Add LaVIN model

### Model description LaVIN is a vision-language instructed model that is affordable to train (it was trained in a few hours on 8 A100 GPUs) with good performance on ScienceQA. I'd like to add LaVIN to HF transformers. ### Open source status - [X] The model implementation is available - [X] The model weights are available ### Provide useful links for the implementation The paper [Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models](https://arxiv.org/pdf/2305.15023.pdf) is by [Gen Luo](https://luogen1996.github.io/), [Yiyi Zhou](https://github.com/huggingface/transformers/issues/new?assignees=&labels=New+model&projects=&template=new-model-addition.yml), [Tianhe Ren](https://rentainhe.github.io/), [Shengxin Chen](https://github.com/huggingface/transformers/issues/new?assignees=&labels=New+model&projects=&template=new-model-addition.yml), [Xiaoshuai Sun](https://sites.google.com/view/xssun), and [Rongrong Ji](https://mac.xmu.edu.cn/rrji/) @luogen1996 has made the code and model weights available at [github.com/luogen1996/LaVIN](https://github.com/luogen1996/LaVIN). The weights for the following models are available at the following links: ### ScienceQA | Model | Weights | Time | Memory | #Params | Acc | Weights | |-----------|----------:|----------:|-------:|--------:|-----:|-----------------:| | LaVIN-7B | LLaMA | 1.4 hours | 33.9G | 3.8M | 89.37 | [google drive](https://drive.google.com/file/d/10X2qCBYrLH1grZOHwHRMXLUoz-S6MSgV/view?usp=share_link) | | LaVIN-7B | Vicuna | 1.4 hours | 33.9G | 3.8M | 89.41 | [google drive](https://drive.google.com/file/d/1nuMxeiWlnJKxDybCshg8pVGSvLc5dZy8/view?usp=share_link) | | LaVIN-13B | LLaMA | 2 hours | 55.9G | 5.4M | 90.54 | [google drive](https://drive.google.com/file/d/1LkKUY54spZkkeXrR7BDmU-xmK9YadcKM/view?usp=share_link) | ### Multimodal ChatBot | Model |Weights | Time | Memory | #Params | Acc | Weights | |-----------|------…