中国のオープンソースAIエコシステムにおけるアーキテクチャ選択：DeepSeekを超えた構築

Back to Articles Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek

Upvote 45

This is the second blog in a three-part series on China's open source community's historical advancements since January 2025's "DeepSeek Moment." The first blog is available here, and the third blog is available here.

In this second piece we turn our focus from models to the architectural and hardware choices Chinese companies have made as openness becomes the norm.

For AI researchers and developers contributing to and relying on the open source ecosystem and for policymakers understanding the rapidly changing environment, architectural preferences, modality diversification, license permissiveness, small model popularity, and growing adoption of Chinese hardware point to leadership strategies across a multitude of paths. DeepSeek R1's own characteristics inspired overlap and competition, and contributed to heavier focus on domestic hardware in China.

Mixture of Experts (MoE) as the Default Choice

In the past year, leading models from the Chinese community had almost unanimously moved toward Mixture-of-Experts (MoE) architectures, including Kimi K2, MiniMax M2, and Qwen3. R1 itself was an MoE model, it also proved a crucial point: strong reasoning could be open, reproducible, and engineered in practice. Under China's real-world constraints, maintaining high capability while controlling cost, and ensuring models could be trained, deployed, and widely adopted, MoE emerged as a natural solution.

MoE is like a controllable compute distribution system; under a single capability framework, compute resources are allocated across requests and deployment environments by dynamically activating different numbers of experts according to task complexity and value. More importantly, it does not require every inference to consume the full set of resources, nor does it assume that all deployment environments share identical hardware conditions.

The overall direction of Chinese open-source models in 2025 was clear: not necessarily the strongest possible performance, but ability to operate sustainably, deploy flexibly, and evolve continuously, achieving the best cost performance balance.

The Rush for Supremacy by Modality

Starting in February 2025, open-source activity was no longer focused only on text models. It quickly expanded into multimodal and agent-based directions: Any-to-Any models, text-to-image, image-to-video, text-to-video, TTS, 3D, and agents all progressed in parallel. What the community pushed forward was not just model weights, but a full set of engineering assets, including inference deployment, datasets and evaluation, toolchains, workflows, and edge-to-cloud coordination. The parallel emergence of video generation tools, 3D components, distillation datasets, and agent frameworks pointed to something larger than isolated breakthroughs---it pointed to reusable system-level capabilities.

The competition to lead similar to DeepSeek in a non-text modality heated up. StepFun's released high performance multimodal models, excelling in audio, video, and image generation and processing or editing. Their latest speech-to-speech model Step-Audio-R1.1 boasts state-of-the-art performance, beating proprietary models. Tencent also reflected this shift through open-source work in video and 3D. Its Hunyuan Video models and projects such as Hunyuan 3D reflect growing competition beyond text-centric models.

Big Preferences for Small Models

Models in the 0.5B--30B range were easier to run locally, fine-tune, and integrate into business systems and agent workflows. For example: Among the Qwen series, Qwen 1.5-0.5B has the most derivative models. In environments with limited compute or strict compliance requirements, these models were far better suited for long-term operation. At the same time, leading players often used large MoE models in the 100B--700B range as capability ceilings or "teacher models," then distilled those capabilities down into many smaller models. This created a clear structure: a few very large models at the top, and many practical models underneath. The growing share of small models in monthly summaries reflected real usage needs in the community.

![](data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAA9oAAAG/CAYAAACnsa+HAAAQAElEQVR4AeydB5wURdPGn9m74wAFRRT1Nbzm9OlrzgLmnHPOCZGgopjFAAoGkKSikoMSBAwIqIAIYgJRMSIqSM4ZLn/99N7szs5t7mFn967udzXTPd3VXfWfmtA7KVDh49/C5ZsqRISBxIDEgMSAxIDEgMSAxIDEgMSAxIDEgMRAujHg45A2ZtcBZOWfGCUEhIAQEAJCQAgIASEgBISAEBACQiA3CchAO5X1JnWFgBAQAkJACAgBISAEhIAQEAJCQAgkICAD7QSAcqFYbBQCQkAICAEhIASEgBAQAkJACAiB7CEgA+3sWRfVzRLxRwgIASEgBISAEBACQkAICAEhUCMJyEC7Rq72muy0+C4EhIAQEAJCQAgIASEgBISAENiyBHwdaM/61cKI9wNapv9gYcNGoKQ0LFvWdWldCGQRATFFCAgBISAEhIAQEAJCQAgIgWpDwNeBNinOnGmBYlnAgoUW+vTP0/LtDN9No3kiQqBGExDnhYAQEAJCQAgIASEgBISAEEidQNaNZv+dD1BSd0U0hIAQqCEExE0hIASEgBAQAkJACAgBIZDVBLJuoJ3VtMQ4ISAEhEBMAlIgBISAEBACQkAICAEhIASCBGSgHeQgUyEgBIRA9SQgXgkBISAEhIAQEAJCQAhknIAMtDOOXDoUAkJACAgBISAEhIAQEAJCQAgIgepMQAba1Xntim9CQAgIASGQCgGpKwSEgBAQAkJACAgBTwjIQNsTjNKIEBACQkAICIEtRUDaFQJCQAgIASEgBHKNgAy0c22Nib1CQAgIASEgBLKBgNggBISAEBACQkAIxCQgA+2YaKRACAgBISAEhIAQyDUCYq8QEAJCQAgIgWwgIAPtbFgLYoMQEAJCQAgIASFQnQmIb0JACAgBIVDDCKQ00C4rK0N5eUVURBs2bsaatRuqlE2YMgOrVq+rspwLLIvTsARSsiasJykhIASEgBAQAkJACAiBVAlIfSEgBISAENhSBJIe2haXlOK65s+BA2enMUXFJbi/XU+cde2DuPjWx3BTq+exeu36UJWOPYbgn/mLQ3lJCAEhIASEgBAQAkJACAiBmASkQAgIASFQDQgkNdDu1nskml7aEj/9/ncVl4d9MAnLVqzC5yO6YOLwLmi0fQO81m90lXqyQAgIASEgBISAEBACQkAI5CoBsVsICAEhkAqBpAbaLW69BNM+6ImD9v0vLCvyfu9Pv5iOC848EXl5ebrfy85rgk8mf6fT7sn6DZtwV9uXMX7St+4iyQsBISAEhIAQEAJCQAgIASGQGgGpLQSEQJYSSGqgHc/2JctWYudGDUNVmF66YjXKy8tDy5goKipGs0c6Y989d8WZJx/NRSJCQAgIASEgBISAEBACQkAIVDsC4pAQEALGA+216zeidmFBiCTTFRUV4MvR7IWlpWVo/VQP7L/Xbmhz91X2YhTkh6+O5+cFkJ/nzFtoWL8Wdti2UEQYSAxIDEgMSAxIDEgMSAxIDEgMSAyYxYDwq7b8kIV/xgPt+lvXRVFxaci1zUUl+vbyrerWCS17vtsgfD/rD7S87dLQMiZKSys401JeVo4yxxvNy8oqsGZDCVavKxYRBhIDEgMSAxIDEgMSAxIDEgMSAxID1TIGZLxjPt7TA8osmxgPtHfcYTssXLI85NbCxcvQqOG2CATCV6ebHn8YKC0e7wq+vdyuHB5mA7zRXF0It4vAslI12C4RgTCoEAayHUgMSAxIDEgMSAxIDEgMSAxIDGQuBnKKdWgQmUUJ44H26Y2PxOixU1BWVqbdGjHmC5ze+CidtidNjvsfnnvoNuTn56Ft+zdQ7rhybdeRuRAQAkJACAgBISAEhIAQEAJCQAgIgdgEcqckqYF2p57v4NQr7sPsv+bjyZd66/SKVWu0l1ec3xQNt6uPppe11ssXLVmBZjdeqMuck4KCfLz6TAvMm78Ez3cf5CyStBAQAkJACAgBISAEhIAQEAJCQAgIgdwkEMXqpAbaD91zNSYM64yZn76NqaO763TDBtvo5goLa6Hrsy0xZsALGNarHQb1eBwNtq2nyzgZN+RFHH7wvkxi663qYMRbz+CxltfrvEyEgBAQAkJACAgBISAEhIAQEAJCQAhUNwJJDbSTcbp+va1gD76Tqe+oEzO5dh2wZm1YYlaUAiEgBISAEBACQkAICAEhIASEgBAQAllCIJAldkQ1Y+UqC/0G5WmZPjPTpkY1SRYKASEgBISAEBACQkAICAEhIASEgBCISyDrR68rVgDLlsX1oWYVirdCQAgIASEgBISAEBACQkAICAEhkNUEsn6gndX0xLgQAUkIASEgBISAEBACQkAICAEhIASEQJCADLSDHGRaPQmIV0JACAgBISAEhIAQEAJCQAgIgYwTkIF2xpFLh0JACAgBISAEhIAQEAJCQAgIASFQnQnIQLs6r13xTQikQkDqCgEhIASEgBAQAkJACAgBIeAJARloe4JRGhECQmBLEZB2hYAQEAJCQAgIASEgBIRArhGQgXaurTGxVwgIgWwgIDYIASEgBISAEBACQkAICIGYBHJqoL1gkYV/F4QlpldSIASEgBCokQTEaSEgBISAEBACQkAICIFsIJBTA+2yMqDfgICWn362soGf2CAEhIAQEAKJCEi5EBACQkAICAEhIARqGIGcGmhz3VRUAEXFTIkIASEgBISAEEifgGgKASEgBISAEBACQmBLEci5gfaWAiHtCgEhIASEgBDIAgJighAQAkJACAgBIVANCMhAuxqsRHFBCAgBISAEhMCWJSCtCwEhIASEgBAQAqkQkIF2KrSkrhAQAkJACAgBIZA9BMQSISAEhIAQEAJZSkAG2lm6YsQsISAEhIAQEAJCIDcJiNVCQAgIASEgBHJ6oL1goYUfZoVFVqcQEAJCQAgIASEgBIRAVAKyUAgIASEgBDJIIKcH2uQ05uMAhr8XwJ9/yee+yENECAgBISAEhIAQEAK5Q0AsFQJCQAhUTwI5P9CunqtFvBICQkAICAEhIASEgBDwjYB0LASEgBAwJFCtBtpLlgFD1dVtWwzZiLoQEAJCQAgIASEgBISAEMgaAmKIEBACuUOgWg20iX3uPAs/zbJQVCS3kpOHiBAQAkJACAgBISAEhIAQ2IIEpGkhIASiEIgYaJeWlkWpEly0ctVaNXgtDmZc04qKCixdvgrl5eWukmB2w8bNWLN2QzCTwemKVcCI9wMhKS4BVqplttCUTZsBW5gXEQJCQAgIASEgBISAEBACQiDXCYj9QsBfAqGB9pJlK3Hc+c2qDIgXLF6OS297Alfd/TROufw+PNdlQMSAetp3s9D00la4ufULOPGiezFy7JSQR0VqZHt/u54469oHcfGtj+GmVs9j9dr1ofJMJOapK9wzZ1pYudLCxo3AwHfz0G9wHt4dkad8BfoMyAsJTfvxZwu2cECeCRulDyEgBISAEBACQkAICAEhIARqAAFxscYQ0APtOx98CWdd9xA2FVW9Yt2pxxCceMwh+OTdl/Hp0JcxbfrPmDh1pgZUVlaGtu17of3Dd2DMwI4Y0PVRtO/SH7z6zQrDPpiEZeqy8ucjumDi8C5otH0DvNZvNIt8lZUrIrtftAhQruiFX30TwLARAXw2KYCApqMXy0QICAEhIASEgBAQAkJACAgBIVAtCYhT3hPQQ8leL7bB1FHddeuW49HmkpJSfD5tJi47t7Euq1unNs465RiMn/ytzs/4abYajFpofOwhOr/PnrviwP32wIQvgwPxT7+YjgvOPBF5eXm6/LLzmuCTyd/pdC5MOND+4OMAbFm6PBesFhuFgBAQAkJACAgBISAEhIAQEAI5TyCnHdAD7VgerFy9FiXqUu/OjRqGqjC9ZNkqned8J0cZFwbLVzKJJctWgnmdUROml65YHXHruVqc1f+rV1v45lsLv/1uIT8PmPpVICTL1MD7tz9UWaUsWmphwcKwLFrs+NUiq70U44SAEBACQkAICAEhIASEgBAQAkIgMYHkasQdaK9bv1G3UqtWgZ5zUqewFuzla1R5bZXncltqFxaEytfq8rAuy/jiNL4cjfXzA+GBaJ66lJ7nyDMZkVcL8vPC9QOw1MA3wGa0KHUU5IfzXJgoX6sgsn6tKvrh/thevipftAQYO97CF1NU/yr/198BDHongOHvBZCvLoH/MSeAfoOCAmXjtG8CeH9MnpZ/5gWwVe28CKlXNx8iwkBiQGJAYkBiQGJAYkBiQGJAYkBiQGIgvRhAFv4F4tlUb+u6uri4pFTPOeFz3PXrBZdvo8r5wjMut2VzUQnq19tKZ+vr8lKd5oRllmVhq7p1mEWFnoYn7ny4pGoqat2oC6vq2ksqUqxv69nzWOqbNgHFRXYt4NvvgsLfCaZ+U4H3PoSWH36uwC9/lEcIX9xOu0QAYSAMJAYkBiQGJAYkBiQGJAYkBiQGJAYSxUB45JU9qbgD7e22rY9a+flYtGR5yOKFi5frl5pxwY47NIgo47LI8u2wMEJ3GRo13FY/1826ZeXhoWqZolfuyDPpLGdZaVm4foUappeWhT8nptRR4siz/ZLScHmCPItRXKV+uD9WKFXl7IdpSpnKlzsWlKpRMu1kGaVM2asWMamFPlKmfAlQ6N+adRV4s4+lZfnKCqxcU4oVq8OyflMpRISBxIDEgMSAxIDEgMSAxIDEgMSAxIDEQPQY0IOtLJvEHWgXFOSjyXGHYsRHX2izN27ajLGTvsEZjY/S+SMO2RdlanD7xVc/6Pzsv+bjtz/n4tQTDtP50xsfidFjp6g6we9zjxjzBU6v1NUVZKIJcKxOURf7MW++hT4D87TM+DGADRuB9RvCohVkIgSEgBAQAkJACAgBISAEhIAQEAJZS0APtK9r/hzOv/FhbeRFtzyGG1t20GlOHmx2tX7z+BlXP4DTrrwfxxx2IE496XAW6beJP//oXXi4Qy+cd8PDuL5Fezzc4nps16C+Lr/i/KZouF19NL2sNU694j519XsFmt14oS6TSWwCCxYAFNZYttxC30F5Wr6bEdAD8Q/HBkAZ+0lAD8JXrQZsoQ6/0mYL856LNCgEhIAQEAJCQAgIASEgBISAEBACMQkEWDKox+P6O9c/T+yr5/27PsrFWnb9zw54v18HDOr+OD599xU83eZmBAJaTZefdMzB+GJUd/Tq9ACmju6Oy89ropdzUlhYC12fbYkxA17AsF7twH4abFuPRSIpEFi6BFiyOKww43sLX38TfFHbmjUW+g3K0zLpiwCWLAP6DMjTMmxkHlasBLjcls1FAD9TZgtbtQflnDOfqyJ2CwEhIASEgBAQAkJACAgBISAEsoFAeMScwJpG2zfAVnVrR60VCFjYZecdkJ+fF7WcL0dr2GCbqGWy0JzApo3AihXhdtatC18R59IZMy18NtHCn3MsbN4MvDMsODB/b3Qe1qwND8w5QN+4iRoiHhKQpoSAEBACQkAICAEhIASEgBCoYQSSHmjXvsFbmQAAEABJREFUMC7V3t21a8Iu8oVtvFW9tBQoLVMDb3WFvE+lrFsPfbs6nx2nrHbohVuQVO4REIuFgBAQAkJACAgBISAEhIAQ2FIEZKC9pcjmcLslRcBfc4A1q4NOTJgcQN8BAbw7IqA/uTX0vQAGvpunZZm6km4/H845X9wW1JKpEEiDgKgIASEgBISAEBACQkAICIFqQEAG2tVgJWbChZKSyF5+/x34d0Fw2ZRpAf2MOJ8VX7/OAgfmtixYYOHvuZES1JKpEMgdAmKpEBACQkAICAEhIASEgBBIhYAMtFOhJXVjEuAz4uvXB4vLy4CJkyxM/iL4wrYFCy307hfQws+YBWvJVAgIAUMCoi4EhIAQEAJCQAgIASGQpQRkoJ2lK6a6mpWXB3z3fQCfTgzK77Mt/PSLBfut6DN/Cg7Oq6v/4pcQqP4ExEMhIASEgBAQAkJACAgBGWhLDPhC4HN1tZtid/7ZREu/Gd1S4+w//gzffv71dxKiNiOZCwEhYEBAVIWAEBACQkAICAEhkEECMorJIGzpKnkCvPWcQg2+cG3ZcsAWLhMRAkJACFQHAuKDEBACQkAICAEhUD0JyEC7eq7XauXV+vUW+g3O0/LLbxKy1WrlijNCQAhkIwGxSQgIASEgBISAEDAkIKMWQ4CinhkCa9eEPzc2918Ls34Ny6bNwNp1YcmMRdKLEBACQkAIZJaA9CYEhIAQEAJCIHcIyEA7d9aVWOog8N7IAN4dFgA/H7ZypYW+g/K0fDYpgMVLLUz+MhCS5SuBH2ZZISmvcDQkSSEgBISAEBACJgREVwgIASEgBIRAFAIy0I4CRRblHoH16or2sqVhu7/62sInn1r4d4GlF346MYDh7wXw7XQJeQ1EJkJACAgBIVCtCYhzQkAICAEh4C8BGXX4y19694HAmrXAmPGBkDD/2ecB2LJhow9GSZdCQAgIASEgBKo/AfFQCAgBIVBjCMhAu8asanHUSWD2HAvTvrIw79/gFe/ffrcw6XMLv6p5eTnAz4rZsm49MPMnC7asWg1wcG4LnxF3ti1pISAEhIAQEAJCIJcIiK1CQAgIAe8JyEDbe6bSYjUg8MOPFj4cowbjXwcH4t//GMCIkQHwFnS6N/aTPPQbFJQNG4DfZ1shWbgoqMN6IkJACAgBISAEhIAQSIuAKAkBIZDTBGSgndOrT4z3k8CyZcCmTUELfvvDwsAhAf0ceCAP+GRCAO+OyNOyYKGFOX+H5Z95Ftaqq+ROCbYiUyEgBISAEBACQkAIZDcBsU4ICIHkCMhAOzlOUksIpExg1s/Ab78H1RYtttB3QECLpS54//5HAP0G5mlZrMp+/FldPf82gGlKmF69FnBKsBWZCgEhIASEgBAQAkJACEQhIIuEQNYRkIF21q0SMaimEFi6FKDY/o752AKF+SVLLNi3pv8xWzZTMhERAkJACAgBISAEhEBuERBrazIBOYOvyWtffM9qAsuXARQa+fdcC/bL2Dhfu05d8V4TlpISYOOmsFBHRAgIASEgBISAEBACQkAIVCEgCzJCQAbaGcFcPTuxyqunX9nqFV/GRlm7zsKq1Rb6DsrT8vW3ASxZpvIDVV7J+M8C4K3qg4blgTJkeB6WrQC+/CYQkmz1UewSAkJACAgBISAEhIAQqJkEqpvXMtCubmtU/KkxBNauBlYsD7u7ahWwaFE4v2A+8Nuv4fyXX1n4eKyFX3+zsFpdDe+jBuq2rFFXyKd+FYAt6zcAfGmbLcw7hZ9AC7csKSEgBISAEBACQkAICAEhUC0JpO1U0gPt8vIKlMc4u66oqMDS5atilm/YuBlr1qoz97TNFEUhIAS8JrBGDbb/mgMUFwVbnvmjhbHjLXCuNmmM+zSA3v0CGPVhcDfBt6jbV9HXqoE5r5Tzijllubpi/u8CC7YsXwksXmqFhHnnre1MB3uVqRAQAkJACAgBISAEhIAQqH4EgmfQSfj1QvfBeKH7kCo1p303C00vbYWbW7+AEy+6FyPHTgnVKSouwf3teuKsax/Exbc+hptaPY/V/KZRqIYkhIAQyGYCHHA77VuyGNi8ObyEV8x55ZxLpn9vod+AAPoPCqC0zMIPauDONKWoyMJ33wfQd2CeliVqEE4dESEgBISAEBACQkAICAEhUB0JJBxoT/pyJk65vDUGj/y0iv9lZWVo274X2j98B8YM7IgBXR9F+y79sXLVWl132AeTsGzFKnw+ogsmDu+CRts3wGv9RusyPyfStxAQAluGQFFxZLvr1JXvzZvCy3hrOyUvD/hmekB/zoyfNJs9xwJf+OaUsJakhIAQEAJCQAgIASEgBIRAbhFIONA++YTD9CD5xivOAr//63Rvxk+zEQhYaHzsIXrxPnvuigP32wMTvpyp859+MR0XnHki8nhWrZZcdl4TfDL5O5WS/ygEZJEQqHEE+DkzCh3n7ei8VZ2ybj2XiAgBISAEhIAQEAJCQAgIgdwkkHCgHc+tJctWYadGDSOq7KzyS5at1Ms4Z15n1ITppStWx3yWW1WR/6wjIAYJgcwTUL/fhZ7vtp/1zrwV0qMQEAJCQAgIASEgBISAEEiPgNFAe836jahdWCui59qFBVinlnPhWjVnnmkK03xxGl+OxrzzCjkNceaZprAehWmefDNtS4BKdkbNq+YttTT8H3A14M7nJSgPqP5oh90i084eAlYF4FjAcndeNQH7j+WO6tB5xwJ3HqpM/dvqYJ42wfHnckHfceAohuWqEHDnrYgeEHDlLacDqmEWOzWsPMVALbf/dX1HBV2fnCorMB+oUl5ZyJkqYx0mtai8rq8zaqLyEeVqUSAQaUPAVaGKzwHViNKz/6uUJ9Cnj84qOg7sxtRclzm6YJ6iivQ/0xSdUROmKSqp/5mm6IyaMB1hsmrbmdflrvXg9smylJJqy/53l7vzlpWoPuCsohk4VBg2znKmKaj8Y5pSmdVt8WVtfL6bMn9B8NbyzyYHQJnyVUB/4mzFSgu25OdZyM8PS4FKi1gQBsJAYkBiQGJAYkBiQGKguseAfQ6ZTXOe/6ZtzzZb10VRcUmE/uaiEtSvt5VeVl+Xl+o0JyyzLAtb1a3DLPIdo4OAOkl2DnSZjihXejyR1opqElD5gryw+e481El+LXWiraqG/mvlh+tzYeK8akT9sy6lQOk7suqkPgArEF6Sr+wJWJH5vEA4zzT9ZFuUPPqcF2BSS56qS9EZNclTbTnzHPzk54Xbsyy10yhw5ZWNSjX0z40qlFEJt8+Frvq1CsL2qOqoklf1Vbcs0qKZKLt1Rk00A4eNzDt9yFPKEfk8C4FAuM88d7lq2+lznisfUPULHDZblmKSF26PdBIxKHAwhPpzM3Iz0O05fiwoUP1ZFnsClDrosxWIzOc58kznhU1EvirLC4QX5Kt0nlrGtigBlXbn8/PC7QdU3+yTdSmWpRjkh9vjslrubaEgsrywSv3I8qgM2HCl6DhQ/VZmUZAXiPiRJl/1Rz/s8nxlvzOvt4VAuM+ASucFLPAZb0qeKspT+UmTLFCY3rTJQp+BAS3f/xjAwkUBTPs6LMuWW/h3fiAkAbVTKC7Kgy30qW5hHmzZqnY+ttmqQEQYSAxIDEgMSAxIDEgMSAzkWAzY55jZNA+YGLPjDg2waInjQ76qsYWLl+uXnqkkdtxhOyx0lC9cvAyNGm6LgDphZnlJWfjKY6lKU7icwrSzvKy8AsWl4frlFRUoKilnVS3uPFTVzcXhclbaXFzGWUjc+U1VypW+asdWKFLtKTPsLEpU/+WOBbTPmS8pLUeZ8stWoE+UUF75U1qm+qhcUKrqUiqzKFVtO/PlqtzJpEKVFxWFDeTdAk4mbIc2c25LkcvHqj7HZ8T2FHq7ORS7GJQUV4B22hXIKIKBsrnU0UWpm4EuD/tE3RJVx26PeXK28+RdrNaLnQ8yCOsz5Way2cWgqCi8DtiOu9ydL2J/FeGBrpsB7eO6YVuUkqhxwJKgcJ2WOuKgRKVL1boOlkLHkDvPPuxyzUD14cwXOeICADbTZruCmhe5GCSKA3d9zUC1Y/8zTztCebXOnHky4rqzy0tUuTPvjoMyFwPGjJsB29iwHlizGiBv9jH+U+D9j4CFiyuwaXMF+g0GevUGPp8KzF9cjh5vVWjp+04F5i8qQ5deFSFZvqYEy9cUiwgDiQGJAYkBiQGJAYkBiYEciwH7HDOb5kYD7SMO2VcNAsrxxVc/aJ9m/zUfv/05F6eecJjOn974SIweO0XVCY6sRoz5Aqc3PkqXyUQICIGaTiAz/peEb6rB5iJgyZJwvxyk/zUHKFHLN2wEhr4XCMkmx2fMwhqSEgJCQAgIASEgBISAEBACiQkkHGiP//w7nHrFfRj+4USM/HiyTk+YMkO3nJeXh+cfvQsPd+iF8254GNe3aI+HW1yP7RrU1+VXnN8UDberj6aXtdZ6i5asQLMbL9RlMhECQkAIZBuBpcst/DTLAm87LylBaNDNAfi6DZH51Wsj83xpW7b5I/YIASEgBISAEBACQkAI+EMg4UD7zKZHYcKwzvhmzBtamD71pCNC1p50zMH4YlR39Or0AKaO7o7Lz2sSKissrIWuz7bEmAEvYFivdhjU43E02LZeqFwSQkAICIFsJrBylYWf1MB70ZLgowJr1wXz/y4I5kvKgvl/5looyK/Ad98HQrJgYbCOV/5JO0JACAgBISAEhIAQEAK5QyDhQDsZV/jM9S4774D8/Lyo1flytIYNtolaJguFgBAQAtWFwL/zgdEfWBj/qYW8fIC3n9viem8kqsmfuCEEhIAQEAJCQAgIASEQhYAnA+0o7coiISAEhECNJmBZFZg8JYC+A/O08Hb06T9YsGXefAtz54XlX5VfsRJwSo0GaOS8KAsBISAEhIAQEAJCwF8CMtD2l7/0LgSEQDUnsHAhsGxp0Mn16yyMGh3A6PeDu14+191nQACU4mKAt6T3G5QHCst+/d3CpC8CWnhb+l//WLDzU6YF9EB99hwLtgR7kWnWEhDDhIAQEAJCQAgIgRpDIHi2V2PcFUeFgBAQAtlFoKyMn3AL27RqFUCxl3w20QIlVn7QOwH0HxQcdM9XV8V/+8OCLdThLeu2MC8iBNwEJC8EhIAQEAJCQAh4T0AG2t4zlRaFgBAQAr4RGD4yAA6+eZV70WJLXS3P0zLqgwCWLgf+/MsKiW9GSsdCIDEBqSEEhIAQEAJCIKcJyEA7p1efGC8EhIAQiE9g5Wpg/vxwnZFqwN1vYABTvgpglSrrOzgPtqzfAPDZcVv4ibOwpqSEgBAAhIEQEAJCQAgIgeQIyEA7OU5SSwgIASFQLQmsXgXM+RMo3gyUlgHvfxRAvwEBfPhxQL81/ZMJAdiyYSOweg1gC29Jt9Ocby6qlojEKSGQ/QTEQiEgBISAEMg6AjLQzrpVIgYJASEgBPwlwAG0bcGcvy1MnmKBL2YrLweGj8xD30FB2bQJ+HBsMM1lHIiPVgN1W5YsA8DUTbcAABAASURBVMZ+EoCdX7gk/OI23tr+zzzL7kbmQkAIVEMC4pIQEAJCoCYTkIF2TV774rsQEAJCIA0CK5YD5erqt63KfElxMMfB+HfTLfzyS3gQzfwPPwbzCxZa+uVtAwYHkJcH/D3XCsncf8Npe3mwVZkKASEgBDwjIA0JASEgBDJCQAbaGcEsnQgBISAEhEA0AvyMWe9+AVD4Bnbegs40ZdNm6Cvpn08JgDL9h+BgPVo7skwICAEhkNsExHohIASqGwEZaFe3NSr+CAEhIASqGYFPJ1ig0C3eym6/vG3qVwHwBW5r1wO2bNwUTnMZdUSEgBAQAkIgTQKiJgSEQNoEZKCdNjpRFAJCQAgIAT8I8OVtFPa9fIWFfgPztHw7PYAVK8P5yepK+MJFFr78JhCSNWsBPjtuy8aNkXk+n26XcV5RwV5EhIAQEAJCIJsIiC1CIBcIyEA7F9aS2CgEhIAQEAIxCfAZ8aVLw8VrVgPO/OTJFj4ea2HBQoBvRu8/KA+U8Z/m6fzgocH86A/zwCviQ0cE8yNGBcs5WLelqPJZ9HBvkhICQkAICAEhoAnIRAhEEJCBdgQOyQgBISAEhEBNILBWXdl2+hkrX1IC/db0/oMCGD46gGI10P5wbAC2rFmHUJrLVq4C7EE550uXO3uRtBAQAkJACAiBTBOQ/vwiIANtv8hLv0JACAgBIZAzBPjpMtvYRYstfP2Nhdl/Bl/OtmpVMP/rb8H8tG+Db1bn4BwVwDI12LaFL3uz03q+0m5V5kJACAgBISAEahCBGuCqDLRrwEoWF4WAEBACQiCzBDgwt5/v/nZGAP0G52nZuNnCT7+E85s2WuDb1Z2SWUulNyEgBISAEBACQsAm4OVcBtpe0pS2hIAQEAJCQAhEIcDnxjdtCBcwv24tYKmL4N//GEDfgXlaFi+x8M88C7bM/deCnY41h/wJASEgBISAEBACWUfAw4F21vkmBgkBISAEhIAQyAkCCxcCFBq7YhXQp39AC1/Oxqvjdn7laqC0NFy+cLEFvjmdnzmzhW2ICAEhIASEgBAQAv4SqP4DbX/5Su9CQAgIASEgBFImUF4OUGxFpinR8kuXW+g7SF0RV/LN9AAWLLIwb35YFi8Np7l8+UpElNttylwICAEhIASEgBDwjoAMtL1jmVJLUlkICAEhIASEgFcEli0FliwOtlZWBvQbENAy6xcLZeoK+KAhwfy3M1Relb87PJj//As5DQhSk6kQEAJCQAgIAW8JyBHWW5653prYLwSEgBAQAtWEQHFJpCOJ8pG1JScEhIAQEAJCQAiYEJCBtgk90c0QAekmlwhYuWSs2CoEhAD4TPjb/fNgCz9BZqc5LypGxJvRBZkQEAJCQAgIASGQmIBnA+2ysjKUl1dE7XHDxs1Ys9bxutWotWShEMgxAmKuEBACQqCaEFi7FvjnH6jjeNAhvoDtn3+AYjXI3rwZsN+Kzvna9cE6MhUCQkAICAEhIARiE/BkoF1cUorrmj+HCVNmRPRUVFyC+9v1xFnXPoiLb30MN7V6HqvlCB3BSDJCwGsC0p4QEAJCwGsCFRXBt6Lzjed5eVWvcG9Sg3FbvO5b2hMCQkAICAEhkIsEjAfa3XqPRNNLW+Kn3/+u4v+wDyZh2YpV+HxEF0wc3gWNtm+A1/qNrlJPFggBIVDtCYiDQkAIVBMCZWXAgCF5oavca9cBw0eG83yreTVxVdwQAkJACAgBIZA2AeOBdotbL8G0D3rioH3/C8uKfDrz0y+m44IzT0Qef/5WJl52XhN8Mvk7lZJ/ISAEhEA2EBAbhIAQSJfAwoXA5qKwNvPr1wMBCxg2KoCB7+ZpWbYc+HBsOL9oqYXPPg/n5y+wMPWrcP6feRam/2BpXbbxy++qwXA3khICQkAICAEhkBMEjAfa8bxcsmwldm7UMFSF6aUrVqPc+THQUKkkhIAQEAJCQBOQiRCoBgR+/x2Y/2/YEeb/cdz8xvyfsyPLucxewjQloM5UZv1qYcq0gJaZP1mYPSecn/ZtAByc2+Wcz5sfLmfeblPmQkAICAEhIAQyRUAdvrZcV2vXb0TtwoJQB0xXVFSAL0fjwlr54V+pC/ICKHDk8/Ms1MoPwP7LU/nCgnA+oH4yLywM6wfU1fTatcLlUEV1CvNsdT2vUzt+vm6tfF3Pnmh91Y6dr63aYz92vpbqj3aE8spe2hnKK3vph50voI9KQnnlL5eF8qosgkHAgrOcbTuZsG8nA8uyEMFANax9UHP7v06tPDup53WVTzpROalbGIVBZRlnhaq+6oZJLYVuBoUBBNS60oVqUisKg3zltyrS//TX6SPTXKYL1SRftVVLcVVJ/U8GVeJA9aEL1cSyyCC80phK5HMd5ZNSDf3XKYzPgHEAqyJU382gsMAC1w0q/xgn9KMyq9dpvqML+lug1n2oXPnLZXY+XzFw56swUOvBrs++6zi2Db0tOMpZz+1z3QQMarvKazOOCJeNKanN9a7iVSX1f20Xg0LlE/3QhWpSy5WnfwVqmSrS//mKB5fpjJrkK14FioNK6n+2xTZ0Rk3os5tJ7QgGFVW2jdoun+rSJ9WW/Z+ICePKgUC3b1nhJbSHdtntkQHj15mnH3Y+X/lfoPy280wXOLaVfJWOyCsetRyxz+0uIq/WR6FaL3Z7NK22Kw6qMHAxqePK1y5UK8JuUM2rlCuGlhVmwP6cDGrl58HJoJbyOV/ZqZrS/wXKf4rOqAnTTp/debbFNlRV/c88ueuMmrBvJ4OAso02qaLgvzLV7UPV9Z4XrFs5rVMYyaAuGal2KotBpuzHzlfZP+RFMmBc5Kt1adfPdzGo5VrvBSxXy8L1rWp/rNQMlN/jPrFAsRkwTWEMcdn4T4PlFRUWCvMDmDDJ0vU3bLSwenUeli7ND8n6DYFQmsu3q1eAHRsUiggDiQGJAYmBHI0B+7iYTfPAljSm/tZ1UVRcGupic1EJLMvCVnXr6GUlpeHBSmlZOZz5srIKlS/X9TgpZ77EkS+vQLFDv7yiAkWOcqimi4rD9dnGZle+qCiyfFNJGauFRLen2rEXFBWXgf3Y+WLVX7myw86XlJaDdjvzpY7yUnUln36GypVPzjzTJQ6fypRuieJi19d51Yedpy1OBvwRY7OyyS7nfJMrX6XcxWRzUSSDza7yYsVAoWbTWopVuZNBsbKP60oXqkmJypcqP1RS/9OfModPJWSguOhCNSGDUgcD6pY46pMB+1BV9X+QQXg9koFeb7oUDAO4fXb7VCVOEjDQ7asTucoudNxVOHykfU4mJYoR/bDr0x8+4xjOV4DL7HwpmSkuobxqu9TBpEyVsQ+7XDNQfdh52lKk2rDzhFBU4ghkVbDJUV9l4WayWa1nLrelyFW/iHHlaJJ59huqr8ppl52nvbTbzrvjolT5VOqwuVSt8xK1zK5PXs48ebINu5y8nT7TliKnz2p9bXYwpJ7bJ/e24mZU5GaifHQgCMaBY+OgzxEMVJwzftk3pVj5SD+YppQp/+k305RSVd/pc5mqX+LwoVTFRYnSYV0Ktzu2yTRFM3Hs42hakbKZZba4GWx21Gedza71Xuxi4N62itQ+lNsgdSluBiWqPIKBst+ZL1E+RjBQ+RJHHLCs1JGnbklZObvSUqbKih0+kgH3UbpQTbg+IhioFbjZUV9VqbotuJhscjMgI9UOdSlFqpz9ME3RDNS6YppSUloGriumKcVkoOxmmlKqfKYwTSlR67xUCdMUlnEZ0xT6XKLaYJrCtkscPmkGDn3a5mZQJQ7oExurlCI3A7UeK4v0TLcXj4Gyh3boympCe2m3Sup/5hnPOqMmpSr26adK6v8SZb8zzzSX6UI1qRIHije5qiL9z743Kh/e7leBXr0rMPXrcmzYVI5+g4P58RMrsHpDKZatKY4ry9cUQUQYSAxIDEgMZGcM6B1+lk226EB7xx22w8Ily0MuL1y8DI0abhu62uc4LnMsEKrHBMsoTFOYDg+nuEQNoiLHhOCJZLAkOOUJRTAVnPLkO5gKTquUuxrgwTlYMzh1FSsDgsvtKW2005zr+o6FzDuyWt+Zd6a1PidOURXUf3iJylS4GFQBqU44wgqqSxrhWOA8KebiclcD7nKXuqu2asFlj66v7FQlof8KNegJZ2hTKKfbi6iuMhVKQjVUOm5eVaxwtq/zSknN7X/3enfnK7QVdm3aF6nvjiNWd9ao0j+bclZQ+Qpn3plmGcW5TKXVv1oa/Gfarc9lwVJlr0qUlzkusTEfoaAWuPJVGLjKq8aBs0fVp9o4nUsqoPqvUP1U/jNJqcwSmVKycyqpCtV/eAFTjgUuc5SC/metsDjrq6UVyiY1C/+nuC24fXYzcufdNuq80yba48wzTam0kElKZTa4P3MsqHDFNSFWOMq1HvvQiegTd/0qPrJRh2qVclcD7m3BVQw1XopYUdoFl82ubIQFukxPgkYxGdGHWhCRV9XUIjUN/1cpd1Vw+1BlvUZYpNp1NVilfqh9VVf9u+OwPHLT0K27VPQypar/WUbRGTVxplVW13UuY9odBu7jhMsFVPHBta1UKXc1sKWPlfSJQn8pznS0PKFUqVN5bCoqpoaSygp2ftnyCgwZFgjJytWR+Y2bKqB+AxFRwSUcIHEgcSAxkIUxoPbsWfe/RQfapzc+EqPHTlFXeYNHuBFjvsDpjY/KOghikBAQAkJACAiBGkFAnIxJYMFCYNbPwLp1wSpLlgbzq1YDlvqBZKm6bmBLafC0BvInBISAEBACQiAWAeOBdqee7+DUK+7D7L/m48mXeuv0ilVrdH9XnN8UDberj6aXtdbLFy1ZgWY3XqjLZCIEhIAQEAJCQAgIARLIdtm8OfgJs36D8jB0RB42qXy22yz2CQEhIASEgL8EjAfaD91zNSYM64yZn76NqaO763TDBttorwoLa6Hrsy0xZsALGNarHQb1eBwNtq2ny2QiBISAEBACQkAICIEsJlDFtLXB6wjIU2dP/y6wYMuGTQiluWyNuirOuS0r1VVxO805r4xzbgs/eWan7XmVzmWBEBACQkAI5BQBdajY8vbWr7cV7MH3lu9NehACQkAICAEhIASEwJYjwFvHPx4XQL8BAYwYFUB5GfS3wZl/Z3gwP+0bS5cPGhIAX+g488dgvt9AVV5q4fc/KvOqjfISYO68cL5E5WNbLyVCQAgIASGQCwQCuWCk2CgEhIAQEAJCQAgIgWwjYL9MzbYrnTwH7U59tpGXByxfGZYVq8Jp5/J46ZXqKrqzfM3ayDbsPj2bS0NCQAgIASEQQUAG2hE4JCMEhIAQEAJCQAgIAf8J/MMr3IPywOfCly23sGixuuJdmV+w0MLKleH8nL8CWLcunP/5l8j89BkBrF8fLv9ias05/fN/TYoFQkAI1FQCsqetqWte/BYCQkAICAEhIASymsBqdSWbYhvJNCVWfo26iu0s37AOcOaLNkfm7XZknnEC0qEQEAI1gIAMtGvAShbjsSjiAAAQAElEQVQXhYAQEAJCQAgIASHgJLB4qYVv1ZVuW3ibuZ3mnB+Q4dwW3tLu1Jd0dSQgPgkBIeAlARloe0lT2hICQkAICAEhIASEQI4QmPi5hfc/tPDHHEtbPHlqMP/DT8H8l18H89O/D+Z1JZkIgUwTkP6EQI4SkIF2jq44MVsICAEhIASEgBAQAkJACAgBfwhIr0IgEQEZaCciJOVCQAgIASEgBISAEKjhBDZvBv74U139rpR16+PnV62OLOfL3Go4QnFfCGSCgPSRRQRkoJ1FK0NMEQJCQAgIASEgBIRAthL4ZEIAAwYHMF7NaeOkycH8mHHB08mpXwfz748J5r//IZgf+X4wTx0RISAEaiKBmumz7PlyeL1X5LDtYroQEAJCQAgIASEgBISAEBACQsA3Alu4Yxlob2HA0rwQEAJCQAhUTwLyY2f1XK/ilRAQAkJACAgBLwikO9D2om9pQwgIASEgBISAEBACQqAGECgoqMBf/1gh4efFnPkFC8NlXD7338j8P/Mi83/PjcxTx73M3UYNwCwuCgEhkEUEqtlAO4vIiilCQAgIASEgBISAEBACIQI//WyhT/8AhrwbPP2c81cwz+e+WWnhomCedZhfsTKcLy4G1m+A1mc5X8ZWUhLOL18R/AQZyyjz1cCdbQwcHNA6s/8MlnOZiBAQAkIgEwSCe7pM9FST+xDfhYAQEAJCQAgIASEgBISAEBACQqDGEJCBdo1Z1VUdlSVCQAgIASEgBISAEBACQkAICAEh4D0BGWh7z1RaNCMg2kJACAgBISAEhIAQEAJCQAgIgZwmIAPtnF59YnzmCEhPQkAICAEhIASEgBAQAkJACAiB5AjIQDs5TlJLCGQnAbFKCAgBISAEhIAQSIoAX5A27tMAbFm02AqluWzZCkTkV6+JzK9ZF5nnC9moZwtf1manOXfrL3e1v3hZZP8LFlmY/GXYvnnzLXwzPZyfPcfCD7PCOj/+LC94S2rFSyUh4BOBnB1oy/dLfYoY6VYIJEFAqggBISAEhIAQyEYC382wMOVLC5s2B6374adgfuXq4KD1p1+CeQ7KWePXP4J5fl6M+T//CuY5Z57L2R7rMU895tkO82yXefbDPPtlnnYwT2H+62+C/dt5LmOawjSFaQrTFKZFhIAQyF4COTvQzl6kYpkQEAJZSkDMEgJCQAgIASEgBISAEBACGSEgA+2MYK5mnYR/dK1mjok7QsAPAtKnEBACQkAICAEhIASEQHUjkLGBdmlpWXVjJ/4IASEgBKovAfFMCAgBISAEhIAQEAJCIG0CGRlofzp5Oq6486m0jRRFISAEhIAQEAIkICIEhIAQEAJCQAgIgVwgsEUH2stXrsE517dF63bdc4GF2CgEhIAQEAJCIB0CoiMEhIAQEAJCQAgIgQgCW3Sgvf122+DjgR3R/blWsCx5sDeCvGSEgBAQAkJACGxRAtK4EBACQkAICAEh4BeBLTrQ9ssp6VcICAEhIASEgBDIUgJilhAQAkJACAiBGkDA14F2fl74KndewEJenHxAlRc4y9UV8oL8sPkqi1oF4TxU07Uc5VB/tWo5ylW+0J136qty3Z5qRyX1P/tTZug0J/mq/QA7ZkYJ/aGdKqn/6U9EPmCBfqLyj+WUyqwuYxvOvLM+28pXbdjlAdU3bbLzcOdVQUE0n9Ry+7+wVp6d1PPC/EhGbob02YEEBXkB1W14SX6BBdqFyr+8fAu0G5V/+QFL+YnQH/2n2AvyWO5YzwGVdpazLWccBNw+63zYHqbcPhQmYOKOEx0HtoFqrvNWhUoF/zWTAHuqzCubLSucp/20O1gK5KvyPAf2POYd+m4G0fIFiqvdXkD1VZAXsLOwAhZq1Qr3zwI3gwIXg0RMIuJMNVig1rOahf7ZHvu1F3AdBaywDfnK3ryAI+/22Z1XdZ318xQvZ54885WO3Z9lWcjPD9hZ0JYIG9X6oo2hCiqh16Oa2/+JGETbNsIeIdi/FV5CewIReQu0G5V/tJ/xXZkF004f8wMW8hw+5gWAPLUMlX9si21UZvV2xz7tvGUpJo71pLIwZeBmViWfr4xkR5VGFKi8ZVmVOSBfpWm3vYD2O31imhIqV/5GMrDgzLMttoHKv2A+UJlDkIkj1lVzVY8TjnIqun1KiplFzaAEfQ6mOWU+oPxmmpKfB9BOpin5ah07fWaawjIKyylMU1jmZODOs21uf6xLYd+0gWkKTYnw0QLc+wf3PrDQ52NlfsCKWO/0uQoTVQeVf2TgLA8op50M1EELEXmlx/WsZqH/hEzyw3FGJXd9bosKLYu0FOQFVLfhJflq26RdulBN3MfKvIAFCir/8plXsVKZ1WXOOND7D0c5GcSLA2WMYhC2hym3D4n2ie44iYgrZajOq32vSup/zUT5oTNqkq/stSz2rDLqn/7QbpXU/8zn5emknuSp+k4mTHOZLlSTaPmC/HD7AdVXQV5A1Qz+WwGrWhwrKyoUJIe48wErsjw/LzKv17tDv3ZhAHDmuf078+7yFPM6rhzt6W3Rkc+z8iP6txxlTrvipd0MLET6nJeIgcc+u5nqfarDryoMAi4GLvvj+W6XJWQQiGTitsFto9sH03yhK27c/eenwwDZ96e2Jv+MqgiPVdRGVQFnvkJl1H/IOFYt56RyCcvKOanMc1YeUQGIW64UysrVxPFf5m6PeWefqq4jq+1VVqullf+qvrscCC9RxSrrzlfqqhl9jnBBKah/VRL8pyYlmAtOI32sQAQDVaXC2aDKu8vLXOVRGSi90L8yQP07syodXkIfwjmAzUfkde3wEu2fnqgC9a/1w8Wg/Y5iTdOdr8LAWUG1GVkOuH0ud8VBeZnDAOrTCTW3/3X9ivDBW3enJ8EaFdrKYJpTFjlbZHP0k2UUXc4JM0pY5sgqhqpFRwMsq3DYzKIIH1UF93qOKFd9VCl3tKeK4S6nTVxui2ZgZ9RcdQnoicqof2VxBIWKsohikIHTJqo6+2Cafqmm9L/OOxYwSR1dWDlhncqk7szZPtT6cvtUJdbdDFwdRLSnOnLnaZPqWJUE/6keXFaZJ4NgUk9ZrkHonJqoyk4fNEO1TJXo/6p5uNVV3qEApaE70eoqp+oTfDCrp24f3PtEV3W1ip3tR9mWdLGe6PYd3Yfy4VJlj8pE+Bw1r1WDE9Wg+g+m9ZQ+6oSeKPUIG1WpK6/6dDqlFNwM3LHtzrv3Hzqv2tEGqEmkfao/VRaxrNzS60JV1f8si2DApVzIuRImKSoZ/FcZ9R9Mqyl1I/JqWYSLqv+qPqqFqp7+V8m45aqSOy6qbDs0QLWjqup/Jik6oybBYscStcCRU+tIVXJQUcWoXMiCYIlDgT5H+qjWtLNcaek21Jz/LIr0sQLu/QHbZF1bIutD1bdLgvOoDIJFeursnwuCuxdawhyUexVBv4JZ0J9wKcspeomuoVOORmmvIws24Myzvjsf6VOFUmEt3byeRJbD92Ml7aef2jg1qZqvUBxVQeU/7Wedyqwuq+7HSktF0ew5Fej5FrRM/6Ecc+eF81O/AebND+c/nQT8uyCcf//jCsxfHM6/+x6w0JHvMxhYujJc3qsPs