Add OtterHD model description

app.py

@@ -109,6 +109,8 @@ title = """
 # OTTER-HD: A High-Resolution Multi-modality Model
 [[Otter Codebase]](https://github.com/Luodian/Otter) [[Paper]]() [[Checkpoints & Benchmarks]](https://huggingface.co/Otter-AI) 
 
+**OtterHD** is a multimodal fine-tuned from [Fuyu-8B](https://huggingface.co/adept/fuyu-8b) to facilitate a more fine-grained interpretation of high-resolution visual input *without a explicit vision encoder module*. All image patches are linear transformed and processed together with text tokens. This is a very innovative and elegant exploration. We are fascinated and paved in this way, we opensourced the finetune script for Fuyu-8B and improve training throughput by 4-5 times faster with [Flash-Attention-2](https://github.com/Dao-AILab/flash-attention).
+
 **Tips**: 
 - Since high-res images are large that may cause the longer transmit time from HF Space to our backend server. Please be kinda patient for the response.
 - The model is currently mainly focus on high-res image resolution and need to be futher improved on (1) hallucination reduction (2) text formatting control and some more you can spot and suggest to us.