vl

Here are 3 public repositories matching this topic...

This is an ultra-simple, single-file PyTorch implementation of MoonViT, the native-resolution vision encoder from Kimi-VL.

ai ml transformers torch pytorch attention vit vl torchvision vision-transformer

Billus 大模型技能库：面向 LLM、VL、多模态与图像生成模型的训练、调参、剪枝、量化与工程化技能库

training skill diffusion codex vl peft multimodal huggingface deepspeed llm fsdp qlora

About SkyFind paper reproduction

uav vl grounding

To associate your repository with the vl topic, visit your repo's landing page and select "manage topics."