Adds VIP-llava to transformers (huggingface#27932)

* v1

* add-new-model-like

* revert

* fix forward and conversion script

* revert

* fix copies

* fixup

* fix

* Update docs/source/en/index.md

* Apply suggestions from code review

* push

* fix

* fixes here and there

* up

* fixup and fix tests

* Apply suggestions from code review

* add docs

* fixup

* fixes

* docstring

* add docstring

* fixup

* docstring

* fixup

* nit

* docs

* more copies

* fix copies

* nit

* update test

README.md

@@ -505,6 +505,7 @@ Current number of checkpoints: ![](https://img.shields.io/endpoint?url=https://h
 1. **[VAN](https://huggingface.co/docs/transformers/model_doc/van)** (from Tsinghua University and Nankai University) released with the paper [Visual Attention Network](https://arxiv.org/abs/2202.09741) by Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu.
 1. **[VideoMAE](https://huggingface.co/docs/transformers/model_doc/videomae)** (from Multimedia Computing Group, Nanjing University) released with the paper [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://arxiv.org/abs/2203.12602) by Zhan Tong, Yibing Song, Jue Wang, Limin Wang.
 1. **[ViLT](https://huggingface.co/docs/transformers/model_doc/vilt)** (from NAVER AI Lab/Kakao Enterprise/Kakao Brain) released with the paper [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://arxiv.org/abs/2102.03334) by Wonjae Kim, Bokyung Son, Ildoo Kim.
+1. **[VipLlava](https://huggingface.co/docs/transformers/main/model_doc/vipllava)** (from University of Wisconsin–Madison) released with the paper [Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://arxiv.org/abs/2312.00784) by Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Dennis Park, Yong Jae Lee.
 1. **[Vision Transformer (ViT)](https://huggingface.co/docs/transformers/model_doc/vit)** (from Google AI) released with the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.
 1. **[VisualBERT](https://huggingface.co/docs/transformers/model_doc/visual_bert)** (from UCLA NLP) released with the paper [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://arxiv.org/pdf/1908.03557) by Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang.
 1. **[ViT Hybrid](https://huggingface.co/docs/transformers/model_doc/vit_hybrid)** (from Google AI) released with the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.

README_es.md

@@ -480,6 +480,7 @@ Número actual de puntos de control: ![](https://img.shields.io/endpoint?url=htt
 1. **[VAN](https://huggingface.co/docs/transformers/model_doc/van)** (from Tsinghua University and Nankai University) released with the paper [Visual Attention Network](https://arxiv.org/abs/2202.09741) by Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu.
 1. **[VideoMAE](https://huggingface.co/docs/transformers/model_doc/videomae)** (from Multimedia Computing Group, Nanjing University) released with the paper [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://arxiv.org/abs/2203.12602) by Zhan Tong, Yibing Song, Jue Wang, Limin Wang.
 1. **[ViLT](https://huggingface.co/docs/transformers/model_doc/vilt)** (from NAVER AI Lab/Kakao Enterprise/Kakao Brain) released with the paper [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://arxiv.org/abs/2102.03334) by Wonjae Kim, Bokyung Son, Ildoo Kim.
+1. **[VipLlava](https://huggingface.co/docs/transformers/main/model_doc/vipllava)** (from University of Wisconsin–Madison) released with the paper [Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://arxiv.org/abs/2312.00784) by Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Dennis Park, Yong Jae Lee.
 1. **[Vision Transformer (ViT)](https://huggingface.co/docs/transformers/model_doc/vit)** (from Google AI) released with the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.
 1. **[VisualBERT](https://huggingface.co/docs/transformers/model_doc/visual_bert)** (from UCLA NLP) released with the paper [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://arxiv.org/pdf/1908.03557) by Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang.
 1. **[ViT Hybrid](https://huggingface.co/docs/transformers/model_doc/vit_hybrid)** (from Google AI) released with the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.

README_hd.md

@@ -454,6 +454,7 @@ conda install -c huggingface transformers
 1. **[VAN](https://huggingface.co/docs/transformers/model_doc/van)** (सिंघुआ यूनिवर्सिटी और ननकाई यूनिवर्सिटी से) साथ में पेपर [विजुअल अटेंशन नेटवर्क](https://arxiv.org/ pdf/2202.09741.pdf) मेंग-हाओ गुओ, चेंग-ज़े लू, झेंग-निंग लियू, मिंग-मिंग चेंग, शि-मिन हू द्वारा।
 1. **[VideoMAE](https://huggingface.co/docs/transformers/model_doc/videomae)** (मल्टीमीडिया कम्प्यूटिंग ग्रुप, नानजिंग यूनिवर्सिटी से) साथ में पेपर [वीडियोएमएई: मास्क्ड ऑटोएन्कोडर स्व-पर्यवेक्षित वीडियो प्री-ट्रेनिंग के लिए डेटा-कुशल सीखने वाले हैं] (https://arxiv.org/abs/2203.12602) ज़ान टोंग, यिबिंग सॉन्ग, जुए द्वारा वांग, लिमिन वांग द्वारा पोस्ट किया गया।
 1. **[ViLT](https://huggingface.co/docs/transformers/model_doc/vilt)** (NAVER AI Lab/Kakao Enterprise/Kakao Brain से) साथ में कागज [ViLT: Vision-and-Language Transformer बिना कनवल्शन या रीजन सुपरविजन](https://arxiv.org/abs/2102.03334) वोनजे किम, बोक्यूंग सोन, इल्डू किम द्वारा पोस्ट किया गया।
+1. **[VipLlava](https://huggingface.co/docs/transformers/main/model_doc/vipllava)** (University of Wisconsin–Madison से) Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Dennis Park, Yong Jae Lee. द्वाराअनुसंधान पत्र [Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://arxiv.org/abs/2312.00784) के साथ जारी किया गया
 1. **[Vision Transformer (ViT)](https://huggingface.co/docs/transformers/model_doc/vit)** (गूगल एआई से) कागज के साथ [एक इमेज इज़ वर्थ 16x16 वर्ड्स: ट्रांसफॉर्मर्स फॉर इमेज रिकॉग्निशन एट स्केल](https://arxiv.org/abs/2010.11929) एलेक्सी डोसोवित्स्की, लुकास बेयर, अलेक्जेंडर कोलेसनिकोव, डिर्क वीसेनबोर्न, शियाओहुआ झाई, थॉमस अनटरथिनर, मुस्तफा देहघानी, मैथियास मिंडरर, जॉर्ज हेगोल्ड, सिल्वेन गेली, जैकब उस्ज़कोरेइट द्वारा हॉल्सबी द्वारा पोस्ट किया गया।
 1. **[VisualBERT](https://huggingface.co/docs/transformers/model_doc/visual_bert)** (UCLA NLP से) साथ वाला पेपर [VisualBERT: A Simple and Performant Baseline for Vision and Language](https:/ /arxiv.org/pdf/1908.03557) लियुनियन हेरोल्ड ली, मार्क यात्स्कर, दा यिन, चो-जुई हसीह, काई-वेई चांग द्वारा।
 1. **[ViT Hybrid](https://huggingface.co/docs/transformers/model_doc/vit_hybrid)** (from Google AI) released with the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.

README_ja.md

@@ -514,6 +514,7 @@ Flax、PyTorch、TensorFlowをcondaでインストールする方法は、それ
 1. **[VAN](https://huggingface.co/docs/transformers/model_doc/van)** (Tsinghua University and Nankai University から) Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu から公開された研究論文: [Visual Attention Network](https://arxiv.org/abs/2202.09741)
 1. **[VideoMAE](https://huggingface.co/docs/transformers/model_doc/videomae)** (Multimedia Computing Group, Nanjing University から) Zhan Tong, Yibing Song, Jue Wang, Limin Wang から公開された研究論文: [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://arxiv.org/abs/2203.12602)
 1. **[ViLT](https://huggingface.co/docs/transformers/model_doc/vilt)** (NAVER AI Lab/Kakao Enterprise/Kakao Brain から) Wonjae Kim, Bokyung Son, Ildoo Kim から公開された研究論文: [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://arxiv.org/abs/2102.03334)
+1. **[VipLlava](https://huggingface.co/docs/transformers/main/model_doc/vipllava)** (University of Wisconsin–Madison から) Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Dennis Park, Yong Jae Lee. から公開された研究論文 [Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://arxiv.org/abs/2312.00784)
 1. **[Vision Transformer (ViT)](https://huggingface.co/docs/transformers/model_doc/vit)** (Google AI から) Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby から公開された研究論文: [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929)
 1. **[VisualBERT](https://huggingface.co/docs/transformers/model_doc/visual_bert)** (UCLA NLP から) Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang から公開された研究論文: [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://arxiv.org/pdf/1908.03557)
 1. **[ViT Hybrid](https://huggingface.co/docs/transformers/model_doc/vit_hybrid)** (Google AI から) Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby から公開された研究論文: [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929)

README_ko.md

@@ -429,6 +429,7 @@ Flax, PyTorch, TensorFlow 설치 페이지에서 이들을 conda로 설치하는
 1. **[VAN](https://huggingface.co/docs/transformers/model_doc/van)** (Tsinghua University and Nankai University 에서) Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu 의 [Visual Attention Network](https://arxiv.org/pdf/2202.09741.pdf) 논문과 함께 발표했습니다.
 1. **[VideoMAE](https://huggingface.co/docs/transformers/model_doc/videomae)** (Multimedia Computing Group, Nanjing University 에서) Zhan Tong, Yibing Song, Jue Wang, Limin Wang 의 [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://arxiv.org/abs/2203.12602) 논문과 함께 발표했습니다.
 1. **[ViLT](https://huggingface.co/docs/transformers/model_doc/vilt)** (NAVER AI Lab/Kakao Enterprise/Kakao Brain 에서) Wonjae Kim, Bokyung Son, Ildoo Kim 의 [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://arxiv.org/abs/2102.03334) 논문과 함께 발표했습니다.
+1. **[VipLlava](https://huggingface.co/docs/transformers/main/model_doc/vipllava)** (University of Wisconsin–Madison 에서 제공)은 Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Dennis Park, Yong Jae Lee.의 [Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://arxiv.org/abs/2312.00784)논문과 함께 발표했습니다.
 1. **[Vision Transformer (ViT)](https://huggingface.co/docs/transformers/model_doc/vit)** (Google AI 에서) Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby 의 [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) 논문과 함께 발표했습니다.
 1. **[VisualBERT](https://huggingface.co/docs/transformers/model_doc/visual_bert)** (UCLA NLP 에서) Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang 의 [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://arxiv.org/pdf/1908.03557) 논문과 함께 발표했습니다.
 1. **[ViT Hybrid](https://huggingface.co/docs/transformers/model_doc/vit_hybrid)** (Google AI 에서) Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby 의 [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) 논문과 함께 발표했습니다.

README_zh-hans.md

@@ -453,6 +453,7 @@ conda install -c huggingface transformers
 1. **[VAN](https://huggingface.co/docs/transformers/model_doc/van)** (来自 Tsinghua University and Nankai University) 伴随论文 [Visual Attention Network](https://arxiv.org/pdf/2202.09741.pdf) 由 Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu 发布。
 1. **[VideoMAE](https://huggingface.co/docs/transformers/model_doc/videomae)** (来自 Multimedia Computing Group, Nanjing University) 伴随论文 [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://arxiv.org/abs/2203.12602) 由 Zhan Tong, Yibing Song, Jue Wang, Limin Wang 发布。
 1. **[ViLT](https://huggingface.co/docs/transformers/model_doc/vilt)** (来自 NAVER AI Lab/Kakao Enterprise/Kakao Brain) 伴随论文 [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://arxiv.org/abs/2102.03334) 由 Wonjae Kim, Bokyung Son, Ildoo Kim 发布。
+1. **[VipLlava](https://huggingface.co/docs/transformers/main/model_doc/vipllava)** (来自 University of Wisconsin–Madison) 伴随论文 [Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://arxiv.org/abs/2312.00784) 由 Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Dennis Park, Yong Jae Lee 发布。
 1. **[Vision Transformer (ViT)](https://huggingface.co/docs/transformers/model_doc/vit)** (来自 Google AI) 伴随论文 [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) 由 Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby 发布。
 1. **[VisualBERT](https://huggingface.co/docs/transformers/model_doc/visual_bert)** (来自 UCLA NLP) 伴随论文 [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://arxiv.org/pdf/1908.03557) 由 Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang 发布。
 1. **[ViT Hybrid](https://huggingface.co/docs/transformers/model_doc/vit_hybrid)** (来自 Google AI) 伴随论文 [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) 由 Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby 发布。

README_zh-hant.md

@@ -465,6 +465,7 @@ conda install -c huggingface transformers
 1. **[VAN](https://huggingface.co/docs/transformers/model_doc/van)** (from Tsinghua University and Nankai University) released with the paper [Visual Attention Network](https://arxiv.org/pdf/2202.09741.pdf) by Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu.
 1. **[VideoMAE](https://huggingface.co/docs/transformers/model_doc/videomae)** (from Multimedia Computing Group, Nanjing University) released with the paper [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://arxiv.org/abs/2203.12602) by Zhan Tong, Yibing Song, Jue Wang, Limin Wang.
 1. **[ViLT](https://huggingface.co/docs/transformers/model_doc/vilt)** (from NAVER AI Lab/Kakao Enterprise/Kakao Brain) released with the paper [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://arxiv.org/abs/2102.03334) by Wonjae Kim, Bokyung Son, Ildoo Kim.
+1. **[VipLlava](https://huggingface.co/docs/transformers/main/model_doc/vipllava)** (from University of Wisconsin–Madison) released with the paper [Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://arxiv.org/abs/2312.00784) by Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Dennis Park, Yong Jae Lee.
 1. **[Vision Transformer (ViT)](https://huggingface.co/docs/transformers/model_doc/vit)** (from Google AI) released with the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.
 1. **[VisualBERT](https://huggingface.co/docs/transformers/model_doc/visual_bert)** (from UCLA NLP) released with the paper [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://arxiv.org/pdf/1908.03557) by Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang.
 1. **[ViT Hybrid](https://huggingface.co/docs/transformers/model_doc/vit_hybrid)** (from Google AI) released with the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.

docs/source/en/_toctree.yml

@@ -741,6 +741,8 @@
         title: TVP
       - local: model_doc/vilt
         title: ViLT
+      - local: model_doc/vipllava
+        title: VipLlava
       - local: model_doc/vision-encoder-decoder
         title: Vision Encoder Decoder Models
       - local: model_doc/vision-text-dual-encoder