CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 10839 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 19:48:15 +00:00
parent b00a3175c5
commit b7a08521aa
5 changed files with 90 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
.modelhub_state/recovery_intents.jsonl
View File

@@ -1759,32 +1759,32 @@
{"batchId": "91968e61747d4364bdf7fbbd10ba49db", "completedAt": "2026-09-20T19:33:29.660592+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:30:13.722451+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b323cdb4c8604c8f827ffd1eb1b9811b", "lastModified": "2026-08-31T14:27:40+00:00", "modelAddress": "https://modelscope.cn/models/sbintuitions/sarashina2.2-3b-instruct-v0.1", "reason": null, "reconciledAt": "2026-09-20T19:47:50.163977+00:00", "repoId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986333", "taskType": "text-generation"} {"batchId": "91968e61747d4364bdf7fbbd10ba49db", "completedAt": "2026-09-20T19:33:29.660592+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:30:13.722451+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b323cdb4c8604c8f827ffd1eb1b9811b", "lastModified": "2026-08-31T14:27:40+00:00", "modelAddress": "https://modelscope.cn/models/sbintuitions/sarashina2.2-3b-instruct-v0.1", "reason": null, "reconciledAt": "2026-09-20T19:47:50.163977+00:00", "repoId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986333", "taskType": "text-generation"}
{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040138+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.061559+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1fd4bb7349cf4e348b6ed2ad4707abf9", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T19:47:50.162472+00:00", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4986407", "taskType": "text-generation"} {"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040138+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.061559+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1fd4bb7349cf4e348b6ed2ad4707abf9", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T19:47:50.162472+00:00", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4986407", "taskType": "text-generation"}
{"batchId": "afdf88a0377042f18acdb6b1332d34a1", "completedAt": "2026-09-20T19:47:48.783546+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:44:35.828352+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3637e84970b84816b32fd346bd264346", "lastModified": "2026-08-26T18:08:39+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT", "reason": null, "reconciledAt": "2026-09-20T19:47:50.164764+00:00", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986586", "taskType": "text-generation"} {"batchId": "afdf88a0377042f18acdb6b1332d34a1", "completedAt": "2026-09-20T19:47:48.783546+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:44:35.828352+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3637e84970b84816b32fd346bd264346", "lastModified": "2026-08-26T18:08:39+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT", "reason": null, "reconciledAt": "2026-09-20T19:47:50.164764+00:00", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986586", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229065+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f80b0994063c4feb8eeabd68353634d6", "lastModified": "2026-09-14T20:26:18+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/CEERS-2112-14B-Instruct", "repoId": "prithivMLmods/CEERS-2112-14B-Instruct", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928438+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229065+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f80b0994063c4feb8eeabd68353634d6", "lastModified": "2026-09-14T20:26:18+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/CEERS-2112-14B-Instruct", "reason": null, "repoId": "prithivMLmods/CEERS-2112-14B-Instruct", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986607", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229169+00:00", "framework": "vllm_fix_tokenizer", "intentId": "991315d5ee284fa59b657cee3f9f0357", "lastModified": "2026-09-17T14:05:32+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928449+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229169+00:00", "framework": "vllm_fix_tokenizer", "intentId": "991315d5ee284fa59b657cee3f9f0357", "lastModified": "2026-09-17T14:05:32+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986598", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229217+00:00", "framework": "vllm_fix_tokenizer", "intentId": "603b57ae29cb4bcaac13f5f408f372e7", "lastModified": "2026-09-16T16:05:58+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "repoId": "BAAI/RoboBrain2.5-8B-NV", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928453+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229217+00:00", "framework": "vllm_fix_tokenizer", "intentId": "603b57ae29cb4bcaac13f5f408f372e7", "lastModified": "2026-09-16T16:05:58+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "reason": null, "repoId": "BAAI/RoboBrain2.5-8B-NV", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986604", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229261+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4d9d587be87d44229e3483926baf2e75", "lastModified": "2026-09-14T19:52:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "repoId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928456+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229261+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4d9d587be87d44229e3483926baf2e75", "lastModified": "2026-09-14T19:52:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986599", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229304+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ea2a561cd50c482094c76a48aa49b4c0", "lastModified": "2026-09-17T12:51:11+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928458+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229304+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ea2a561cd50c482094c76a48aa49b4c0", "lastModified": "2026-09-17T12:51:11+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986606", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229347+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6a87c98448634f39b800d44ca18bbec0", "lastModified": "2026-09-20T14:38:08+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "repoId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928460+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229347+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6a87c98448634f39b800d44ca18bbec0", "lastModified": "2026-09-20T14:38:08+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "reason": null, "repoId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986605", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229390+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4bba68205323458bb91f4f99c5b0cdb2", "lastModified": "2026-09-20T14:39:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928463+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229390+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4bba68205323458bb91f4f99c5b0cdb2", "lastModified": "2026-09-20T14:39:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986601", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229433+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b850115047d047d084320cae7891607a", "lastModified": "2026-09-20T14:21:01+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "repoId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928465+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229433+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b850115047d047d084320cae7891607a", "lastModified": "2026-09-20T14:21:01+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986600", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229476+00:00", "framework": "vllm_fix_tokenizer", "intentId": "45af77873ef943899bd9d9758543472a", "lastModified": "2026-09-20T14:29:29+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "repoId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928468+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229476+00:00", "framework": "vllm_fix_tokenizer", "intentId": "45af77873ef943899bd9d9758543472a", "lastModified": "2026-09-20T14:29:29+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "reason": null, "repoId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986603", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229518+00:00", "framework": "vllm_fix_tokenizer", "intentId": "10e59121ff154e91a946c44e9a0fcba6", "lastModified": "2026-09-17T13:39:53+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928470+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229518+00:00", "framework": "vllm_fix_tokenizer", "intentId": "10e59121ff154e91a946c44e9a0fcba6", "lastModified": "2026-09-17T13:39:53+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986602", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229561+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9dd1093ba6a84dc5818800d603cb9fb1", "lastModified": "2026-09-20T14:50:03+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "repoId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928473+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229561+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9dd1093ba6a84dc5818800d603cb9fb1", "lastModified": "2026-09-20T14:50:03+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986609", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229604+00:00", "framework": "vllm_fix_tokenizer", "intentId": "30b1dae13c854984a24604f5d853db9e", "lastModified": "2026-09-15T14:59:20+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928475+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229604+00:00", "framework": "vllm_fix_tokenizer", "intentId": "30b1dae13c854984a24604f5d853db9e", "lastModified": "2026-09-15T14:59:20+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986608", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229647+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8cb98008d2c24aceb7ac5ffa7bd6ab60", "lastModified": "2026-09-20T14:39:19+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "repoId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928477+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229647+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8cb98008d2c24aceb7ac5ffa7bd6ab60", "lastModified": "2026-09-20T14:39:19+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986610", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229782+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d556d131f314bc89810674be74badf4", "lastModified": "2026-09-14T19:46:18+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "repoId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928480+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229782+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d556d131f314bc89810674be74badf4", "lastModified": "2026-09-14T19:46:18+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986615", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229827+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8a920204f48744b1891ad0c95d2f16d5", "lastModified": "2026-09-15T15:10:12+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "repoId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928483+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229827+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8a920204f48744b1891ad0c95d2f16d5", "lastModified": "2026-09-15T15:10:12+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "reason": null, "repoId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986618", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229870+00:00", "framework": "vllm_fix_tokenizer", "intentId": "892463b5a54148beb85eac105d093132", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928485+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229870+00:00", "framework": "vllm_fix_tokenizer", "intentId": "892463b5a54148beb85eac105d093132", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "reason": null, "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986614", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229913+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c97630c25af641b897b4a8aa41373360", "lastModified": "2026-09-20T15:32:35+00:00", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "repoId": "Arain119/Sophia", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928488+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229913+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c97630c25af641b897b4a8aa41373360", "lastModified": "2026-09-20T15:32:35+00:00", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "reason": null, "repoId": "Arain119/Sophia", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986612", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229956+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2272b724bcac45e1976fddd01b71d439", "lastModified": "2026-09-15T15:08:08+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "repoId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928490+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229956+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2272b724bcac45e1976fddd01b71d439", "lastModified": "2026-09-15T15:08:08+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "reason": null, "repoId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986611", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229999+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e37b8803d7744f07b5f6e6e984568166", "lastModified": "2026-09-17T15:15:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928492+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.229999+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e37b8803d7744f07b5f6e6e984568166", "lastModified": "2026-09-17T15:15:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986617", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230041+00:00", "framework": "vllm_fix_tokenizer", "intentId": "be2aaf7c9b5642eaa37d7274500df3a5", "lastModified": "2026-09-15T15:01:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928495+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230041+00:00", "framework": "vllm_fix_tokenizer", "intentId": "be2aaf7c9b5642eaa37d7274500df3a5", "lastModified": "2026-09-15T15:01:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986613", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230084+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6fac8b49bdbd4be6be4c6eeff75df012", "lastModified": "2026-09-15T14:57:59+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "repoId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928497+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230084+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6fac8b49bdbd4be6be4c6eeff75df012", "lastModified": "2026-09-15T14:57:59+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "reason": null, "repoId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986616", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230128+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7194cc1d1472499f9e6c92282dd605a0", "lastModified": "2026-09-17T13:54:18+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928499+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230128+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7194cc1d1472499f9e6c92282dd605a0", "lastModified": "2026-09-17T13:54:18+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986619", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230170+00:00", "framework": "vllm_fix_tokenizer", "intentId": "53a89da44d404bc9b7cbd57caf79af10", "lastModified": "2026-09-16T17:02:01+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "repoId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928501+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230170+00:00", "framework": "vllm_fix_tokenizer", "intentId": "53a89da44d404bc9b7cbd57caf79af10", "lastModified": "2026-09-16T17:02:01+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "reason": null, "repoId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986620", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230213+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2dd2cfc1733046af9ecbb358c073b383", "lastModified": "2026-09-16T17:13:44+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928504+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230213+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2dd2cfc1733046af9ecbb358c073b383", "lastModified": "2026-09-16T17:13:44+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "reason": null, "repoId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986621", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230256+00:00", "framework": "vllm_fix_tokenizer", "intentId": "37ebc03812d144f4adddeefb147baed5", "lastModified": "2026-09-17T13:29:50+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "repoId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928506+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230256+00:00", "framework": "vllm_fix_tokenizer", "intentId": "37ebc03812d144f4adddeefb147baed5", "lastModified": "2026-09-17T13:29:50+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "reason": null, "repoId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986622", "taskType": "text-generation"}
{"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230299+00:00", "framework": "vllm_fix_tokenizer", "intentId": "550270da792c442d8df436de01029c61", "lastModified": "2026-09-15T15:11:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "6252f4ac62854ed7ac0796e8fdb39dc5", "completedAt": "2026-09-20T19:48:14.928509+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:48:06.230299+00:00", "framework": "vllm_fix_tokenizer", "intentId": "550270da792c442d8df436de01029c61", "lastModified": "2026-09-15T15:11:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4986623", "taskType": "text-generation"}
{"batchId": "afdf88a0377042f18acdb6b1332d34a1", "completedAt": "2026-09-20T19:47:48.783554+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:44:35.828518+00:00", "framework": "vllm_fix_tokenizer", "intentId": "303c54082d6f4de78e21aaa05e4e8220", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "afdf88a0377042f18acdb6b1332d34a1", "completedAt": "2026-09-20T19:47:48.783554+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:44:35.828518+00:00", "framework": "vllm_fix_tokenizer", "intentId": "303c54082d6f4de78e21aaa05e4e8220", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "afdf88a0377042f18acdb6b1332d34a1", "completedAt": "2026-09-20T19:47:48.783551+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:44:35.828462+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e8411decd0484162be84ed647c5bc79b", "repoId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "afdf88a0377042f18acdb6b1332d34a1", "completedAt": "2026-09-20T19:47:48.783551+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:44:35.828462+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e8411decd0484162be84ed647c5bc79b", "repoId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "afdf88a0377042f18acdb6b1332d34a1", "completedAt": "2026-09-20T19:47:48.783549+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:44:35.828407+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0b402cd014524ef0ba0bc89f78f9c821", "repoId": "aisingapore/Llama-SEA-LION-v3-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "afdf88a0377042f18acdb6b1332d34a1", "completedAt": "2026-09-20T19:47:48.783549+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:44:35.828407+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0b402cd014524ef0ba0bc89f78f9c821", "repoId": "aisingapore/Llama-SEA-LION-v3-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}

10
.modelhub_state/routing_intelligence.json
View File

@@ -1,6 +1,6 @@
{ {
"acceptedByCategory": { "acceptedByCategory": {
"unified_success_first": 1899 "unified_success_first": 1925
}, },
"acceptedByRoute": { "acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 17, "text-generation|Ascend_910-b3|llamacpp": 17,
@@ -10,7 +10,7 @@
"text-generation|Ascend_910-b4|vllm": 20, "text-generation|Ascend_910-b4|vllm": 20,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 130, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 130,
"text-generation|Biren_166m|vllm": 79, "text-generation|Biren_166m|vllm": 79,
"text-generation|Biren_166m|vllm_fix_tokenizer": 13, "text-generation|Biren_166m|vllm_fix_tokenizer": 39,
"text-generation|Cambricon_mlu-370-x4|vllm": 50, "text-generation|Cambricon_mlu-370-x4|vllm": 50,
"text-generation|Cambricon_mlu-370-x4|vllm-customized": 2, "text-generation|Cambricon_mlu-370-x4|vllm-customized": 2,
"text-generation|Cambricon_mlu-370-x4|vllm-mlu": 82, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 82,
@@ -37,8 +37,8 @@
"text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm": 26,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 113 "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 113
}, },
"acceptedSinceRefresh": 1899, "acceptedSinceRefresh": 1925,
"acceptedTotal": 1899, "acceptedTotal": 1925,
"generatedAt": "2026-09-20T19:47:48.721256+00:00", "generatedAt": "2026-09-20T19:48:14.868309+00:00",
"version": 1 "version": 1
} }

26
ledger/submissions.jsonl
View File

@@ -1125,3 +1125,29 @@
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a8", "submitTime": "2026-09-20T13:22:06.962643+00:00", "targetGpu": "Biren_166m", "taskId": "4979624", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a8", "submitTime": "2026-09-20T13:22:06.962643+00:00", "targetGpu": "Biren_166m", "taskId": "4979624", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "submitTime": "2026-09-20T14:26:11.835960+00:00", "targetGpu": "Biren_166m", "taskId": "4980425", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "submitTime": "2026-09-20T14:26:11.835960+00:00", "targetGpu": "Biren_166m", "taskId": "4980425", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "modelId": "LiquidAI/LFM2.5-2.6B", "submitTime": "2026-09-20T14:26:18.189644+00:00", "targetGpu": "Biren_166m", "taskId": "4980427", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "modelId": "LiquidAI/LFM2.5-2.6B", "submitTime": "2026-09-20T14:26:18.189644+00:00", "targetGpu": "Biren_166m", "taskId": "4980427", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/prithivMLmods/CEERS-2112-14B-Instruct", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "submitTime": "2026-09-20T19:48:14.523364+00:00", "targetGpu": "Biren_166m", "taskId": "4986607", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T19:48:14.450477+00:00", "targetGpu": "Biren_166m", "taskId": "4986598", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "modelId": "BAAI/RoboBrain2.5-8B-NV", "submitTime": "2026-09-20T19:48:14.484978+00:00", "targetGpu": "Biren_166m", "taskId": "4986604", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.473777+00:00", "targetGpu": "Biren_166m", "taskId": "4986599", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-20T19:48:14.509974+00:00", "targetGpu": "Biren_166m", "taskId": "4986606", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-20T19:48:14.502504+00:00", "targetGpu": "Biren_166m", "taskId": "4986605", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T19:48:14.472448+00:00", "targetGpu": "Biren_166m", "taskId": "4986601", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-20T19:48:14.461438+00:00", "targetGpu": "Biren_166m", "taskId": "4986600", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-20T19:48:14.486486+00:00", "targetGpu": "Biren_166m", "taskId": "4986603", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "submitTime": "2026-09-20T19:48:14.482557+00:00", "targetGpu": "Biren_166m", "taskId": "4986602", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T19:48:14.549308+00:00", "targetGpu": "Biren_166m", "taskId": "4986609", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.535472+00:00", "targetGpu": "Biren_166m", "taskId": "4986608", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T19:48:14.574218+00:00", "targetGpu": "Biren_166m", "taskId": "4986610", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.639695+00:00", "targetGpu": "Biren_166m", "taskId": "4986615", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.595651+00:00", "targetGpu": "Biren_166m", "taskId": "4986618", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "submitTime": "2026-09-20T19:48:14.592812+00:00", "targetGpu": "Biren_166m", "taskId": "4986614", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "modelId": "Arain119/Sophia", "submitTime": "2026-09-20T19:48:14.640908+00:00", "targetGpu": "Biren_166m", "taskId": "4986612", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.646752+00:00", "targetGpu": "Biren_166m", "taskId": "4986611", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.636564+00:00", "targetGpu": "Biren_166m", "taskId": "4986617", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.643458+00:00", "targetGpu": "Biren_166m", "taskId": "4986613", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "submitTime": "2026-09-20T19:48:14.653000+00:00", "targetGpu": "Biren_166m", "taskId": "4986616", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "submitTime": "2026-09-20T19:48:14.673114+00:00", "targetGpu": "Biren_166m", "taskId": "4986619", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.736283+00:00", "targetGpu": "Biren_166m", "taskId": "4986620", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T19:48:14.739365+00:00", "targetGpu": "Biren_166m", "taskId": "4986621", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T19:48:14.745647+00:00", "targetGpu": "Biren_166m", "taskId": "4986622", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.804006+00:00", "targetGpu": "Biren_166m", "taskId": "4986623", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}

14
manifest.json
View File

@@ -9,16 +9,16 @@
".modelhub_state/queue_cleanup_latest.json": "51060760318808c95c5f937aac9389cef4379d95a33f6213764b0f798b1c6bb9", ".modelhub_state/queue_cleanup_latest.json": "51060760318808c95c5f937aac9389cef4379d95a33f6213764b0f798b1c6bb9",
".modelhub_state/recent_outcomes.jsonl": "f394f77eaff8b342a5cc3752aeb626cc40c67ebb881842f93954228dc015a15c", ".modelhub_state/recent_outcomes.jsonl": "f394f77eaff8b342a5cc3752aeb626cc40c67ebb881842f93954228dc015a15c",
".modelhub_state/recovery_active_tasks.jsonl": "db0594b4f6cac381cf7845c3047272c8428a8df9382a26021c216d47c0a10897", ".modelhub_state/recovery_active_tasks.jsonl": "db0594b4f6cac381cf7845c3047272c8428a8df9382a26021c216d47c0a10897",
".modelhub_state/recovery_intents.jsonl": "54982d0b39338e3b61031616ef35812406a5db37ca95ebf99f340247c3da049f", ".modelhub_state/recovery_intents.jsonl": "cba90f74e0bca9e450a1e4332d7e3c91c1ec8a15601474099f4ee54d4328b7d7",
".modelhub_state/routing_intelligence.json": "f4d5b8b9dcb1c204c6e1e30971a11d9cc28844fec061d5b484f538c84028653c", ".modelhub_state/routing_intelligence.json": "a79c843de34a5eca511f88fcac5f1b15b626a9c97e9cf1acbf03dec7b4d95675",
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
"ledger/submissions.jsonl": "9e95f17de83962dfc513d832d7bbcf17f7092ff95ecd233437f99450f89c1aa8", "ledger/submissions.jsonl": "2e47bb95528a475acf6d2e246df34b447f7afe008892a662495f77dba95a3bec",
"outcomes/submissions.jsonl": "57412b23adc88734193f2ef77bb3041c569eec6af94f635bbd9bf92d0ec385e2" "outcomes/submissions.jsonl": "58e870da542fcd286c6e2826018db47dcb9ec0f5e7b0f76d2a0c3733347ec5c6"
}, },
"generation": 10838, "generation": 10839,
"phase": "intent", "phase": "result",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-20T19:48:06.386167+00:00", "updatedAt": "2026-09-20T19:48:15.100482+00:00",
"writerId": "fc715c06e24c4db2ae3e425e435db996" "writerId": "fc715c06e24c4db2ae3e425e435db996"
} }

26
outcomes/submissions.jsonl
View File

@@ -1086,3 +1086,29 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6711252896, "estimatedRequiredGiB": 7.503, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6713123803, "modelscopeLicense": "mit", "modelscopeParams": 3355609600, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6713123803}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:31:34.206245+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986333", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6711252896, "estimatedRequiredGiB": 7.503, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6713123803, "modelscopeLicense": "mit", "modelscopeParams": 3355609600, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6713123803}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:31:34.206245+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986333", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:37:15.014300+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4986407", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:37:15.014300+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4986407", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:46:10.235701+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986586", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:46:10.235701+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986586", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.523364+00:00", "targetGpu": "Biren_166m", "taskId": "4986607", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683241105, "estimatedRequiredGiB": 23.138, "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": 20703487237, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703487237}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.450477+00:00", "targetGpu": "Biren_166m", "taskId": "4986598", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.484978+00:00", "targetGpu": "Biren_166m", "taskId": "4986604", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.473777+00:00", "targetGpu": "Biren_166m", "taskId": "4986599", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "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": 20703971805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703971805}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.509974+00:00", "targetGpu": "Biren_166m", "taskId": "4986606", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.502504+00:00", "targetGpu": "Biren_166m", "taskId": "4986605", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.472448+00:00", "targetGpu": "Biren_166m", "taskId": "4986601", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.461438+00:00", "targetGpu": "Biren_166m", "taskId": "4986600", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.486486+00:00", "targetGpu": "Biren_166m", "taskId": "4986603", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "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": 16313701503, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.482557+00:00", "targetGpu": "Biren_166m", "taskId": "4986602", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.549308+00:00", "targetGpu": "Biren_166m", "taskId": "4986609", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.535472+00:00", "targetGpu": "Biren_166m", "taskId": "4986608", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.574218+00:00", "targetGpu": "Biren_166m", "taskId": "4986610", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.639695+00:00", "targetGpu": "Biren_166m", "taskId": "4986615", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37184031394, "estimatedRequiredGiB": 41.579, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37204398600, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10061358960, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:mixed-precision", "custom_tag:qwen3.6", "custom_tag:agentic-search"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37204398600}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.595651+00:00", "targetGpu": "Biren_166m", "taskId": "4986618", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.592812+00:00", "targetGpu": "Biren_166m", "taskId": "4986614", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 9.768, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 8740644030, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8740644030}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.640908+00:00", "targetGpu": "Biren_166m", "taskId": "4986612", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.646752+00:00", "targetGpu": "Biren_166m", "taskId": "4986611", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.636564+00:00", "targetGpu": "Biren_166m", "taskId": "4986617", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.643458+00:00", "targetGpu": "Biren_166m", "taskId": "4986613", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25593158704, "estimatedRequiredGiB": 28.626, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 25613691403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7626590448, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25613691403}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.653000+00:00", "targetGpu": "Biren_166m", "taskId": "4986616", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293473597, "estimatedRequiredGiB": 18.233, "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": 16314185171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16314185171}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.673114+00:00", "targetGpu": "Biren_166m", "taskId": "4986619", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.736283+00:00", "targetGpu": "Biren_166m", "taskId": "4986620", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.739365+00:00", "targetGpu": "Biren_166m", "taskId": "4986621", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "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": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.745647+00:00", "targetGpu": "Biren_166m", "taskId": "4986622", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:48:14.804006+00:00", "targetGpu": "Biren_166m", "taskId": "4986623", "taskType": "text-generation", "verifyResult": null}