049+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5359099", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:53:44.579925+00:00", "lastSyncTime": "2026-11-13T15:53:47.653054+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5358695", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -788,7 +788,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:29:28.010794+00:00", "lastSyncTime": "2026-11-13T21:29:31.178099+00:00", "modelId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5699620", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T23:02:21.853187+00:00", "lastSyncTime": "2026-11-13T23:02:24.563038+00:00", "modelId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5699606", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:50:07.339106+00:00", "lastSyncTime": "2026-11-13T21:50:09.963283+00:00", "modelId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697881", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:28:12.719174+00:00", "lastSyncTime": "2026-11-13T15:28:15.451109+00:00", "modelId": "iluvatar-corex/Qwen3-8B-W8A8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5692570", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T23:56:19.908317+00:00", "lastSyncTime": "2026-11-13T23:56:22.872825+00:00", "modelId": "iluvatar-corex/Qwen3-8B-W8A8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5692570", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T16:44:47.682303+00:00", "lastSyncTime": "2026-11-13T16:44:50.457672+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5691022", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:17:01.552484+00:00", "lastSyncTime": "2026-11-13T21:17:04.657320+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5688937", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T20:14:05.144346+00:00", "lastSyncTime": "2026-11-13T20:14:07.728090+00:00", "modelId": "StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5676921", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -856,7 +856,7 @@
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T21:00:41.735309+00:00", "lastSyncTime": "2026-11-13T21:00:44.850347+00:00", "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 19.185, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 17166416942, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17166416942, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b0b0c9a002005922", "recursiveRepositoryBytes": 17166416942, "repositoryOnDiskBytes": 17166416942}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.256695+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824148", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T21:55:01.760458+00:00", "lastSyncTime": "2026-11-13T21:55:04.664267+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077977948, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 11077977948, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:abf2795564ed82d1", "recursiveRepositoryBytes": 11077977948, "repositoryOnDiskBytes": 11077977948}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.252703+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824152", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T21:09:15.846823+00:00", "lastSyncTime": "2026-11-13T21:09:18.669780+00:00", "modelId": "cpatonn-mirror/LFM2-8B-A1B-AWQ-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9682515680, "estimatedRequiredGiB": 10.827, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 9688084066, "modelscopeLicense": "other", "modelscopeParams": 8474148288, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9688084066, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:0662089ef0756354", "recursiveRepositoryBytes": 9688084066, "repositoryOnDiskBytes": 9688084066}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.254577+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824151", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T15:28:12.719174+00:00", "lastSyncTime": "2026-11-13T15:28:15.451080+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593025749, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17593025749, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 17593025749, "repositoryOnDiskBytes": 17593025749}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.285428+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824153", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T23:56:19.908317+00:00", "lastSyncTime": "2026-11-13T23:56:22.872785+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593025749, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17593025749, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 17593025749, "repositoryOnDiskBytes": 17593025749}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.285428+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824153", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T22:49:58.050740+00:00", "lastSyncTime": "2026-11-13T22:50:02.260759+00:00", "modelId": "cyankiwi/Nemotron-Orchestrator-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921104, "estimatedRequiredGiB": 11.048, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9885904129, "modelscopeLicense": null, "modelscopeParams": 8190735360, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9885904129, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b478ca1d5cf05e4", "recursiveRepositoryBytes": 9885904129, "repositoryOnDiskBytes": 9885904129}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.382051+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824159", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T21:55:01.760458+00:00", "lastSyncTime": "2026-11-13T21:55:04.664274+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145039537, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8145039537, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:06e1b44940b82d27", "recursiveRepositoryBytes": 8145039537, "repositoryOnDiskBytes": 8145039537}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.350896+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824155", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T17:01:21.312892+00:00", "lastSyncTime": "2026-11-13T17:01:24.361437+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22070410112, "estimatedRequiredGiB": 24.69, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22091795362, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977388, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22091795362, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5179e7fa01f5b826", "recursiveRepositoryBytes": 22091795362, "repositoryOnDiskBytes": 22091795362}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.295226+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824166", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -900,7 +900,7 @@
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T20:56:17.901749+00:00", "lastSyncTime": "2026-11-13T20:56:20.553949+00:00", "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10544400664, "estimatedRequiredGiB": 11.802, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 10560388030, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 10560388030, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b91e1843aeaeb7f4", "recursiveRepositoryBytes": 10560388030, "repositoryOnDiskBytes": 10560388030}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T13:23:26.578428+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826876", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T23:22:52.221293+00:00", "lastSyncTime": "2026-11-13T23:22:55.053929+00:00", "modelId": "cyankiwi/granite-4.0-h-tiny-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5504236472, "estimatedRequiredGiB": 6.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 5514064765, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7093177920, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5514064765, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b7e650901445ae6", "recursiveRepositoryBytes": 5514064765, "repositoryOnDiskBytes": 5514064765}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T13:23:35.140603+00:00", "targetGpu": "Vastai_va16", "taskId": "5826891", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T21:09:15.846823+00:00", "lastSyncTime": "2026-11-13T21:09:18.669813+00:00", "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "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": 29038368655, "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": 29038368655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038368655, "repositoryOnDiskBytes": 29038368655}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T14:06:48.823038+00:00", "targetGpu": "MetaX_c-500", "taskId": "5827510", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T15:28:12.719174+00:00", "lastSyncTime": "2026-11-13T15:28:15.451087+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593025749, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17593025749, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 17593025749, "repositoryOnDiskBytes": 17593025749}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T14:36:37.144718+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5827949", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T23:56:19.908317+00:00", "lastSyncTime": "2026-11-13T23:56:22.872795+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593025749, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17593025749, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 17593025749, "repositoryOnDiskBytes": 17593025749}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T14:36:37.144718+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5827949", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T21:00:41.735309+00:00", "lastSyncTime": "2026-11-13T21:00:44.850372+00:00", "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 19.185, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 17166416942, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17166416942, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b0b0c9a002005922", "recursiveRepositoryBytes": 17166416942, "repositoryOnDiskBytes": 17166416942}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T14:38:24.903632+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5827982", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455333+00:00", "modelId": "cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 80093556736, "estimatedRequiredGiB": 89.546, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 80124470126, "modelscopeLicense": "other", "modelscopeParams": 139149203788, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minimax", "custom_tag:MOE", "custom_tag:pruning", "custom_tag:compression"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 80124470126, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:4fbcad1e55b4a8ec", "recursiveRepositoryBytes": 80124470126, "repositoryOnDiskBytes": 80124470126}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T14:41:34.908600+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5828032", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T23:14:49.328006+00:00", "lastSyncTime": "2026-11-13T23:14:52.246545+00:00", "modelId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115852073, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115852073, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2f008ff356aba06a", "recursiveRepositoryBytes": 18115852073, "repositoryOnDiskBytes": 18115852073}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T15:48:43.873629+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5828882", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -926,7 +926,7 @@
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T16:48:49.737870+00:00", "lastSyncTime": "2026-11-13T16:48:52.429008+00:00", "modelId": "ornith-ai/Ornith-1.5-122B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 77627904940, "estimatedRequiredGiB": 86.798, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 77665409734, "modelscopeLicense": "mit", "modelscopeParams": 66496526576, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 77665409734, "quantizationMethod": "modelopt", "quantizationSignature": "modelopt:d57a22327d8e981b", "recursiveRepositoryBytes": 77665409734, "repositoryOnDiskBytes": 77665409734}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T21:16:15.179849+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5833277", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T22:03:10.739314+00:00", "lastSyncTime": "2026-11-13T22:03:13.774197+00:00", "modelId": "cyankiwi/Kimi-Dev-72B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 79588295928, "estimatedRequiredGiB": 88.967, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 79606716979, "modelscopeLicense": "mit", "modelscopeParams": 72706203648, "modelscopeTags": ["license:mit", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code", "custom_tag:swebench", "custom_tag:software", "custom_tag:issue-resolving"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 79606716979, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:08953c0a152f288b", "recursiveRepositoryBytes": 79606716979, "repositoryOnDiskBytes": 79606716979}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T21:37:45.569641+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5833505", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T21:00:41.735309+00:00", "lastSyncTime": "2026-11-13T21:00:44.850381+00:00", "modelId": "cpatonn-mirror/Hermes-4-70B-AWQ-4bit", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709261480, "estimatedRequiredGiB": 47.751, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42726705025, "modelscopeLicense": "llama3", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Llama-3.1", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 42726705025, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:35574ab300879f51", "recursiveRepositoryBytes": 42726705025, "repositoryOnDiskBytes": 42726705025}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T22:00:05.384600+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5833839", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T15:28:12.719174+00:00", "lastSyncTime": "2026-11-13T15:28:15.451103+00:00", "modelId": "iluvatar-corex/Qwen3-14B-W8A8", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16332993224, "estimatedRequiredGiB": 18.271, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16348969354, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16348969354, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f1c25abf7aa3a14c", "recursiveRepositoryBytes": 16348969354, "repositoryOnDiskBytes": 16348969354}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T23:39:13.353718+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5835147", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T23:56:19.908317+00:00", "lastSyncTime": "2026-11-13T23:56:22.872812+00:00", "modelId": "iluvatar-corex/Qwen3-14B-W8A8", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16332993224, "estimatedRequiredGiB": 18.271, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16348969354, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16348969354, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f1c25abf7aa3a14c", "recursiveRepositoryBytes": 16348969354, "repositoryOnDiskBytes": 16348969354}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T23:39:13.353718+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5835147", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T23:14:49.328006+00:00", "lastSyncTime": "2026-11-13T23:14:52.246565+00:00", "modelId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064355224, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064355224, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:a1e46deb2f53e69c", "recursiveRepositoryBytes": 33064355224, "repositoryOnDiskBytes": 33064355224}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T23:40:38.428117+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5835156", "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": "2026-11-13T21:58:49.760805+00:00", "modelId": "cyankiwi/Kimi-Dev-72B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44481971344, "estimatedRequiredGiB": 49.733, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 44500391843, "modelscopeLicense": "mit", "modelscopeParams": 72706203648, "modelscopeTags": ["license:mit", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code", "custom_tag:swebench", "custom_tag:software", "custom_tag:issue-resolving"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 44500391843, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:25822ca12e839e41", "recursiveRepositoryBytes": 44500391843, "repositoryOnDiskBytes": 44500391843}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T23:41:08.929556+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5835161", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T21:13:09.673686+00:00", "lastSyncTime": "2026-11-13T21:13:12.083456+00:00", "modelId": "cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "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": 18115830036, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115830036, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2f008ff356aba06a", "recursiveRepositoryBytes": 18115830036, "repositoryOnDiskBytes": 18115830036}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T00:05:20.460078+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5835394", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -979,7 +979,7 @@
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:14:05.144346+00:00", "lastSyncTime": "2026-11-13T20:14:07.728069+00:00", "modelId": "StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "modelProfile": {"architectures": ["GatedDeltaNetForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5729353240, "estimatedRequiredGiB": 6.407, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gated_deltanet", "modelscopeFileSize": 5732907231, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:gated_deltanet", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:fla", "custom_tag:gated-deltanet", "custom_tag:hybrid-linear-attention", "custom_tag:linear-attention", "custom_tag:massive-activations", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5732907231, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 5732907231, "repositoryOnDiskBytes": 5732907231}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-29T21:44:11.733863+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5897650", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T23:39:14.609451+00:00", "lastSyncTime": "2026-11-13T23:39:17.957347+00:00", "modelId": "groxaxo/Qwen3.5-4B-Tmux-Pocket-Mini-AutoRound-AWQ-W4A16", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3127680424, "estimatedRequiredGiB": 3.518, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 3147776572, "modelscopeLicense": "apache-2.0", "modelscopeParams": 838985568, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen3.5", "custom_tag:text-only", "custom_tag:awq", "custom_tag:auto-round", "custom_tag:4-bit", "custom_tag:tmux-pocket"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3147776572, "quantizationMethod": "awq", "quantizationSignature": "awq:c96b7e02d0a02d5e", "recursiveRepositoryBytes": 3147776572, "repositoryOnDiskBytes": 3147776572}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T07:54:23.473189+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5905150", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T19:49:14.889343+00:00", "lastSyncTime": "2026-11-13T19:49:17.262220+00:00", "modelId": "RWKV/RWKV7-G1k-1.5B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055417000, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057516623, "modelscopeLicense": "apache-2.0", "modelscopeParams": 134217728, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3057516623, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 3057516623, "repositoryOnDiskBytes": 3057516623}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T11:50:40.946937+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5908957", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T15:28:12.719174+00:00", "lastSyncTime": "2026-11-13T15:28:15.451095+00:00", "modelId": "iluvatar-corex/Qwen3-14B-W8A8", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16332993224, "estimatedRequiredGiB": 18.271, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16348969354, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16348969354, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f1c25abf7aa3a14c", "recursiveRepositoryBytes": 16348969354, "repositoryOnDiskBytes": 16348969354}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T12:01:32.656336+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5909135", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T23:56:19.908317+00:00", "lastSyncTime": "2026-11-13T23:56:22.872803+00:00", "modelId": "iluvatar-corex/Qwen3-14B-W8A8", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16332993224, "estimatedRequiredGiB": 18.271, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16348969354, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16348969354, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f1c25abf7aa3a14c", "recursiveRepositoryBytes": 16348969354, "repositoryOnDiskBytes": 16348969354}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T12:01:32.656336+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5909135", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T19:28:10.755104+00:00", "lastSyncTime": "2026-11-13T19:28:14.240729+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24533499859, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 24533499859, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T12:58:36.603957+00:00", "targetGpu": "Vastai_va16", "taskId": "5909782", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:54:09.805842+00:00", "lastSyncTime": "2026-11-13T18:54:12.669019+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275791556, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23275791556, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:ab6d01fdc995a6aa", "recursiveRepositoryBytes": 23275791556, "repositoryOnDiskBytes": 23275791556}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T13:36:23.229802+00:00", "targetGpu": "Vastai_va16", "taskId": "5910254", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:08:03.450057+00:00", "lastSyncTime": "2026-11-13T18:08:05.667838+00:00", "modelId": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16680151504, "estimatedRequiredGiB": 18.647, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16685193382, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:finetune", "custom_tag:unsloth", "custom_tag:mixture of experts", "custom_tag:sparse moe", "custom_tag:moe", "custom_tag:heretic", "custom_tag:uncensored", "custom_tag:aliterated", "custom_tag:all use cases", "custom_tag:coder", "custom_tag:creative", "custom_tag:creative writing", "custom_tag:fiction writing", "custom_tag:plot generation", "custom_tag:sub-plot generation", "custom_tag:story generation", "custom_tag:scene continue", "custom_tag:storytelling", "custom_tag:fiction story", "custom_tag:science fiction", "custom_tag:romance", "custom_tag:all genres", "custom_tag:story", "custom_tag:writing", "custom_tag:vivid prosing", "custom_tag:vivid writing", "custom_tag:fiction", "custom_tag:roleplaying", "custom_tag:bfloat16"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16685193382, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 16685193382, "repositoryOnDiskBytes": 16685193382}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T14:32:09.681081+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5911083", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -989,7 +989,7 @@
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T19:20:39.262379+00:00", "lastSyncTime": "2026-11-13T19:20:41.881166+00:00", "modelId": "LiquidAI/LFM3-1.7B", "modelProfile": {"architectures": ["Lfm3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3457635448, "estimatedRequiredGiB": 3.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm3", "modelscopeFileSize": 3476070866, "modelscopeLicense": "other", "modelscopeParams": 1728801536, "modelscopeTags": ["license:other", "model_type:lfm3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm3", "custom_tag:edge", "custom_tag:conversational", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3476070866, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 3476070866, "repositoryOnDiskBytes": 3476070866}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T16:57:08.157003+00:00", "targetGpu": "Vastai_va16", "taskId": "5913633", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T23:35:23.473859+00:00", "lastSyncTime": "2026-11-13T23:35:26.828014+00:00", "modelId": "ggml-org/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0977f3bfd039386242568ad017691544fc8e9646cae8de8e6f0517ae4360c763", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8031245312, "estimatedRequiredGiB": 26.465, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 23680745888, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7518069290, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:quantized", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23680745888, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 23680745888, "repositoryOnDiskBytes": 23680745888}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T18:05:18.524129+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5914537", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T23:35:23.473859+00:00", "lastSyncTime": "2026-11-13T23:35:26.828006+00:00", "modelId": "ggml-org/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9db497a9b0994b19d766a4f358090ea4120d3ef03c5344dd599fb0d095c0d944", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8031245312, "estimatedRequiredGiB": 26.465, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 23680745888, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7518069290, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:quantized", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23680745888, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 23680745888, "repositoryOnDiskBytes": 23680745888}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T18:21:16.942943+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5914807", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T15:28:12.719174+00:00", "lastSyncTime": "2026-11-13T15:28:15.451117+00:00", "modelId": "iluvatar-corex/Qwen3-8B-W8A8", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9441379272, "estimatedRequiredGiB": 10.569, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9457348916, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9457348916, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f1c25abf7aa3a14c", "recursiveRepositoryBytes": 9457348916, "repositoryOnDiskBytes": 9457348916}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T18:42:15.829318+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5915117", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T23:56:19.908317+00:00", "lastSyncTime": "2026-11-13T23:56:22.872819+00:00", "modelId": "iluvatar-corex/Qwen3-8B-W8A8", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9441379272, "estimatedRequiredGiB": 10.569, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9457348916, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9457348916, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f1c25abf7aa3a14c", "recursiveRepositoryBytes": 9457348916, "repositoryOnDiskBytes": 9457348916}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T18:42:15.829318+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5915117", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T17:31:39.850646+00:00", "lastSyncTime": "2026-11-13T17:31:43.081136+00:00", "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5067121544, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18264867356, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 18264867356, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-31T04:10:57.329051+00:00", "targetGpu": "MetaX_c-500", "taskId": "5922110", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T19:44:55.672755+00:00", "lastSyncTime": "2026-11-13T19:44:58.283897+00:00", "modelId": "ProCreations/Dory-Beam-4B", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7950515504, "estimatedRequiredGiB": 8.912, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 7973689504, "modelscopeLicense": "other", "modelscopeParams": 3975229440, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:dory", "custom_tag:looped-transformer", "custom_tag:latent-reasoning", "custom_tag:distillation", "custom_tag:beam", "custom_tag:reasoning", "custom_tag:math"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7973689504, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7973945420, "repositoryOnDiskBytes": 7973945420}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-31T14:00:50.067884+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5929924", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T19:44:55.672755+00:00", "lastSyncTime": "2026-11-13T19:44:58.283903+00:00", "modelId": "ProCreations/Dory-Beam-4B", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7950515504, "estimatedRequiredGiB": 8.912, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 7973945420, "modelscopeLicense": "other", "modelscopeParams": 3975229440, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:dory", "custom_tag:looped-transformer", "custom_tag:latent-reasoning", "custom_tag:distillation", "custom_tag:beam", "custom_tag:reasoning", "custom_tag:math"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7973945420, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7973945420, "repositoryOnDiskBytes": 7973945420}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-31T14:16:38.516559+00:00", "targetGpu": "Vastai_va16", "taskId": "5930089", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in new issue
Block a user