10 lines
13 KiB
JSON
10 lines
13 KiB
JSON
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "llamacpp", "lastSyncTime": "2026-10-18T17:16:34.981957+00:00", "modelId": "ornith-ai/Ornith-1.0-9B-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-18T17:13:43+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4332412", "taskType": "text-generation", "verifyResult": -1}
|
|
{"agentVersion": "2026.10.18.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "6bc3bbce84627dafe0eb", "lastSyncTime": null, "modelId": "DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22561854096, "estimatedRequiredGiB": 25.221, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 22566975607, "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": 22566975607, "quantizationMethod": null, "recursiveRepositoryBytes": 22566975607, "repositoryOnDiskBytes": 22566975607}, "outcome": "pending", "status": "pending", "strategyId": "7844045f-5918-4d03-9e5a-3a3bba4e8444", "submitTime": "2026-10-18T19:21:11.744535+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633238", "taskType": "text-generation", "verifyResult": null}
|
|
{"agentVersion": "2026.10.18.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "6bc3bbce84627dafe0eb", "lastSyncTime": null, "modelId": "jiaheng0815/feng-30m", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 117730088, "estimatedRequiredGiB": 0.151, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "published_repository_upper_bound", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 135137246, "modelscopeLicense": "apache-2.0", "modelscopeParams": 29429184, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:esp32", "custom_tag:edge-ai", "custom_tag:tiny-llm", "custom_tag:on-device", "custom_tag:embedded", "custom_tag:chinese", "custom_tag:qwen3"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 135137246, "quantizationMethod": null, "recursiveRepositoryBytes": 135071151, "repositoryOnDiskBytes": 135137246}, "outcome": "pending", "status": "pending", "strategyId": "7844045f-5918-4d03-9e5a-3a3bba4e8444", "submitTime": "2026-10-18T19:21:12.462122+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633240", "taskType": "text-generation", "verifyResult": null}
|
|
{"agentVersion": "2026.10.18.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "6bc3bbce84627dafe0eb", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19310950017, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 19310950017, "quantizationMethod": null, "recursiveRepositoryBytes": 19310950017, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "pending", "strategyId": "7844045f-5918-4d03-9e5a-3a3bba4e8444", "submitTime": "2026-10-18T19:21:11.754579+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633237", "taskType": "text-generation", "verifyResult": null}
|
|
{"agentVersion": "2026.10.18.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "6bc3bbce84627dafe0eb", "lastSyncTime": null, "modelId": "BananaMind/Picolo-BananaMind", "modelProfile": {"architectures": ["PicoloForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 912, "estimatedRequiredGiB": 0.001, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "picolo", "modelscopeFileSize": 638936, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:picolo", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:custom_code", "custom_tag:transformer", "custom_tag:tiny", "custom_tag:bananamind", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 638936, "quantizationMethod": null, "recursiveRepositoryBytes": 638936, "repositoryOnDiskBytes": 638936}, "outcome": "pending", "status": "pending", "strategyId": "7844045f-5918-4d03-9e5a-3a3bba4e8444", "submitTime": "2026-10-18T19:21:11.742991+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633234", "taskType": "text-generation", "verifyResult": null}
|
|
{"agentVersion": "2026.10.18.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "6bc3bbce84627dafe0eb", "lastSyncTime": null, "modelId": "GestaltLabs/LFM2.5-24B-A2B-NVFP4-W4A16", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14953580360, "estimatedRequiredGiB": 16.736, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 14975129078, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:fp4", "custom_tag:modelopt", "custom_tag:quantized", "custom_tag:w4a16", "custom_tag:fp8-kv", "custom_tag:moe", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:blackwell", "custom_tag:sglang", "custom_tag:reasoning", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 14975129078, "quantizationMethod": "modelopt", "recursiveRepositoryBytes": 14975129078, "repositoryOnDiskBytes": 14975129078}, "outcome": "pending", "status": "pending", "strategyId": "7844045f-5918-4d03-9e5a-3a3bba4e8444", "submitTime": "2026-10-18T19:21:12.662465+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633239", "taskType": "text-generation", "verifyResult": null}
|
|
{"agentVersion": "2026.10.18.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "6bc3bbce84627dafe0eb", "lastSyncTime": null, "modelId": "r0b0tlab/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-EXL3-2.08bpw", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20065950490, "estimatedRequiredGiB": 22.5, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20133005090, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:moe", "custom_tag:nemotron"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20133005090, "quantizationMethod": "exl3", "recursiveRepositoryBytes": 20133005090, "repositoryOnDiskBytes": 20133005090}, "outcome": "pending", "status": "pending", "strategyId": "7844045f-5918-4d03-9e5a-3a3bba4e8444", "submitTime": "2026-10-18T19:21:11.745740+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633236", "taskType": "text-generation", "verifyResult": null}
|
|
{"agentVersion": "2026.10.18.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "6bc3bbce84627dafe0eb", "lastSyncTime": null, "modelId": "IFM/Jais-3-3.7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6342166448, "estimatedRequiredGiB": 7.112, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6363495357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5058255360, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:3.7B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 6363495357, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 6363495357, "repositoryOnDiskBytes": 6363495357}, "outcome": "pending", "status": "pending", "strategyId": "7844045f-5918-4d03-9e5a-3a3bba4e8444", "submitTime": "2026-10-18T19:21:11.757914+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633235", "taskType": "text-generation", "verifyResult": null}
|
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-10-18T20:19:16.456402+00:00", "modelId": "ornith-ai/Ornith-1.0-9B-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-18T20:15:43+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4353479", "taskType": "text-generation", "verifyResult": -1}
|