{"Code":200,"Data":{"AigcAttributes":"{}","AigcIsTop":0,"AigcType":"","AlreadyStar":false,"ApplyMeta":"{}","ApprovalMode":0,"ApprovalNotifyEmail":"","Architectures":["BailingMoeV3ForCausalLM"],"Avatar":"https://img.alicdn.com/imgextra/i1/O1CN01yhHrHg1Pdl3UKPhGc_!!6000000001864-2-tps-88-88.png","Backbone":[],"BackendSupport":{"architectures":null,"backend_info":{"deploy_task":null,"lmdeploy":null,"lmdeploy_turbomind":null,"ollama":null,"sglang":null,"vllm":null},"model_id":"inclusionAI/Ling-3.1-flash-1019"},"BaseModel":null,"BaseModelRelation":"","CardReady":0,"CardUnreadyReason":"","CertificationCreateBy":"","CertificationCreatedTime":-62135596800,"ChineseName":"","CoverHeight":0,"CoverImages":[],"CoverWidth":0,"CreatedBy":"systemd","CreatedTime":1793100211,"DashSdkParameter":"","Datasets":{},"DemoAvailable":0,"DemoUnavailableReason":"","Description":"","Domain":[],"Downloads":11,"ExampleCodeAvailable":0,"ExampleCodeUnavailableReason":"","ForbiddenVisibilityUpdate":false,"Frameworks":["pytorch"],"FromSite":"github","Id":1618240,"Integrating":0,"IntegrationFailureLog":"","IntegrationFailureReason":"","IsAccessible":1,"IsCertification":4,"IsHot":0,"IsNewModel":false,"IsOnline":1,"IsPreTrain":0,"IsPublished":1,"IsTop":0,"Language":[],"LastUpdatedTime":1793103109,"Libraries":["safetensors","pytorch"],"License":"mit","LicenseLink":"","LicenseName":"","Meta":"","Metrics":[],"ModelDetail":{},"ModelInfos":{"safetensor":{"chat_template":"","files":[{"name":"model.safetensors.index.json","sha256":"f01006f7a65eb4b32b66ba60868ef7cc1642c66afe658cb7e6faf80eb246b468","size":20536895},{"name":"model-00001-of-00054.safetensors","sha256":"5f328cbc5019f3f6cd5bd42559044b0fd37b24463c6cbb31854a7b4b77ecdb63","size":10722295762},{"name":"model-00002-of-00054.safetensors","sha256":"d1b9ebf155408b627ee8bfb9e169207797ae8ff227e28db5ba834855dfc5df0d","size":10632563942},{"name":"model-00003-of-00054.safetensors","sha256":"8fb13f432ca16c7031f239017f179e24a2f2a39af04b9c44b561a8ca9400b02d","size":10698613146},{"name":"model-00004-of-00054.safetensors","sha256":"d6eb8031ea1571a515216ceeb3b2a217f05937366df599131aa9252c19713701","size":10698612846},{"name":"model-00005-of-00054.safetensors","sha256":"04abcd05e824bed0fc94e1b773d2eaeefedb92461f1e064f0c948a6f15e63f9b","size":10698612786},{"name":"model-00006-of-00054.safetensors","sha256":"add206466e507fb22e837b924baf26cfe1f5833deb9366d8a985d25970119cd9","size":10698613146},{"name":"model-00007-of-00054.safetensors","sha256":"caf97ef852bbb051ed5d163e49c85e1694ce2fc080a0d82f81390dafa73fdf7d","size":10698616158},{"name":"model-00008-of-00054.safetensors","sha256":"52e754070db006f32f689f72a32380a50eee0aca13201eb9c8ff68a49d3a8ad1","size":10698616818},{"name":"model-00009-of-00054.safetensors","sha256":"27b8f5186a97303ea33be2beab9f7a79c088272ac8a546473dd49a6fa6ff727f","size":10698617226},{"name":"model-00010-of-00054.safetensors","sha256":"d1e6d4cc716bf627805ce059c50e6392307a7645d120e340ff3785c5af9262dc","size":10698617022},{"name":"model-00011-of-00054.safetensors","sha256":"dfb42a1cb77446caa2e6a9fa4883c8c3f36e3ae31f6b15e6154c97d2cf8b5458","size":10698616770},{"name":"model-00012-of-00054.safetensors","sha256":"b724d21597f6fd8c5200a08d91fd53efb5a69454607e92963bec688ec51af2f2","size":10698617226},{"name":"model-00013-of-00054.safetensors","sha256":"a06364c4ee581437fc765b0f7b08f90e638144af56d1d766f6d7d09af58fa34a","size":10698617070},{"name":"model-00014-of-00054.safetensors","sha256":"65df83ea6a9a1fb1d8818325980a2bfa6f3eeb49b8e5aa06f6b0504ed193b8e7","size":10698616722},{"name":"model-00015-of-00054.safetensors","sha256":"1b069c181c3ca0ec7b1cc48689b3145fdf89cc40358cd091eaeb911d5a5597d6","size":10698617226},{"name":"model-00016-of-00054.safetensors","sha256":"bb5adacfe3fa2eb731a552db4c45e53a7891d1a81144602edd60a07972a2b135","size":10698617130},{"name":"model-00017-of-00054.safetensors","sha256":"1a3ab46333caff93bc99ec762c86c7cc40d623e4bdfda28ff1404cc6aba1a746","size":10698616662},{"name":"model-00018-of-00054.safetensors","sha256":"887c421d77fc6102430407374f0d5ece4741a4affa76cf14d066f28c2cf43af4","size":10698617226},{"name":"model-00019-of-00054.safetensors","sha256":"3e0a26dbb10d2e1d6d1f776cf3b772324d058146329860b2e7739595a604e881","size":10698617226},{"name":"model-00020-of-00054.safetensors","sha256":"0e30adc5d6a9b56888dfddddea5e9988fd0708528fd779484f48db21edb4c4a0","size":10698616566},{"name":"model-00021-of-00054.safetensors","sha256":"c2805a248a8f87b5d29d5cc897affb0c5074a6224d9dead9b83924c4563879a6","size":10698617226},{"name":"model-00022-of-00054.safetensors","sha256":"f38a4b26773273daf59b3a4fd3ae12b407e80a58c63c244eafa1f21dae1c72dc","size":10698617226},{"name":"model-00023-of-00054.safetensors","sha256":"ebae73d14f0622ed03d580b0d23bb62fec7a1e9caf538e5c675f83c7e318ebac","size":10698616566},{"name":"model-00024-of-00054.safetensors","sha256":"e2374395648bf59fd67c1265be5af0f850d243359d8cd7d61336cff9afb6297c","size":10698617226},{"name":"model-00025-of-00054.safetensors","sha256":"86f33b270887a0d3a45f9f852741930677aec334a411a5cd7d519296ed8af427","size":10698617226},{"name":"model-00026-of-00054.safetensors","sha256":"7edd6ef7f8dfa66040fff255ef3cb426a27eb9fcb9fddc1f6d404c07c300e916","size":10698616566},{"name":"model-00027-of-00054.safetensors","sha256":"f520d1646087335d0c8dbd20e1590eab0ddfe6866fcffe59106ebbb4d8b5085e","size":10698617226},{"name":"model-00028-of-00054.safetensors","sha256":"0a13108bdef80de971b1fbb0f5c73cfd42bca50cb8a2563d10ac50d404406bec","size":10698617226},{"name":"model-00029-of-00054.safetensors","sha256":"8836ee02e036e1f3c4b930155ba2f224512d8b1226c2e11292584da81e845b0e","size":10698616566},{"name":"model-00030-of-00054.safetensors","sha256":"71bcb5aa40ae7ad63e709f7813d94c94bd222df1d04b9fb227d6d65acd7332f5","size":10698617226},{"name":"model-00031-of-00054.safetensors","sha256":"75731635b97a297fd06d28c85f753d9f136a02d19b8cd07f33e8f604d5207424","size":10698617226},{"name":"model-00032-of-00054.safetensors","sha256":"d5604ba9a0523fdb75aa191d7ff5b7b26c76fb3309e07b65b5a6e255bbb41f7d","size":10698616566},{"name":"model-00033-of-00054.safetensors","sha256":"d0fd011efd7f88b1e0bc6d239fd7db3af53ee190468db725324a447246c14f8d","size":10698617226},{"name":"model-00034-of-00054.safetensors","sha256":"a576375f4e9f209e26b6d913420b7382cc2cda260155f719cdfc1fbb166b13a5","size":10698617226},{"name":"model-00035-of-00054.safetensors","sha256":"94e62b2f78a38861826d02a60768c814cc59828a15a41b3dd1b58028b512a8ef","size":10698616566},{"name":"model-00036-of-00054.safetensors","sha256":"8c7130a8702f3abe88d4cb46d5655a7938df2d7d9a6ac8e1b756a815b1edc1c6","size":10698617226},{"name":"model-00037-of-00054.safetensors","sha256":"9c83d5dbe1fc59ba74a01ef4fae7240d53e2362f01c780d973be8c0a0a5e2161","size":10698617226},{"name":"model-00038-of-00054.safetensors","sha256":"6f528e5344fac1248a568d9d7f41badf97276d5948c9aac992e28640a87d30c3","size":10698616566},{"name":"model-00039-of-00054.safetensors","sha256":"b54dcdb4c4102283d6e0b00c7d64cd5c0019e5f773f4b675da6d8ed6f821cdbd","size":10698617226},{"name":"model-00040-of-00054.safetensors","sha256":"3e2211f13316c3c9f6aca257d285114f55eda5d08b7128ec18b0ec7e5f10a59a","size":10698617226},{"name":"model-00041-of-00054.safetensors","sha256":"d1e94b2b4e8ce926f2c3fb49affd93974330fe5f801824046d71e5d720d41de2","size":10698616566},{"name":"model-00042-of-00054.safetensors","sha256":"15802fb3163818f0efb73c9021241687f5c65160b436d3ea284de443764f8b14","size":10698617226},{"name":"model-00043-of-00054.safetensors","sha256":"7b8fa0480e83e860cb2169bef4dc50cb769fc9a7185695e30d515e98e41bd07b","size":10698617226},{"name":"model-00044-of-00054.safetensors","sha256":"4fa21f2a2eece53d3994f76a9f805f65214eb35a002b0f21b6e32f52de803841","size":10698616566},{"name":"model-00045-of-00054.safetensors","sha256":"fe47ba15d7e4d5b6268b84dc765427eda1c088e45c100020affa7968d93ec8e4","size":10698617226},{"name":"model-00046-of-00054.safetensors","sha256":"43fdcb522f2cf4061d563e865a00f34c4d01076eac99a69941e59c7b721a2323","size":10698617226},{"name":"model-00047-of-00054.safetensors","sha256":"5d0f87df3f9abf7aa1d603bb691f31477022c35dcb0a4ceac4bb84fdf888b4a2","size":10698616590},{"name":"model-00048-of-00054.safetensors","sha256":"fde427bd34c92e975ddd04f493dcc3836a3df188c56119e9b5f7219e168d6c69","size":10698617202},{"name":"model-00049-of-00054.safetensors","sha256":"3e62a823e52749059f2794d4822738cb6ebb59d4b6fb2b5d0056e3da620b819a","size":10698617226},{"name":"model-00050-of-00054.safetensors","sha256":"daf0dfde4af2460882ff024f074127e0b92c5874b263dc3c89734432546648d3","size":10698616638},{"name":"model-00051-of-00054.safetensors","sha256":"ff4a0a4368dcbfdfa1be7b2440bbc43cdf602afc869a8c1d0c5f8a8b67180a07","size":10698617154},{"name":"model-00052-of-00054.safetensors","sha256":"491db54ed4ca879f115020ab0d9226323a1b0ca1a0a09909af5a9123c5a5b6b1","size":10698617226},{"name":"model-00053-of-00054.safetensors","sha256":"196b9076453d396ea08813a6f159de1344cfaa5f1d7542cde1573af5faf46f3b","size":10698616686},{"name":"model-00054-of-00054.safetensors","sha256":"47145c9836804b7ba23b5aed146038d5528761a71e40aca16058cd5bd9339e0e","size":6796768255}],"model_size":572120680768,"tensor_type":["F8_E4M3","F32","BF16"]}},"ModelRevisions":null,"ModelSource":"USER_UPLOAD","ModelTools":"","ModelType":["bailing_hybrid"],"MuseInfo":null,"NEXA":{"Catalogues":null,"ModelCover":"","ScientificField":"","Source":"","SubScientificField":null},"Name":"Ling-3.1-flash-1019","NewVersion":"","NickName":"","OfficialTags":null,"OpenAiSwingDeployInfo":{"Order":0,"Recommend":null,"lmdeploy":{"eas":{"Script":"","requirements":""},"ens":{"Script":"","requirements":""},"fc":{"Script":"","requirements":""},"image_tag":""},"ollama":{"eas":{"Script":"","requirements":""},"ens":{"Script":"","requirements":""},"fc":{"Script":"","requirements":""},"image_tag":""},"pipeline":{"eas":{"Script":"","requirements":""},"ens":{"Script":"","requirements":""},"fc":{"Script":"","requirements":""},"image_tag":""},"vllm":{"eas":{"Script":"","requirements":""},"ens":{"Script":"","requirements":""},"fc":{"Script":"","requirements":""},"image_tag":""}},"Organization":{"ApplyFailureReason":"","ApplyReason":"","Avatar":"https://resouces.modelscope.cn/avatar/5ab3975f-2d94-4dde-922a-f805bfa1ec0d.png","CreateCompetition":false,"CreatedBy":"m1ngcheng","Description":"[\"root\",{},[\"p\",{},[\"span\",{\"data-type\":\"text\"},[\"span\",{\"bold\":true,\"data-type\":\"leaf\"},\"欢迎来到 inclusionAI——蚂蚁集团通用人工智能（AGI）项目的官方主页。在这里，您可以找到大语言模型（LLM）、强化学习（RL）以及其他模型相关系统。\"]]],[\"p\",{},[\"span\",{\"data-type\":\"text\"},[\"span\",{\"bold\":true,\"data-type\":\"leaf\"},\"\"]]],[\"p\",{},[\"span\",{\"data-type\":\"text\"},[\"span\",{\"data-type\":\"leaf\"},\"🤖 \"],[\"span\",{\"bold\":true,\"data-type\":\"leaf\"},\"我们也在致力于打通数字智能与物理世界之间的鸿沟，积极探索具身智能（Embodied AI）的前沿领域。欢迎了解 Robbyant——蚂蚁集团旗下专注于构建具身智能基础平台的组织。\"]]],[\"p\",{},[\"span\",{\"data-type\":\"text\"},[\"span\",{\"bold\":true,\"data-type\":\"leaf\"},\"\"]]],[\"p\",{},[\"span\",{\"data-type\":\"text\"},[\"span\",{\"bold\":true,\"data-type\":\"leaf\"},\"我们热爱开源 ❤️，本组织内的所有项目（模型）均基于 MIT 或 Apache 开源协议。您不得以侵犯、滥用或违反任何第三方权益（包括知识产权）的方式使用相关模型。欲了解更多详情，请参阅各个项目对应的代码库。\"]]]]","DisplayUrl":"","Email":"","FromSite":"","FullName":"inclusionAI","GithubAddress":"","GmtCreated":"2025-02-21T06:39:49Z","GmtModified":"2026-10-20T07:36:26Z","Id":1644,"InitAdminMembers":"","IsApply":false,"IsCertification":"","Mobile":"","Name":"inclusionAI","Path":"","Roles":null,"StarCnt":0,"Status":0,"SubscribeVo":null,"Type":2},"PaiModelGalleryUrl":null,"PaiSdkParameter":null,"Path":"inclusionAI","ProtectedMode":0,"ReadMeContent":"\u003cp align=\"center\"\u003e\n    \u003cimg src=\"https://mdn.alipayobjects.com/huamei_qa8qxu/afts/img/A*4QxcQrBlTiAAAAAAQXAAAAgAemJ7AQ/original\" width=\"100\"/\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e🤗 \u003ca href=\"https://huggingface.co/inclusionAI\"\u003eHugging Face\u003c/a\u003e\u0026nbsp;\u0026nbsp; | \u0026nbsp;\u0026nbsp;🤖 \u003ca href=\"https://modelscope.cn/organization/inclusionAI\"\u003eModelScope\u003c/a\u003e\u0026nbsp;\u0026nbsp; | \u0026nbsp;\u0026nbsp;🐙 \u003ca href=\"https://openrouter.ai/inclusionai/ling-3.1-flash\"\u003eOpenRouter\u003c/a\u003e\u0026nbsp;\u0026nbsp;\u003c/p\u003e\n\n## Introduction\nWe introduce **Ling-3.1-flash-1019**, an upgraded version of [Ling-3.1-flash](https://huggingface.co/inclusionAI/Ling-3.1-flash), with **560B** total parameters, **25B** active parameters per token, and a **1M-token context window**. With further post-training optimizations, **Ling-3.1-flash-1019** demonstrates significant improvements in reasoning and real-world agentic capabilities. Its **AA-Briefcase** score rises from approximately 1400 to **1524 Elo**, while performance on **AutomationBench-AA** increases from 62% to **68%**. The model also makes gains on scientific benchmarks, including **CritPt** (18% → **26%**) and **SciCode** (54% → **57%**). Overall, it scores **44** on the **Artificial Analysis Intelligence Index v4.3.2**, up from 41 for its predecessor. These gains highlight the model's improved capabilities in complex reasoning, multi-step task execution, and agentic workflows across diverse real-world scenarios.\n\n![AA-44](https://cdn-uploads.huggingface.co/production/uploads/65d6aba7dee9f442f8ea7ded/aZ4wSjB4OCgUFnyYINngi.png)\n\n## Model Overview\nThe table and diagram below summarize the model’s specifications and architecture.\n\n| Architecture | Hybrid-linear MoE |\n| --- | --- |\n| Parameter Scale | Total 560B, Activated 25B |\n| Transformer Layers | 63 KDA + 9 Gated MLA (7:1) |\n| Number of Dense Layers | 4 |\n| Number of Routed Experts | 512 |\n| Number of Shared Experts | 1 |\n| Number of Activated Experts | 8 |\n| Attention Heads | 64 |\n| Hidden Size | 4096 |\n| Expert Intermediate Size | 1280 |\n| Dense Intermediate Size | 10240 |\n| Vocabulary Size | 157184 |\n\n![image](https://cdn-uploads.huggingface.co/production/uploads/678143d4ddb1f1ce16daca8e/qwmfVu_K08auI7R_ijbIX.png)\n\n## Quickstart\n### SGLang (Recommended)\n\nThe day-0 SGLang image includes Ling-3.1-flash support, MTP (NEXTN) speculative decoding, and Hopper decode optimizations:\n\n```bash\ndocker pull lmsysorg/sglang:dev-ling-3.1-flash\n```\n\n#### Run Inference\n\n**Server** (8 × H200, TP8 + EP8):\n\n```bash\ndocker run --gpus all --network host --ipc=host --rm \\\n  lmsysorg/sglang:dev-ling-3.1-flash \\\n  python3 -m sglang.launch_server \\\n    --model-path inclusionAI/Ling-3.1-flash \\\n    --tp 8 --ep 8 \\\n    --speculative-algorithm NEXTN \\\n    --host 0.0.0.0 --port 30000\n```\n\nOn 4 × GB300, use `--tp 4 --ep 4` instead. Hopper decode optimizations (optional, ~10% faster batch-1 decode) can be enabled with `SGLANG_ENABLE_FP8_BLOCK_GEMV=1` and `SGLANG_ENABLE_FUSED_KDA_OUTPUT_QUANT=1`.\n\n**Client**\n\n```bash\ncurl -s http://localhost:30000/v1/chat/completions \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"model\": \"Ling-3.1-flash\",\n       \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}],\n       \"chat_template_kwargs\": {\"enable_thinking\": true},\n       \"stream\": true,\n       \"temperature\": 1.0,\n       \"top_k\": 20,\n       \"top_p\": 0.95}'\n```\n\nVerified recipes for H200, GB300, H800, H100, and B200, plus HiCache (Mooncake L3), reasoning on/off, tool calling, and measured accuracy/speed numbers, are in the [SGLang Ling-3.1-flash cookbook](https://docs.sglang.io/cookbook/autoregressive/InclusionAI/Ling-3.1-flash).\n\n### vLLM\n#### Environment Preparation\n```bash\npip install uv\n\nuv venv ~/my_ling_env\n\nsource ~/my_ling_env/bin/activate\n\ngit clone -b vllm https://github.com/vllm-project/vllm.git\n\ncd vllm\n\nVLLM_USE_PRECOMPILED=1 uv pip install --editable . --torch-backend=auto\n```\n\n#### Run Inference\n**Server**\n\n```bash\nvllm serve \"$MODEL_PATH\" \\\n    --port \"$PORT\" \\\n    --trust-remote-code \\\n    --served-model-name auto \\\n    --tensor-parallel-size 8 \\\n    --gpu-memory-utilization 0.85 \\\n    --enable-prefix-caching \\\n    --enable-expert-parallel \\\n    --mamba-cache-mode align \\\n    --enable-auto-tool-choice \\\n    --tool-call-parser ling3 \\\n    --reasoning-parser ling3 \\\n    --speculative-config '{\"method\":\"mtp\",\"num_speculative_tokens\":3}'\n```\n\n**Client**  \nIt is recommended to use the sampling parameters (`temperature=1.0`, `top_p=0.95`, `top_k=20`) and set `enable_thinking` to `true` for better performance.\n\n```bash\ncurl -s http://${MASTER_IP}:${PORT}/v1/chat/completions \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"model\": \"auto\", \n       \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}],\n       \"chat_template_kwargs\": {\"enable_thinking\": true},\n       \"stream\": true,\n       \"temperature\": 1.0, \n       \"top_k\": 20,\n       \"top_p\": 0.95}'\n```\n\n\u003c!-- TDS-LINKS:START --\u003e\n## Training Content Summary\n\nThe public training-content summary identifying **Ling-3.1-flash** is available below. Please refer to the document for its covered model versions, training-content scope, summary version, and update date.\n\n- [Training-content summary (PDF)](https://huggingface.co/inclusionAI/AI-Transparency/resolve/main/Ling-3.1_TDS-Summary.pdf)\n- [Training-content documentation index](https://huggingface.co/inclusionAI/AI-Transparency)\n\nThis summary concerns training-content disclosure; it does not replace the model’s technical documentation, usage terms, or license.\n\u003c!-- TDS-LINKS:END --\u003e\n\n","ReadMeTips":null,"RelatedArxivId":[],"RelatedPaper":[],"Revision":"master","Stars":0,"StorageSize":573813970536,"Studios":[],"SubVisionFoundation":"","SupportApiInference":false,"SupportDashDeployment":0,"SupportDashInference":0,"SupportDashTraining":0,"SupportDeployment":0,"SupportExperience":0,"SupportFinetuning":0,"SupportFlexTrain":0,"SupportInference":"","SupportPaiModelGallery":null,"SupportPaiSdk":0,"SupportPivotEval":false,"SwingDeployInfo":null,"Tags":[],"Tasks":[{"ChineseName":"文本生成","Description":"","DomainName":"nlp","Id":22,"IsExhibition":true,"IsHot":0,"IsLeaf":true,"IsLoginRequired":true,"IsRetrieval":true,"Level":1,"Name":"text-generation","ParentId":-1,"ParentTask":null,"Sorting":0,"SupportWidgets":false,"TypicalModel":"","WidgetConfig":"{\"task\": \"text-generation\", \"inputs\": [{\"type\": \"text\", \"validator\": {\"max_words\": \"1000\"}, \"displayType\": \"OnlyTextArea\"}], \"output\": {\"displayType\": \"ReadonlyText\", \"transformOutputs\": [{\"outputKey\": \"text\"}], \"displayOutputMapping\": \"text\"}, \"examples\": []}","WidgetValidator":""}],"Tools":[],"TriggerWords":null,"Visibility":5,"VisionFoundation":"","_":null,"widgets":[]},"Message":"success","RequestId":"8c9bdde7-8c9c-49f5-8e63-3d6cb83ca310","Success":true}