Update README and paper link in demo

README.md

@@ -2,7 +2,9 @@
 
 *Visual instruction tuning towards large language and vision models with GPT-4 level capabilities.*
 
-[[Project Page](https://llava-vl.github.io/)] [[Demo](https://llava.hliu.cc/)]  [[Data](https://github.com/haotian-liu/LLaVA/blob/main/docs/Data.md)] [[Model Zoo](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md)] [[Community Build Demo on 🤗Spaces](https://huggingface.co/spaces/badayvedat/LLaVA)]
+[[Project Page](https://llava-vl.github.io/)] [[Demo](https://llava.hliu.cc/)]  [[Data](https://github.com/haotian-liu/LLaVA/blob/main/docs/Data.md)] [[Model Zoo](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md)]
+
+🤝Community Contributions: [[llama.cpp](https://github.com/ggerganov/llama.cpp/pull/3436)] [[🤗Space](https://huggingface.co/spaces/badayvedat/LLaVA)]
 
 **Improved Baselines with Visual Instruction Tuning** [[Paper](https://arxiv.org/abs/2310.03744)] <br>
 [Haotian Liu](https://hliu.cc), [Chunyuan Li](https://chunyuan.li/), [Yuheng Li](https://yuheng-li.github.io/), [Yong Jae Lee](https://pages.cs.wisc.edu/~yongjaelee/)
@@ -163,7 +165,7 @@ python -m llava.serve.cli \
 
 *Below is the latest training configuration for LLaVA v1.5. For legacy models, please refer to README of [this](https://github.com/haotian-liu/LLaVA/tree/v1.0.1) version for now. We'll add them in a separate doc later.*
 
-LLaVA training consists of two stages: (1) feature alignment stage: use our 558K subset of the LAION-CC-SBU dataset to connect a *frozen pretrained* vision encoder to a *frozen LLM*; (2) visual instruction tuning stage: use 150K GPT-generated multimodal instruction-following data (with VQA data from academic-oriented tasks) to teach the model to follow multimodal instructions.
+LLaVA training consists of two stages: (1) feature alignment stage: use our 558K subset of the LAION-CC-SBU dataset to connect a *frozen pretrained* vision encoder to a *frozen LLM*; (2) visual instruction tuning stage: use 150K GPT-generated multimodal instruction-following data, plus around 515K VQA data from academic-oriented tasks, to teach the model to follow multimodal instructions.
 
 LLaVA is trained on 8 A100 GPUs with 80GB memory. To train on fewer GPUs, you can reduce the `per_device_train_batch_size` and increase the `gradient_accumulation_steps` accordingly. Always keep the global batch size the same: `per_device_train_batch_size` x `gradient_accumulation_steps` x `num_gpus`.
 

llava/serve/gradio_web_server.py

@@ -280,7 +280,7 @@ def http_bot(state, model_selector, temperature, top_p, max_new_tokens, request:
 
 title_markdown = ("""
 # 🌋 LLaVA: Large Language and Vision Assistant
-[[Project Page]](https://llava-vl.github.io) [[Paper]](https://arxiv.org/abs/2304.08485) [[Code]](https://github.com/haotian-liu/LLaVA) [[Model]](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md)
+[[Project Page](https://llava-vl.github.io)] [[Code](https://github.com/haotian-liu/LLaVA)] [[Model](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md)] | 📚 [[LLaVA](https://arxiv.org/abs/2304.08485)] [[LLaVA-v1.5](https://arxiv.org/abs/2310.03744)]
 """)
 
 tos_markdown = ("""