相关的文章推荐
deepseek-ai/DeepSeek-V4-Pro | vLLM Recipes
模型介绍
- hf模型权重
deepseek-ai/DeepSeek-V4-Pro · Hugging Face
| Model | #Total Params | #Activated Params | Context Length | Precision | Download |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash-Base | 284B | 13B | 1M | FP8 Mixed | HuggingFace | ModelScope |
| DeepSeek-V4-Flash | 284B | 13B | 1M | FP4 + FP8 Mixed* | HuggingFace | ModelScope |
| DeepSeek-V4-Pro-Base | 1.6T | 49B | 1M | FP8 Mixed | HuggingFace | ModelScope |
| DeepSeek-V4-Pro | 1.6T | 49B | 1M | FP4 + FP8 Mixed* | HuggingFace | ModelScope |
实验方案
1. 实验器材
2台8XH200机器才能完整部署DeepSeek-V4-Pro模型