state: generation 31880 (cycle)
This commit is contained in:
1 parent
68678cb7bc
commit
a9296850a5
7 files changed
+970
-970
No files matched your search
+10
-10
@@ -153,7 +153,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:44:26.658350+00:00", "lastSyncTime": "2026-11-13T14:44:29.951364+00:00", "modelId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Vastai_va16", "taskId": "5786730", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:15:26.936414+00:00", "lastSyncTime": "2026-11-13T14:15:30.083765+00:00", "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5780290", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:44:26.658350+00:00", "lastSyncTime": "2026-11-13T14:44:29.951337+00:00", "modelId": "cyankiwi/Solar-Open-100B-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5778092", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T13:57:28.135778+00:00", "lastSyncTime": "2026-11-13T13:57:31.851622+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5778061", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455304+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5778061", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:27:46.341486+00:00", "lastSyncTime": "2026-11-13T14:27:49.855342+00:00", "modelId": "cyankiwi/OmniCoder-9B-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Vastai_va16", "taskId": "5773873", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:58:46.915729+00:00", "lastSyncTime": "2026-11-13T21:58:49.760743+00:00", "modelId": "cyankiwi/KAT-Dev-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5769793", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:50:07.339106+00:00", "lastSyncTime": "2026-11-13T21:50:09.963290+00:00", "modelId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5768526", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -431,7 +431,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:38:14.101625+00:00", "lastSyncTime": "2026-11-13T21:38:16.875281+00:00", "modelId": "cyankiwi/DASD-4B-Thinking-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5790179", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T18:44:55.732764+00:00", "lastSyncTime": "2026-11-13T18:44:58.782682+00:00", "modelId": "IFM/Jais-3-7B-FP8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5790147", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:50:07.339106+00:00", "lastSyncTime": "2026-11-13T21:50:09.963277+00:00", "modelId": "cyankiwi/Hermes-4.3-36B-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5790051", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T13:57:28.135778+00:00", "lastSyncTime": "2026-11-13T13:57:31.851628+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Vastai_va16", "taskId": "5788765", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455283+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Vastai_va16", "taskId": "5788765", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:27:46.341486+00:00", "lastSyncTime": "2026-11-13T14:27:49.855379+00:00", "modelId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Vastai_va16", "taskId": "5780488", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:23:16.606323+00:00", "lastSyncTime": "2026-11-13T14:23:19.962528+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5772869", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:10:27.623468+00:00", "lastSyncTime": "2026-11-13T14:10:30.869101+00:00", "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5768505", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -441,7 +441,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:23:16.606323+00:00", "lastSyncTime": "2026-11-13T14:23:19.962534+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5761466", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:06:32.706461+00:00", "lastSyncTime": "2026-11-13T14:06:35.769499+00:00", "modelId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5758985", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T17:05:46.750310+00:00", "lastSyncTime": "2026-11-13T17:05:49.674463+00:00", "modelId": "prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5756228", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T13:57:28.135778+00:00", "lastSyncTime": "2026-11-13T13:57:31.851633+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5755982", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455290+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5755982", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:23:16.606323+00:00", "lastSyncTime": "2026-11-13T14:23:19.962509+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5701879", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:46:23.763424+00:00", "lastSyncTime": "2026-11-13T21:46:26.257109+00:00", "modelId": "cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5701880", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:06:32.706461+00:00", "lastSyncTime": "2026-11-13T14:06:35.769505+00:00", "modelId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5701876", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -511,7 +511,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:44:47.897023+00:00", "lastSyncTime": "2026-11-13T15:44:51.553990+00:00", "modelId": "kakarotter/calix", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5775023", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:27:46.341486+00:00", "lastSyncTime": "2026-11-13T14:27:49.855407+00:00", "modelId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5768501", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:33:54.763697+00:00", "lastSyncTime": "2026-11-13T21:33:57.976366+00:00", "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5766836", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T13:57:28.135778+00:00", "lastSyncTime": "2026-11-13T13:57:31.851639+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5765199", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455317+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5765199", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:10:27.623468+00:00", "lastSyncTime": "2026-11-13T14:10:30.869088+00:00", "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5762276", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:10:27.623468+00:00", "lastSyncTime": "2026-11-13T14:10:30.869041+00:00", "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5758982", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:46:23.763424+00:00", "lastSyncTime": "2026-11-13T21:46:26.257128+00:00", "modelId": "cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5756223", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -717,7 +717,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:01:55.430162+00:00", "lastSyncTime": "2026-11-13T14:01:58.441122+00:00", "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5764371", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:03:10.739314+00:00", "lastSyncTime": "2026-11-13T22:03:13.774236+00:00", "modelId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5735872", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:19:18.771613+00:00", "lastSyncTime": "2026-11-13T14:19:22.159923+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5719482", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T13:57:28.135778+00:00", "lastSyncTime": "2026-11-13T13:57:31.851609+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5716785", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455296+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5716785", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:03:10.739314+00:00", "lastSyncTime": "2026-11-13T22:03:13.774228+00:00", "modelId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5712853", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:15:26.936414+00:00", "lastSyncTime": "2026-11-13T14:15:30.083818+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5708208", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T20:22:45.636663+00:00", "lastSyncTime": "2026-11-13T20:22:48.274577+00:00", "modelId": "XHToken/Spark-X2.6-4B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "5697420", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -788,7 +788,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:49:32.259200+00:00", "lastSyncTime": "2026-11-13T14:49:35.328426+00:00", "modelId": "cyankiwi/Trinity-Mini-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5722885", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:38:14.101625+00:00", "lastSyncTime": "2026-11-13T21:38:16.875307+00:00", "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5715909", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T20:22:45.636663+00:00", "lastSyncTime": "2026-11-13T20:22:48.274571+00:00", "modelId": "XHToken/Spark-X2.6-4B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5714121", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T13:57:28.135778+00:00", "lastSyncTime": "2026-11-13T13:57:31.851616+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5701881", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455310+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5701881", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:29:28.010794+00:00", "lastSyncTime": "2026-11-13T21:29:31.178079+00:00", "modelId": "cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5700656", "taskType": "text-generation", "verifyResult": null}
|
||||
{"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": "2026-11-13T14:27:46.341486+00:00", "lastSyncTime": "2026-11-13T14:27:49.855414+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}
|
||||
@@ -907,7 +907,7 @@
|
||||
{"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": "2026-11-13T21:00:41.735309+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": "2026-11-13T14:01:55.430162+00:00", "lastSyncTime": "2026-11-13T14:01:58.441084+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": "2026-11-13T22:11:15.134307+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": "2026-11-13T14:40:34.336867+00:00", "lastSyncTime": "2026-11-13T14:40:37.780261+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}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "llamacpp", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T15:36:29.073361+00:00", "lastSyncTime": "2026-11-13T15:36:31.479609+00:00", "modelId": "incoai/Qwen3.8-Flash-Next-DFlash2-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "4c98ab4ddc73d23ce303538ecd9a88bdd2af18582ee3c2a50f7f11f36d766187", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 652101024, "estimatedRequiredGiB": 3.543, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3169866081, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:dflash2", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3169866081, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 3169866081, "repositoryOnDiskBytes": 3169866081}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T16:05:55.287834+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5829160", "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": "2026-11-13T17:01:24.361429+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22070410112, "estimatedRequiredGiB": 24.69, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-27T16:05:55.379121+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5829196", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -936,7 +936,7 @@
|
||||
{"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}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T21:25:39.083613+00:00", "lastSyncTime": "2026-11-13T21:25:41.949303+00:00", "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-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": 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": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T00:47:44.905039+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5835985", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:57:28.135778+00:00", "lastSyncTime": "2026-11-13T13:57:31.851603+00:00", "modelId": "cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038369021, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038369021, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038369021, "repositoryOnDiskBytes": 29038369021}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T00:47:44.924156+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5835986", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455274+00:00", "modelId": "cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038369021, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038369021, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038369021, "repositoryOnDiskBytes": 29038369021}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T00:47:44.924156+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5835986", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T15:44:47.897023+00:00", "lastSyncTime": "2026-11-13T15:44:51.554056+00:00", "modelId": "lightx2v/Qwen-Image-2.1-PE-I2I-GGUF-Q8_0", "modelProfile": {"architectures": [], "configFingerprint": "cab7fc6aa7d40ff1a1fb792b012eea9b42d2292eaf42910cf6cd04cdd52cd5f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9527501536, "estimatedRequiredGiB": 11.678, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10449230677, "modelscopeLicense": "other", "modelscopeParams": 8953803264, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:prompt-rewriting", "custom_tag:image-editing", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 10449230677, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 10449230677, "repositoryOnDiskBytes": 10449230677}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T04:31:21.831783+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5839196", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T21:17:01.552484+00:00", "lastSyncTime": "2026-11-13T21:17:04.657367+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459874983, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3459874983, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 3459874983, "repositoryOnDiskBytes": 3459874983}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T04:31:21.828449+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5839194", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:36:23.407716+00:00", "lastSyncTime": "2026-11-13T20:36:26.068131+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20321390048, "estimatedRequiredGiB": 22.734, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20341996128, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20341996128, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:ee367b4119f8452e", "recursiveRepositoryBytes": 20341996128, "repositoryOnDiskBytes": 20341996128}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T04:31:22.094069+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5839195", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -949,7 +949,7 @@
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T21:09:15.846823+00:00", "lastSyncTime": "2026-11-13T21:09:18.669822+00:00", "modelId": "cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6691066608, "estimatedRequiredGiB": 7.498, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 6709196718, "modelscopeLicense": "other", "modelscopeParams": 2381547248, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 6709196718, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b91e1843aeaeb7f4", "recursiveRepositoryBytes": 6709196718, "repositoryOnDiskBytes": 6709196718}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T09:03:53.034455+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5843330", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T17:10:07.862548+00:00", "lastSyncTime": "2026-11-13T17:10:10.553649+00:00", "modelId": "r0b0tlab/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-EXL3-2.08bpw", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20065950490, "estimatedRequiredGiB": 22.5, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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", "quantizationSignature": "exl3:3221954a26649da6", "recursiveRepositoryBytes": 20133005090, "repositoryOnDiskBytes": 20133005090}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T09:03:53.459660+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5843331", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T17:55:07.425384+00:00", "lastSyncTime": "2026-11-13T17:55:09.887734+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "7c34efcde5a927a2fb1c4c042dcd5dd78bb085e38cf6786f306974e82875b984", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 281591196, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 281591196, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T10:02:08.478250+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5843990", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:57:28.135778+00:00", "lastSyncTime": "2026-11-13T13:57:31.851596+00:00", "modelId": "cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038369021, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038369021, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038369021, "repositoryOnDiskBytes": 29038369021}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T10:49:59.501022+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5844817", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455253+00:00", "modelId": "cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038369021, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038369021, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038369021, "repositoryOnDiskBytes": 29038369021}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T10:49:59.501022+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5844817", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:22:45.636663+00:00", "lastSyncTime": "2026-11-13T20:22:48.274512+00:00", "modelId": "XHToken/Spark-X2.6-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1d153f006310de4a64f8c5ec9c0a4875a6af2dfc403b09509ed2b227a47b4002", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820113440, "estimatedRequiredGiB": 7.834, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7010046444, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7010046444, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7010046444, "repositoryOnDiskBytes": 7010046444}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T13:34:09.462874+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5847555", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:22:45.636663+00:00", "lastSyncTime": "2026-11-13T20:22:48.274477+00:00", "modelId": "XHToken/Spark-X2.6-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "ee7d3f741e15635edb6a7aaff8a36f09b08e64fc64c26a9e83971ebf3d3ac190", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820113440, "estimatedRequiredGiB": 7.834, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7010046444, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7010046444, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7010046444, "repositoryOnDiskBytes": 7010046444}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T13:49:57.249364+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5847754", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882876+00:00", "modelId": "Haodong07/Qwen3-14B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12610178368, "estimatedRequiredGiB": 14.106, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10550492288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 12621681247, "repositoryOnDiskBytes": 12621681247}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:05:45.083117+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5847970", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -1076,7 +1076,7 @@
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:22:39.566339+00:00", "lastSyncTime": "2026-11-13T18:22:42.569273+00:00", "modelId": "Gryphe/Gemma-4-31B-StyleTune", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65364910736, "estimatedRequiredGiB": 73.088, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 65398028234, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32682375020, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:gemma4", "custom_tag:conversational", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:roleplay", "custom_tag:creative-writing", "custom_tag:style-tune"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 65398028234, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 65398028234, "repositoryOnDiskBytes": 65398028234}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:59:03.495827+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6165089", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T17:49:33.328601+00:00", "lastSyncTime": "2026-11-13T17:49:36.252485+00:00", "modelId": "AtomicChat/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9db497a9b0994b19d766a4f358090ea4120d3ef03c5344dd599fb0d095c0d944", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8031245312, "estimatedRequiredGiB": 39.623, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 35453857167, "modelscopeLicense": "other", "modelscopeParams": 7518069290, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:atomic-dynamic", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:nvidia", "custom_tag:gemma4", "custom_tag:imatrix", "custom_tag:quantized", "custom_tag:conversational", "custom_tag:atomic-chat", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 35453857167, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 35453857167, "repositoryOnDiskBytes": 35453857167}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:22:10.820730+00:00", "targetGpu": "hygon_k100-ai", "taskId": "6165396", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T17:14:24.733288+00:00", "lastSyncTime": "2026-11-13T17:14:27.632496+00:00", "modelId": "security-serch/Sec-sft-AT-4B", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8822894448, "estimatedRequiredGiB": 9.878, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8838816961, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:reinforcement-learning"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8838816961, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 8838816961, "repositoryOnDiskBytes": 8838816961}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:31:20.406937+00:00", "targetGpu": "Ascend_910-b4", "taskId": "6165528", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:57:28.135778+00:00", "lastSyncTime": "2026-11-13T13:57:31.851646+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-8bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10634065360, "estimatedRequiredGiB": 11.89, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 10639191747, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 10639191747, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f3ec6d4095e60bda", "recursiveRepositoryBytes": 10639191747, "repositoryOnDiskBytes": 10639191747}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:39:10.635643+00:00", "targetGpu": "MetaX_c-500", "taskId": "6165649", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T22:11:15.134307+00:00", "lastSyncTime": "2026-11-13T22:11:18.455325+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-8bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10634065360, "estimatedRequiredGiB": 11.89, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 10639191747, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 10639191747, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f3ec6d4095e60bda", "recursiveRepositoryBytes": 10639191747, "repositoryOnDiskBytes": 10639191747}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:39:10.635643+00:00", "targetGpu": "MetaX_c-500", "taskId": "6165649", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T14:23:16.606323+00:00", "lastSyncTime": "2026-11-13T14:23:19.962547+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-8bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35211965376, "estimatedRequiredGiB": 39.364, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "olmo3", "modelscopeFileSize": 35221890362, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32233522176, "modelscopeTags": ["license:apache-2.0", "model_type:olmo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 35221890362, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:46a94bbd3d552170", "recursiveRepositoryBytes": 35221890362, "repositoryOnDiskBytes": 35221890362}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T18:39:10.628313+00:00", "targetGpu": "MetaX_c-500", "taskId": "6165652", "taskType": "text-generation", "verifyResult": null}
|
||||
{"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}
|
||||
|
||||
Reference in new issue
Block a user