state: generation 31631 (cycle)

This commit is contained in:
CoolBoy committed 2026-11-13 16:11:19 +00:00
1 parent 12e25542ae
commit 6cada404d0
7 files changed
+975 -975

No files matched your search

+8 -8
View File
@@ -566,7 +566,7 @@
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:02:23.522521+00:00", "lastSyncTime": "2026-11-13T15:02:26.064316+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Mthreads_s4000", "taskId": "4492914", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T10:04:21.032143+00:00", "lastSyncTime": "2026-11-13T10:04:23.878331+00:00", "modelId": "GestaltLabs/Ornstein-3.5-9B-V2-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4457975", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:02:23.522521+00:00", "lastSyncTime": "2026-11-13T15:02:26.064282+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4376895", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T07:52:46.055119+00:00", "lastSyncTime": "2026-11-13T07:52:49.355862+00:00", "modelId": "neuralmagic/Meta-Llama-3-70B-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4332409", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T16:10:58.788024+00:00", "lastSyncTime": "2026-11-13T16:11:01.460815+00:00", "modelId": "neuralmagic/Meta-Llama-3-70B-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4332409", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:19:45.556208+00:00", "lastSyncTime": "2026-11-13T15:19:48.729751+00:00", "modelId": "hf/douyamv-Qwen3.8-27B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4332405", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T08:20:17.165461+00:00", "lastSyncTime": "2026-11-13T08:20:21.851080+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4203919", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:32:09.209754+00:00", "lastSyncTime": "2026-11-13T14:32:12.347606+00:00", "modelId": "cyankiwi/Ornith-1.0-35B-AWQ-FP8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4080010", "taskType": "text-generation", "verifyResult": null}
@@ -881,7 +881,7 @@
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T14:32:09.209754+00:00", "lastSyncTime": "2026-11-13T14:32:12.347622+00:00", "modelId": "cyankiwi/Ornith-1.0-35B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24430419208, "estimatedRequiredGiB": 27.35, "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": 24472753002, "modelscopeLicense": "mit", "modelscopeParams": 35107181936, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24472753002, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:cc806b483ebd2e69", "recursiveRepositoryBytes": 24472753002, "repositoryOnDiskBytes": 24472753002}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.147215+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824226", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T12:13:37.522679+00:00", "lastSyncTime": "2026-11-13T12:13:41.375456+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-Intent-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169542243, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31215031088, "modelscopeTags": ["license:apache-2.0", "model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:intent-recognition", "custom_tag:slot-filling", "custom_tag:information-extraction", "custom_tag:schema-guided", "custom_tag:named-entity-recognition", "custom_tag:relation-extraction", "custom_tag:event-extraction"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33169542243, "quantizationMethod": "fp8", "quantizationSignature": "fp8:0da8624bcb5e84df", "recursiveRepositoryBytes": 33169542243, "repositoryOnDiskBytes": 33169542243}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.137559+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824223", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T12:13:37.522679+00:00", "lastSyncTime": "2026-11-13T12:13:41.375449+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-Intent", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62431083040, "estimatedRequiredGiB": 69.776, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 62434092643, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31215031088, "modelscopeTags": ["license:apache-2.0", "model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:intent-recognition", "custom_tag:slot-filling", "custom_tag:information-extraction", "custom_tag:schema-guided", "custom_tag:named-entity-recognition", "custom_tag:relation-extraction", "custom_tag:event-extraction"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 62434092643, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 62434092643, "repositoryOnDiskBytes": 62434092643}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.139261+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824235", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T07:48:43.597512+00:00", "lastSyncTime": "2026-11-13T07:48:47.028288+00:00", "modelId": "nanbeige/Nanbeige4.3-33B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 66238009168, "estimatedRequiredGiB": 74.051, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 66260067498, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 66260067498, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 66260067498, "repositoryOnDiskBytes": 66260067498}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.132903+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824233", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T16:10:58.788024+00:00", "lastSyncTime": "2026-11-13T16:11:01.460777+00:00", "modelId": "nanbeige/Nanbeige4.3-33B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 66238009168, "estimatedRequiredGiB": 74.051, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 66260067498, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 66260067498, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 66260067498, "repositoryOnDiskBytes": 66260067498}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.132903+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824233", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T13:09:32.168012+00:00", "lastSyncTime": "2026-11-13T13:09:35.472797+00:00", "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "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": 33064318294, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064318294, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b74ddfdc145e58ff", "recursiveRepositoryBytes": 33064318294, "repositoryOnDiskBytes": 33064318294}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.135642+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824236", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T13:27:36.824175+00:00", "lastSyncTime": "2026-11-13T13:27:40.172842+00:00", "modelId": "cyankiwi/GLM-4.5-Air-AWQ-4bit", "modelProfile": {"architectures": ["Glm4MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 63400571960, "estimatedRequiredGiB": 70.884, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "glm4_moe", "modelscopeFileSize": 63425670208, "modelscopeLicense": "mit", "modelscopeParams": 106852251264, "modelscopeTags": ["license:mit", "model_type:glm4_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 63425670208, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e5192b47c94517b2", "recursiveRepositoryBytes": 63425670208, "repositoryOnDiskBytes": 63425670208}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.257369+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824227", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T12:52:36.033614+00:00", "lastSyncTime": "2026-11-13T12:52:39.268201+00:00", "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-10-27T10:20:56.145395+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824224", "taskType": "text-generation", "verifyResult": null}
@@ -1001,8 +1001,8 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T09:14:26.846950+00:00", "lastSyncTime": "2026-11-13T09:14:29.867856+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": "2026-11-13T11:25:11.559893+00:00", "lastSyncTime": "2026-11-13T11:25:14.858509+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": "2026-11-13T11:25:11.559893+00:00", "lastSyncTime": "2026-11-13T11:25:14.858503+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}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T07:48:43.597512+00:00", "lastSyncTime": "2026-11-13T07:48:47.028297+00:00", "modelId": "nanbeige/Nanbeige4.3-33B-INT4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22550508296, "estimatedRequiredGiB": 25.227, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22572448107, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22572448107, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:7f52dcb6ef9194b8", "recursiveRepositoryBytes": 22572448107, "repositoryOnDiskBytes": 22572448107}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-31T16:21:41.704856+00:00", "targetGpu": "Vastai_va16", "taskId": "5931916", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T07:48:43.597512+00:00", "lastSyncTime": "2026-11-13T07:48:47.028304+00:00", "modelId": "nanbeige/Nanbeige4.3-33B-INT4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22550508296, "estimatedRequiredGiB": 25.227, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22572448107, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22572448107, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:7f52dcb6ef9194b8", "recursiveRepositoryBytes": 22572448107, "repositoryOnDiskBytes": 22572448107}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-31T16:37:44.911794+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5932239", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T16:10:58.788024+00:00", "lastSyncTime": "2026-11-13T16:11:01.460786+00:00", "modelId": "nanbeige/Nanbeige4.3-33B-INT4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22550508296, "estimatedRequiredGiB": 25.227, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22572448107, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22572448107, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:7f52dcb6ef9194b8", "recursiveRepositoryBytes": 22572448107, "repositoryOnDiskBytes": 22572448107}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-31T16:21:41.704856+00:00", "targetGpu": "Vastai_va16", "taskId": "5931916", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T16:10:58.788024+00:00", "lastSyncTime": "2026-11-13T16:11:01.460793+00:00", "modelId": "nanbeige/Nanbeige4.3-33B-INT4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22550508296, "estimatedRequiredGiB": 25.227, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22572448107, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22572448107, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:7f52dcb6ef9194b8", "recursiveRepositoryBytes": 22572448107, "repositoryOnDiskBytes": 22572448107}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-31T16:37:44.911794+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5932239", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:45:06.109466+00:00", "lastSyncTime": "2026-11-13T13:45:09.684682+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145039245, "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": 8145039245, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:06e1b44940b82d27", "recursiveRepositoryBytes": 8145039245, "repositoryOnDiskBytes": 8145039245}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-01T14:28:48.157521+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5949285", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:40:02.145873+00:00", "lastSyncTime": "2026-11-13T13:40:03.435755+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077977657, "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": 11077977657, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:abf2795564ed82d1", "recursiveRepositoryBytes": 11077977657, "repositoryOnDiskBytes": 11077977657}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-01T14:44:34.763156+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5949657", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T15:06:51.172961+00:00", "lastSyncTime": "2026-11-13T15:06:54.581204+00:00", "modelId": "ggml-org/spec-for-testing-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c019f2acaa283e609a098da0625fdd71e422c4cc1ff9dfe59e50259bbf7310e0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2056414688, "estimatedRequiredGiB": 57.232, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 51210239024, "modelscopeLicense": "other", "modelscopeParams": 1112828867, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 51210239024, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 51210239024, "repositoryOnDiskBytes": 51210239024}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-01T18:08:11.434665+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5953186", "taskType": "text-generation", "verifyResult": null}
@@ -1053,7 +1053,7 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T11:47:20.898728+00:00", "lastSyncTime": "2026-11-13T11:47:24.474776+00:00", "modelId": "RedHatAI/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 32293788600, "estimatedRequiredGiB": 36.112, "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": 32312682754, "modelscopeLicense": null, "modelscopeParams": 31577940288, "modelscopeTags": ["model_type:nemotron_h", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:nemotron-3.5", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 32312682754, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f1a7feea183fba72", "recursiveRepositoryBytes": 32312682980, "repositoryOnDiskBytes": 32312682980}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-10T15:19:21.378463+00:00", "targetGpu": "MetaX_c-500", "taskId": "6143489", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T11:47:20.898728+00:00", "lastSyncTime": "2026-11-13T11:47:24.474769+00:00", "modelId": "RedHatAI/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 32293788600, "estimatedRequiredGiB": 36.112, "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": 32312682980, "modelscopeLicense": null, "modelscopeParams": 31577940288, "modelscopeTags": ["model_type:nemotron_h", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:nemotron-3.5", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 32312682980, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f1a7feea183fba72", "recursiveRepositoryBytes": 32312682980, "repositoryOnDiskBytes": 32312682980}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-10T15:35:33.568955+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6143668", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T12:09:42.859618+00:00", "lastSyncTime": "2026-11-13T12:09:46.077561+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-w8a8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35150826024, "estimatedRequiredGiB": 39.292, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 35157551596, "modelscopeLicense": null, "modelscopeParams": 31270466080, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 35157551596, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 35157551596, "repositoryOnDiskBytes": 35157551596}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T03:00:26.003590+00:00", "targetGpu": "MetaX_c-500", "taskId": "6151554", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T07:48:43.597512+00:00", "lastSyncTime": "2026-11-13T07:48:47.028312+00:00", "modelId": "nanbeige/Nanbeige4.3-33B-INT8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35992806936, "estimatedRequiredGiB": 40.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 36014177528, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 36014177528, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:1d6de1e98552edcc", "recursiveRepositoryBytes": 36014177528, "repositoryOnDiskBytes": 36014177528}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T07:58:40.792909+00:00", "targetGpu": "MetaX_c-500", "taskId": "6155838", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T16:10:58.788024+00:00", "lastSyncTime": "2026-11-13T16:11:01.460801+00:00", "modelId": "nanbeige/Nanbeige4.3-33B-INT8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35992806936, "estimatedRequiredGiB": 40.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 36014177528, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 36014177528, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:1d6de1e98552edcc", "recursiveRepositoryBytes": 36014177528, "repositoryOnDiskBytes": 36014177528}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T07:58:40.792909+00:00", "targetGpu": "MetaX_c-500", "taskId": "6155838", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T09:01:15.323662+00:00", "lastSyncTime": "2026-11-13T09:01:18.667813+00:00", "modelId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165276348, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200017856, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6046852151, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 27200017856, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e986acf74893086a", "recursiveRepositoryBytes": 27200017856, "repositoryOnDiskBytes": 27200017856}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T10:24:50.828818+00:00", "targetGpu": "MetaX_c-500", "taskId": "6157714", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T11:51:58.890775+00:00", "lastSyncTime": "2026-11-13T11:52:01.952077+00:00", "modelId": "ShenRen1231/Spark-1.7B-DeepSeek-v4.1-Flash-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "92c9e514ac335a5c1ce5f4a6b3f86a14a806ff20573bb41bc4df2cd47cf2ef14", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112640, "estimatedRequiredGiB": 3.272, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 2927578486, "modelscopeLicense": "MIT License", "modelscopeParams": 1707657216, "modelscopeTags": ["license:MIT License", "library:lora", "library:peft", "library:gguf", "task:text-generation", "custom_tag:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:lora", "custom_tag:peft", "custom_tag:instruction-tuned", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:agent"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 2927578486, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 2927578486, "repositoryOnDiskBytes": 2927578486}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T11:37:38.626083+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6158798", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T12:35:05.807761+00:00", "lastSyncTime": "2026-11-13T12:35:09.445945+00:00", "modelId": "bytkim/Qwen3.8-27B-pi-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34715684264, "estimatedRequiredGiB": 38.825, "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": 34739621865, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:speculative-decoding", "custom_tag:vision", "custom_tag:image", "custom_tag:multimodal", "custom_tag:image-text-to-text", "custom_tag:text-generation-inference", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:qwen38", "custom_tag:27b", "custom_tag:pi", "custom_tag:coding", "custom_tag:coder", "custom_tag:code-generation", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:reasoning", "custom_tag:conversational", "custom_tag:sft", "custom_tag:grpo", "custom_tag:reinforcement-learning", "custom_tag:fp8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 34739621865, "quantizationMethod": "fp8", "quantizationSignature": "fp8:a8794dc9a10580bc", "recursiveRepositoryBytes": 34739621865, "repositoryOnDiskBytes": 34739621865}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T12:51:58.794805+00:00", "targetGpu": "MetaX_c-500", "taskId": "6159867", "taskType": "text-generation", "verifyResult": null}
@@ -1084,7 +1084,7 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T14:10:27.623468+00:00", "lastSyncTime": "2026-11-13T14:10:30.869075+00:00", "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-8bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10546877288, "estimatedRequiredGiB": 11.807, "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": 10565007559, "modelscopeLicense": "other", "modelscopeParams": 3345499888, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 10565007559, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b0b0c9a002005922", "recursiveRepositoryBytes": 10565007559, "repositoryOnDiskBytes": 10565007559}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:39:10.626990+00:00", "targetGpu": "MetaX_c-500", "taskId": "6165655", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T15:10:47.366378+00:00", "lastSyncTime": "2026-11-13T15:10:50.546762+00:00", "modelId": "groxaxo/Qwen3.6-35B-A3B-Heretic-UD-inspired-GPTQPro-W4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25870485144, "estimatedRequiredGiB": 28.949, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 25903513281, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:gptq", "custom_tag:mixed-precision", "custom_tag:qwen3_5_moe", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 25903513281, "quantizationMethod": "gptq", "quantizationSignature": "gptq:dd234368d4ad70f9", "recursiveRepositoryBytes": 25903513281, "repositoryOnDiskBytes": 25903513281}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:39:10.630196+00:00", "targetGpu": "Ascend_910-b4", "taskId": "6165651", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:18:37.392679+00:00", "lastSyncTime": "2026-11-13T13:18:40.673756+00:00", "modelId": "cyankiwi/Agents-A1-AWQ-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926870808, "estimatedRequiredGiB": 26.791, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23972444278, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23972444278, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9bae5222b55fce6e", "recursiveRepositoryBytes": 23972444278, "repositoryOnDiskBytes": 23972444278}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:39:10.633826+00:00", "targetGpu": "Ascend_910-b4", "taskId": "6165653", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T07:48:43.597512+00:00", "lastSyncTime": "2026-11-13T07:48:47.028319+00:00", "modelId": "nanbeige/Nanbeige4.3-33B-INT8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35992806936, "estimatedRequiredGiB": 40.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 36014177528, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 36014177528, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:1d6de1e98552edcc", "recursiveRepositoryBytes": 36014177528, "repositoryOnDiskBytes": 36014177528}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:39:10.632231+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6165650", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T16:10:58.788024+00:00", "lastSyncTime": "2026-11-13T16:11:01.460809+00:00", "modelId": "nanbeige/Nanbeige4.3-33B-INT8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35992806936, "estimatedRequiredGiB": 40.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 36014177528, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 36014177528, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:1d6de1e98552edcc", "recursiveRepositoryBytes": 36014177528, "repositoryOnDiskBytes": 36014177528}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:39:10.632231+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6165650", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T10:30:22.492973+00:00", "lastSyncTime": "2026-11-13T10:30:26.588432+00:00", "modelId": "IFM/K2-Horizon-32B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37350407624, "estimatedRequiredGiB": 41.768, "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": 37372966182, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779304960, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 37372966182, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:36e15c6d014ede20", "recursiveRepositoryBytes": 37372966182, "repositoryOnDiskBytes": 37372966182}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:39:10.636839+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6165654", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T09:59:03.036625+00:00", "lastSyncTime": "2026-11-13T09:59:06.070601+00:00", "modelId": "DavidAU/Qwen3-Great-Bowels-Of-Horror-FREAKSTORM-6B", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23760683776, "estimatedRequiredGiB": 26.573, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 23776795658, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5940153600, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "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:story", "custom_tag:writing", "custom_tag:fiction", "custom_tag:roleplaying", "custom_tag:swearing", "custom_tag:extreme swearing", "custom_tag:rp", "custom_tag:graphic horror", "custom_tag:horror", "custom_tag:nsfw", "custom_tag:not-for-all-audiences", "custom_tag:finetune", "custom_tag:programming", "custom_tag:code generation", "custom_tag:code", "custom_tag:coding", "custom_tag:coder", "custom_tag:chat", "custom_tag:brainstorm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwencoder", "custom_tag:brainstorm 20x", "custom_tag:all uses cases", "custom_tag:Jan-V1", "custom_tag:science fiction", "custom_tag:fantasy", "custom_tag:thinking", "custom_tag:reasoning", "custom_tag:unsloth"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23776795658, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 23776795658, "repositoryOnDiskBytes": 23776795658}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:51:35.690118+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6165900", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T10:22:18.146191+00:00", "lastSyncTime": "2026-11-13T10:22:21.690788+00:00", "modelId": "IFM/Jais-3-32B-MLX-bf16", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "6165852", "taskType": "text-generation", "verifyResult": null}
@@ -1145,5 +1145,5 @@
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T09:05:08.818110+00:00", "lastSyncTime": "2026-11-13T09:05:12.160626+00:00", "modelId": "speakleash/Bielik-11B-v3.1-Instruct", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22337646064, "estimatedRequiredGiB": 24.967, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22340131538, "modelscopeLicense": "apache-2.0", "modelscopeParams": 11168796672, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22340131538, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 22340131538, "repositoryOnDiskBytes": 22340131538}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-11T21:11:54.148938+00:00", "targetGpu": "Vastai_va16", "taskId": "6167899", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T11:16:00.136088+00:00", "lastSyncTime": "2026-11-13T12:44:11.375932+00:00", "modelId": "ReadyArt/gemma-4-31B-it-scotoma-2", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62546338264, "estimatedRequiredGiB": 69.938, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 62579334938, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31273088876, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 62579334938, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 62579334938, "repositoryOnDiskBytes": 62579334938}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T04:42:16.927719+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6175702", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "llamacpp", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T09:46:03.177202+00:00", "lastSyncTime": "2026-11-13T15:40:59.453664+00:00", "modelId": "speakleash/Bielik-Minitron-7B-v3.0-Instruct-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "88887392536caac504983465af24046fe87672e0005b073681ee4a04fe2ff4fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7946804256, "estimatedRequiredGiB": 26.686, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 23878193716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7477727232, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:finetuned", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23878193716, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 23878193716, "repositoryOnDiskBytes": 23878193716}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T07:40:49.836990+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "6178271", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "llamacpp", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T14:32:09.209754+00:00", "lastSyncTime": "2026-11-13T16:06:38.852384+00:00", "modelId": "MiMouse/MiMouseEdgeLLM", "modelProfile": {"architectures": [], "configFingerprint": "cadea9b9404f483d273d225bb814842664573f2f56e2d5cf291713c3b7b0f535", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229093184, "estimatedRequiredGiB": 28.259, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 25285638831, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 9400279040, "modelscopeTags": ["license:Apache License 2.0", "library:gguf", "library:other", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 25285638831, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 25285638831, "repositoryOnDiskBytes": 25285638831}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T09:38:35.656078+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6180024", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "llamacpp", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T14:32:09.209754+00:00", "lastSyncTime": "2026-11-13T16:06:38.852451+00:00", "modelId": "MiMouse/MiMouseEdgeLLM", "modelProfile": {"architectures": [], "configFingerprint": "ae398026f5656cfd4301ce87fc25100cad06a6ff1079be74680599f8c3c8d771", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229093184, "estimatedRequiredGiB": 28.259, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 25285638831, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 9400279040, "modelscopeTags": ["license:Apache License 2.0", "library:gguf", "library:other", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 25285638831, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 25285638831, "repositoryOnDiskBytes": 25285638831}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T09:38:47.148598+00:00", "targetGpu": "Ascend_910-b4", "taskId": "6180037", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "llamacpp", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T14:32:09.209754+00:00", "lastSyncTime": "2026-11-13T16:11:01.460634+00:00", "modelId": "MiMouse/MiMouseEdgeLLM", "modelProfile": {"architectures": [], "configFingerprint": "cadea9b9404f483d273d225bb814842664573f2f56e2d5cf291713c3b7b0f535", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229093184, "estimatedRequiredGiB": 28.259, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 25285638831, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 9400279040, "modelscopeTags": ["license:Apache License 2.0", "library:gguf", "library:other", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 25285638831, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 25285638831, "repositoryOnDiskBytes": 25285638831}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T09:38:35.656078+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6180024", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "llamacpp", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T14:32:09.209754+00:00", "lastSyncTime": "2026-11-13T16:11:01.460707+00:00", "modelId": "MiMouse/MiMouseEdgeLLM", "modelProfile": {"architectures": [], "configFingerprint": "ae398026f5656cfd4301ce87fc25100cad06a6ff1079be74680599f8c3c8d771", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229093184, "estimatedRequiredGiB": 28.259, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 25285638831, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 9400279040, "modelscopeTags": ["license:Apache License 2.0", "library:gguf", "library:other", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 25285638831, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 25285638831, "repositoryOnDiskBytes": 25285638831}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T09:38:47.148598+00:00", "targetGpu": "Ascend_910-b4", "taskId": "6180037", "taskType": "text-generation", "verifyResult": null}