diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 9441a9d07..4b0334eb7 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2578,7 +2578,7 @@ {"batchId": "f62ed5826de8413bb5a3315bfdbd79fd", "completedAt": "2026-09-29T18:57:58.007998+00:00", "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configSource": "modelhub_live", "createdAt": "2026-09-29T18:56:26.894861+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ad27628ec0b843f7aebb6a30c126332f", "lastModified": "2026-09-29T18:49:29+00:00", "modelAddress": "https://modelscope.cn/models/NovelAI/genji-jp-6b-v2-legacy", "reason": null, "reconciledAt": "2026-09-29T19:09:17.596085+00:00", "repoId": "NovelAI/genji-jp-6b-v2-legacy", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5175588", "taskType": "text-generation"} {"batchId": "f614884984e8432e8540d73ba7b81d1b", "completedAt": "2026-09-29T19:00:18.376414+00:00", "configFingerprint": "a01fe5f73d80ae5098de5ec37e5d945b6e3354d3120313494556c90bde3d2565", "configSource": "modelhub_live", "createdAt": "2026-09-29T19:00:15.471029+00:00", "framework": "llamacpp", "intentId": "03c54f1405434d97995a8500de3c46ce", "lastModified": "2026-09-29T18:28:19+00:00", "modelAddress": "https://modelscope.cn/models/NovelAI/novelai-lm-3b-508k", "reason": null, "reconciledAt": "2026-09-29T19:09:17.596981+00:00", "repoId": "NovelAI/novelai-lm-3b-508k", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5175625", "taskType": "text-generation"} {"batchId": "f614884984e8432e8540d73ba7b81d1b", "completedAt": "2026-09-29T19:00:18.376429+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-29T19:00:15.471158+00:00", "framework": "vllm_tokenizer_patch", "intentId": "748c423f3a0b4be8aa6c467e45380833", "lastModified": "2026-09-29T18:29:31+00:00", "modelAddress": "https://modelscope.cn/models/ProCreations/Auto-Reason-3b", "reason": null, "reconciledAt": "2026-09-29T19:09:17.597720+00:00", "repoId": "ProCreations/Auto-Reason-3b", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5175626", "taskType": "text-generation"} -{"batchId": "33c227a6b29b4c52943edbd6d69fd0f1", "configFingerprint": "669d5c8b6211d2073c3b0347378393acc352b6e718091ce3f0243839b888b201", "configSource": "modelhub_live", "createdAt": "2026-09-29T19:15:29.072815+00:00", "framework": "llamacpp", "intentId": "2afebf0f75174da1bb80e65bac81e9c1", "lastModified": "2026-09-29T18:49:29+00:00", "modelAddress": "https://modelscope.cn/models/NovelAI/genji-jp-6b-v2-legacy", "repoId": "NovelAI/genji-jp-6b-v2-legacy", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} +{"batchId": "33c227a6b29b4c52943edbd6d69fd0f1", "completedAt": "2026-09-29T19:15:31.303982+00:00", "configFingerprint": "669d5c8b6211d2073c3b0347378393acc352b6e718091ce3f0243839b888b201", "configSource": "modelhub_live", "createdAt": "2026-09-29T19:15:29.072815+00:00", "framework": "llamacpp", "intentId": "2afebf0f75174da1bb80e65bac81e9c1", "lastModified": "2026-09-29T18:49:29+00:00", "modelAddress": "https://modelscope.cn/models/NovelAI/genji-jp-6b-v2-legacy", "reason": null, "repoId": "NovelAI/genji-jp-6b-v2-legacy", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "5175847", "taskType": "text-generation"} {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925444+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683768+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ba30792e89b44ef5804d5f3613d7df71", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925408+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683638+00:00", "framework": "vllm_tokenizer_patch", "intentId": "69aec4d25f21464c860135eb90d77735", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} {"batchId": "af702292a17240468562311292c55106", "completedAt": "2026-09-29T11:50:56.209408+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-29T11:50:53.929909+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c488d875b85a4d699fe135674c2b940b", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 353ebeb0f..473c71413 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2717 + "unified_success_first": 2718 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 18, @@ -35,12 +35,12 @@ "text-generation|Sunrise_pt-200-x1|vllm": 87, "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 111, "text-generation|Vastai_va16|vllm_fix_tokenizer": 103, - "text-generation|hygon_k100-ai|llamacpp": 23, + "text-generation|hygon_k100-ai|llamacpp": 24, "text-generation|hygon_k100-ai|vllm": 27, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 152 }, - "acceptedSinceRefresh": 2717, - "acceptedTotal": 2717, - "generatedAt": "2026-09-29T19:00:18.263278+00:00", + "acceptedSinceRefresh": 2718, + "acceptedTotal": 2718, + "generatedAt": "2026-09-29T19:15:31.258583+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index e6e9d5556..5c7e1a640 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1007,3 +1007,4 @@ {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-21T18:32:49.780633+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005549", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:01:50.847636+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5097139", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:18:32.495861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5097281", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/NovelAI/genji-jp-6b-v2-legacy", "modelId": "NovelAI/genji-jp-6b-v2-legacy", "submitTime": "2026-09-29T19:15:31.057762+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5175847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"} diff --git a/manifest.json b/manifest.json index 074f9c2d7..5fe6c1fa9 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "1b9a1363360f46e3333fceac79ff2c309befd678fffc2b42aff773c5823cf35e", ".modelhub_state/recent_outcomes.jsonl": "ea81f07d56492dc8073d6b8c3d83451fd1eb74f474036ebf59f262ff9711b54a", ".modelhub_state/recovery_active_tasks.jsonl": "8dc6f25db96666630163a6cbbd60f47d5fad69de524af7d1f4850e6eeb1f6829", - ".modelhub_state/recovery_intents.jsonl": "1fe5f082553820d8a1251ba903b3af6534ce754d9453c465b9ac366f81896cbf", - ".modelhub_state/routing_intelligence.json": "3f8eeb4f7690115b13ebd4fbfcd7aef628ce1840e4ecd82c351e8e6ae02c58ab", + ".modelhub_state/recovery_intents.jsonl": "0710baa9d6b78b58e5206f9cb5d45d6c42c402f1e86e36f20864264db9dc4c7e", + ".modelhub_state/routing_intelligence.json": "52439d2adab5fb6085edce737f2925c0bb787f37c89c02183c0f8f977314fc26", ".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c", ".modelhub_state/worker_crashes.jsonl": "05bcde79076023fd20785b8270312f776430b95a2d4322ee53ef24e354c39f06", - "ledger/submissions.jsonl": "df08e57e5e1a0af96134994fb14527b1c4e816641153b80d519bb45bc9721bf8", - "outcomes/submissions.jsonl": "5739a1b47e7df0a7d1232ae1164b8c0ae46cfe734dfcf40c828b64c239601b95" + "ledger/submissions.jsonl": "4b4cd7d2974ec9d97b87759c19aa08fafd345e20d5d15dcbdf8df011566a9835", + "outcomes/submissions.jsonl": "24510b2e244fc2ed6156dbf22d4441e60885b07247ade8c9dfd16bd4c9472f28" }, - "generation": 18506, - "phase": "intent", + "generation": 18507, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-29T19:15:29.204299+00:00", + "updatedAt": "2026-09-29T19:15:31.479484+00:00", "writerId": "9d958b95ce4146c9939da0f14b9201ff" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 66ed8b2a7..f4a04b8c7 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -790,3 +790,4 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "NovelAI/genji-jp-6b-v2-legacy", "modelProfile": {"architectures": ["GPTJForCausalLM"], "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12101796384, "estimatedRequiredGiB": 52.535, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gptj", "modelscopeFileSize": null, "modelscopeLicense": "gpl-3.0", "modelscopeParams": null, "modelscopeTags": ["license:gpl-3.0", "model_type:gptj", "library:gguf", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 47007134557}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-29T18:57:55.651656+00:00", "targetGpu": "MetaX_c-500", "taskId": "5175588", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "NovelAI/novelai-lm-3b-508k", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "a01fe5f73d80ae5098de5ec37e5d945b6e3354d3120313494556c90bde3d2565", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3236010048, "estimatedRequiredGiB": 33.616, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": null, "modelscopeLicense": "gpl-2.0", "modelscopeParams": null, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30079174063}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-29T19:00:18.088790+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5175625", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-29T19:00:18.151398+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5175626", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "NovelAI/genji-jp-6b-v2-legacy", "modelProfile": {"architectures": ["GPTJForCausalLM"], "configFingerprint": "669d5c8b6211d2073c3b0347378393acc352b6e718091ce3f0243839b888b201", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6433956448, "estimatedRequiredGiB": 52.535, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gptj", "modelscopeFileSize": 47007134557, "modelscopeLicense": "gpl-3.0", "modelscopeParams": null, "modelscopeTags": ["license:gpl-3.0", "model_type:gptj", "library:gguf", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 47007134557}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-29T19:15:31.057762+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5175847", "taskType": "text-generation", "verifyResult": null}