Post
2368
NVIDIA just dropped NVEagle 🦅
Super impressive vision language model that comes in 7B, 13B and 13B fine-tuned on chat 💬
Model repositories: merve/nveagle-66d0705108582d73bb235c26
Try it: NVEagle/Eagle-X5-13B-Chat 💬 (works very well! 🤯)
This model essentially explores having different experts (MoE) for image encoder part of vision language model.
How? 🧐
The authors concatenate the vision encoder output tokens together, and they apply "pre-alignment" essentially fine-tune experts with frozen text encoder.
Then they freeze both experts and the decoder and just train the projection layer, and finally, they unfreeze everything for supervised fine-tuning ✨
In the paper, they explore different fusion strategies and vision encoders, extending basic CLIP encoder, and figure out simply concatenating visual tokens works well.
Rest of the architecture is quite similar to LLaVA. (see below the architecture)
Super impressive vision language model that comes in 7B, 13B and 13B fine-tuned on chat 💬
Model repositories: merve/nveagle-66d0705108582d73bb235c26
Try it: NVEagle/Eagle-X5-13B-Chat 💬 (works very well! 🤯)
This model essentially explores having different experts (MoE) for image encoder part of vision language model.
How? 🧐
The authors concatenate the vision encoder output tokens together, and they apply "pre-alignment" essentially fine-tune experts with frozen text encoder.
Then they freeze both experts and the decoder and just train the projection layer, and finally, they unfreeze everything for supervised fine-tuning ✨
In the paper, they explore different fusion strategies and vision encoders, extending basic CLIP encoder, and figure out simply concatenating visual tokens works well.
Rest of the architecture is quite similar to LLaVA. (see below the architecture)