--- license: mit datasets: - laion/laion2B-en - laion/laion-coco - laion/laion2B-multi - kakaobrain/coyo-700m - conceptual_captions - wanng/wukong100m pipeline_tag: visual-question-answering --- # Model Card for InternVL-Chat-V1.1 Image Description \[[Paper](https://arxiv.org/abs/2312.14238)\] \[[GitHub](https://github.com/OpenGVLab/InternVL)\] \[[Chat Demo](https://internvl.opengvlab.com/)\] \[[中文解读](https://zhuanlan.zhihu.com/p/675877376)] | Model | Date | Download | Note | | ----------------------- | ---------- | --------------------------------------------------------------------------- | ---------------------------------- | | InternVL-Chat-V1.5 | 2024.04.18 | 🤗 [HF link](https://huggingface.co/OpenGVLab/InternVL-Chat-V1-5) | support 4K image; super strong OCR; Approaching the performance of GPT-4V and Gemini Pro on various benchmarks like MMMU, DocVQA, ChartQA, MathVista, etc. (🔥new)| | InternVL-Chat-V1.2-Plus | 2024.02.21 | 🤗 [HF link](https://huggingface.co/OpenGVLab/InternVL-Chat-V1-2-Plus) | more SFT data and stronger | | InternVL-Chat-V1.2 | 2024.02.11 | 🤗 [HF link](https://huggingface.co/OpenGVLab/InternVL-Chat-V1-2) | scaling up LLM to 34B | | InternVL-Chat-V1.1 | 2024.01.24 | 🤗 [HF link](https://huggingface.co/OpenGVLab/InternVL-Chat-V1-1) | support Chinese and stronger OCR | ## Model Details - **Model Type:** multimodal large language model (MLLM) - **Model Stats:** - Architecture: [InternViT-6B-448px](https://huggingface.co/OpenGVLab/InternViT-6B-448px) + MLP + LLaMA2-13B (Our internal SFT versions) - Image size: 448 x 448 (256 tokens) - Params: 19B - **Training Strategy:** - Pretraining Stage - Learnable Component: InternViT-6B + LLaMA2-13B - Data: Trained on 72M samples, including COYO, LAION, CC12M, CC3M, SBU, Wukong, GRIT, Objects365, OpenImages, and OCR-related datasets. - Note: In this stage, we load the pretrained weights of the original [InternViT-6B-224px](https://huggingface.co/OpenGVLab/InternViT-6B-224px) and interpolate its position embedding to the size corresponding to 448 x 448 pixels. Moreover, in order to reduce the number of visual tokens, we use a pixel shuffle operation to reduce 1024 tokens to 256 tokens. - Supervised Finetuning Stage - Learnable Component: MLP + LLaMA2-13B - Data: A comprehensive collection of open-source datasets, along with their Chinese translation versions, totaling approximately 6M samples. ## Model Usage We provide an example code to run InternVL-Chat-V1.1 using `transformers`. You also can use our [online demo](https://internvl.opengvlab.com/) for a quick experience of this model. ```python import torch from PIL import Image from transformers import AutoModel, CLIPImageProcessor from transformers import AutoTokenizer path = "OpenGVLab/InternVL-Chat-V1-1" # If your GPU has more than 40G memory, you can put the entire model on a single GPU. model = AutoModel.from_pretrained( path, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, trust_remote_code=True).eval().cuda() # Otherwise, you need to set device_map='auto' to use multiple GPUs for inference. # model = AutoModel.from_pretrained( # path, # torch_dtype=torch.bfloat16, # low_cpu_mem_usage=True, # trust_remote_code=True, # device_map='auto').eval() tokenizer = AutoTokenizer.from_pretrained(path) image = Image.open('./examples/image2.jpg').convert('RGB') image = image.resize((448, 448)) image_processor = CLIPImageProcessor.from_pretrained(path) pixel_values = image_processor(images=image, return_tensors='pt').pixel_values pixel_values = pixel_values.to(torch.bfloat16).cuda() generation_config = dict( num_beams=1, max_new_tokens=512, do_sample=False, ) # single-round conversation question = "请详细描述图片" response = model.chat(tokenizer, pixel_values, question, generation_config) print(question, response) # multi-round conversation question = "请详细描述图片" response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True) print(question, response) question = "请根据图片写一首诗" response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True) print(question, response) ``` ## Examples In this update, InternVL-Chat has **improved support for Chinese and OCR**. As you can see, although the Lynyrd Skynyrd in the image has some letters that are out of the camera's lens, and TOUR's T is blocked, the model is still able to recognize it correctly. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/-jQ8jCctx1VjkzVxzChQa.png) This model can also conduct an in-depth analysis of AAAI's official website and identify important information on the web page. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/08W04RdT3PmzJuGwFU3--.png) ## Evaluation See [here](https://github.com/OpenGVLab/InternVL/tree/main/internvl_chat#-evaluation) for detailed evaluation results. ## Citation If you find this project useful in your research, please consider citing: ```BibTeX @article{chen2023internvl, title={InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks}, author={Chen, Zhe and Wu, Jiannan and Wang, Wenhai and Su, Weijie and Chen, Guo and Xing, Sen and Zhong, Muyan and Zhang, Qinglong and Zhu, Xizhou and Lu, Lewei and Li, Bin and Luo, Ping and Lu, Tong and Qiao, Yu and Dai, Jifeng}, journal={arXiv preprint arXiv:2312.14238}, year={2023} } ``` ## License This project is released under the MIT license. Parts of this project contain code and models (e.g., LLaMA2) from other sources, which are subject to their respective licenses. Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved. ## Acknowledgement InternVL is built with reference to the code of the following projects: [OpenAI CLIP](https://github.com/openai/CLIP), [Open CLIP](https://github.com/mlfoundations/open_clip), [CLIP Benchmark](https://github.com/LAION-AI/CLIP_benchmark), [EVA](https://github.com/baaivision/EVA/tree/master), [InternImage](https://github.com/OpenGVLab/InternImage), [ViT-Adapter](https://github.com/czczup/ViT-Adapter), [MMSegmentation](https://github.com/open-mmlab/mmsegmentation), [Transformers](https://github.com/huggingface/transformers), [DINOv2](https://github.com/facebookresearch/dinov2), [BLIP-2](https://github.com/salesforce/LAVIS/tree/main/projects/blip2), [Qwen-VL](https://github.com/QwenLM/Qwen-VL/tree/master/eval_mm), and [LLaVA-1.5](https://github.com/haotian-liu/LLaVA). Thanks for their awesome work!