InternVL icon indicating copy to clipboard operation
InternVL copied to clipboard

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Results 271 InternVL issues
Sort by recently updated
recently updated
newest added

### Motivation For the evaluation, could you please add the MMIU benchmark(https://mmiu-bench.github.io/) in https://internvl.readthedocs.io/en/latest/internvl2.0/evaluation.html? ### Related resources _No response_ ### Additional context _No response_

### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [ ] 2. The bug has not been fixed in the latest version....

### Checklist - [X] 1. I have searched related issues but cannot get the expected help. - [ ] 2. The bug has not been fixed in the latest version....

### Motivation 选择模型那里是灰色的,不能选择,是什么原因呢?麻烦请教一下怎么弄。模型用的是InternVL2-Llama3-76B。路径如下图: ### Related resources 请问下图中是不是路径不对?/root/InternVL/InternVL2-Llama3-76B 里面是 OpenGVLab/InternVL2-Llama3-76B 模型文件和其他文件。 ### Additional context ![ubuntulujing](https://github.com/user-attachments/assets/632411a0-05cb-4658-a27e-18c46f8ba69d) ![无法选择模型](https://github.com/user-attachments/assets/78db5f3f-f546-4c6b-92e9-2418b4026c33)

### Checklist - [X] 1. I have searched related issues but cannot get the expected help. - [X] 2. The bug has not been fixed in the latest version. -...

### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [x] 2. The bug has not been fixed in the latest version. -...

### Checklist - [X] 1. I have searched related issues but cannot get the expected help. - [X] 2. The bug has not been fixed in the latest version. -...

InternVL-1.1 中的结果 ![image](https://github.com/user-attachments/assets/a617738c-5e45-41e6-8593-15cf0760e3c5) InternVL-1.2 中的结果 ![image](https://github.com/user-attachments/assets/dbe22e74-7998-4b64-a471-b3b5519cce9b) 可以看到InternVL-1.2 相比于InternVL-1.1 在SQA,TextVQA等好几个benchmark 上都要低,这是为什么?理论上1.2 版本应该比1.1 版本要高。

### Checklist - [X] 1. I have searched related issues but cannot get the expected help. - [ ] 2. The bug has not been fixed in the latest version....

At the moment the internvl_chat/internvl/train/internvl_chat_finetune.py and internvl_chat/internvl/train/internvl_chat_pretrain.py are almost the same. I am wondering if the ITM loss and Contrastive loss would be used. Am I miss something? Is generative...