diff --git a/models/deepseek-ai/deepseek-r1-0528-qwen3-8b-/metadata.yaml b/models/deepseek-ai/deepseek-r1-0528-qwen3-8b-/metadata.yaml new file mode 100644 index 0000000..f6d4ca1 --- /dev/null +++ b/models/deepseek-ai/deepseek-r1-0528-qwen3-8b-/metadata.yaml @@ -0,0 +1,50 @@ +apiVersion: model.hydra.io/v1alpha1 +kind: ModelSpec +metadata: + name: deepseek-r1-0528-qwen3-8b +spec: + deployments: + - customRuntimeArgs: [] + resourceRequirements: + cpu: 8 + gpuCount: 8 + gpuType: nvidia-vgpu + memory: 640 + perGPUMemoryGB: 80 + runtime: vllm + versionRequired: '>=0.8.5' + descriptor: + description: + enUS: The DeepSeek R1 model has undergone a minor version upgrade, with the + current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 + has significantly improved its depth of reasoning and inference capabilities + by leveraging increased computational resources and introducing algorithmic + optimization mechanisms during post-training. The model has demonstrated outstanding + performance across various benchmark evaluations, including mathematics, programming, + and general logic. + zhCN: The DeepSeek R1 model has undergone a minor version upgrade, with the + current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 + has significantly improved its depth of reasoning and inference capabilities + by leveraging increased computational resources and introducing algorithmic + optimization mechanisms during post-training. The model has demonstrated outstanding + performance across various benchmark evaluations, including mathematics, programming, + and general logic. + display: DeepSeek-R1-0528-Qwen3-8B + icon: + src: https://public-resources.d.run/models/logos/deepseek-model-logo.svg + type: image/svg + links: + - description: About + url: https://www.deepseek.com/ + provider: + id: deepseek + name: + enUS: DeepSeek + zhCN: 深度求索 + tags: + - TEXT_GENERATION + source: + huggingface: + name: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B + modelscope: + name: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B