Baidu Geek Talk
Apr 2, 2025 · Artificial Intelligence
DeepSeek-VL2 Multimodal Model: Architecture, Training, and Code Walkthrough
DeepSeek‑VL2 is a state‑of‑the‑art multimodal model built on a Mixture‑of‑Experts architecture that combines a SigLIP‑L vision encoder with dynamic tiling, a two‑layer VL adaptor, and a DeepSeek‑MoE language model using Multi‑head Latent Attention, trained in three stages on diverse visual‑language and text data, and achieving strong results on benchmarks such as DocVQA and TextVQA, with full implementation and inference code available in PaddleMIX.
CodeDeepSeek-VL2Inference
0 likes · 36 min read