仓库议题
lucasjinreal/LLaVA-Magvit2
LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.
议题
此仓库没有已索引议题。
仓库议题
LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.
此仓库没有已索引议题。