--- 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-V1.5 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-V1-5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-5) + MLP + [InternLM2-Chat-20B](https://huggingface.co/internlm/internlm2-chat-20b) - Image size: dynamic resolution, max to 32 tiles of 448 x 448 (4K resolution) during inference. - Params: 25.5B - **Training Strategy:** - Pretraining Stage - Learnable Component: ViT + MLP - Data: Please see our technical report. - SFT Stage - Learnable Component: ViT + MLP + LLM - Data: Please see our technical report. ## Model Usage We provide an example code to run InternVL-Chat-V1.2 using `transformers`. You also can use our [online demo](https://internvl.opengvlab.com/) for a quick experience of this model. ```python import json import os from transformers import AutoTokenizer, AutoModel from tqdm import tqdm import torch import torchvision.transforms as T from PIL import Image from torchvision.transforms.functional import InterpolationMode IMAGENET_MEAN = (0.485, 0.456, 0.406) IMAGENET_STD = (0.229, 0.224, 0.225) def build_transform(input_size): MEAN, STD = IMAGENET_MEAN, IMAGENET_STD transform = T.Compose([ T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img), T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC), T.ToTensor(), T.Normalize(mean=MEAN, std=STD) ]) return transform def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size): best_ratio_diff = float('inf') best_ratio = (1, 1) area = width * height for ratio in target_ratios: target_aspect_ratio = ratio[0] / ratio[1] ratio_diff = abs(aspect_ratio - target_aspect_ratio) if ratio_diff < best_ratio_diff: best_ratio_diff = ratio_diff best_ratio = ratio elif ratio_diff == best_ratio_diff: if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]: best_ratio = ratio return best_ratio def dynamic_preprocess(image, min_num=1, max_num=6, image_size=448, use_thumbnail=False): orig_width, orig_height = image.size aspect_ratio = orig_width / orig_height # calculate the existing image aspect ratio target_ratios = set( (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if i * j <= max_num and i * j >= min_num) target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1]) # find the closest aspect ratio to the target target_aspect_ratio = find_closest_aspect_ratio( aspect_ratio, target_ratios, orig_width, orig_height, image_size) # calculate the target width and height target_width = image_size * target_aspect_ratio[0] target_height = image_size * target_aspect_ratio[1] blocks = target_aspect_ratio[0] * target_aspect_ratio[1] # resize the image resized_img = image.resize((target_width, target_height)) processed_images = [] for i in range(blocks): box = ( (i % (target_width // image_size)) * image_size, (i // (target_width // image_size)) * image_size, ((i % (target_width // image_size)) + 1) * image_size, ((i // (target_width // image_size)) + 1) * image_size ) # split the image split_img = resized_img.crop(box) processed_images.append(split_img) assert len(processed_images) == blocks if use_thumbnail and len(processed_images) != 1: thumbnail_img = image.resize((image_size, image_size)) processed_images.append(thumbnail_img) return processed_images def load_image(image_file, input_size=448, max_num=6): image = Image.open(image_file).convert('RGB') transform = build_transform(input_size=input_size) images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num) pixel_values = [transform(image) for image in images] pixel_values = torch.stack(pixel_values) return pixel_values path = "OpenGVLab/InternVL-Chat-V1-5" # If you have an 80G A100 GPU, 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, trust_remote_code=True) # set the max number of tiles in `max_num` pixel_values = load_image('./examples/image1.jpg', max_num=6).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) ``` ## 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!