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 461 InternVL issues
Sort by recently updated
recently updated
newest added

请问internvl2.5 8B在评测longvideobench时,有没有使用 subtitle? 我看其他的video llm,如llava video, qwen2.5vl都没有使用subtitle 但是internvl 2.5 8B不使用subtitle的结果比report少了2个点多

这个部分目前是否支持保存数据的state_dict呢,或者未来有计划支持么,不然训练过程中中断可能会导致数据重复训练(影响性能)/从头过一遍数据再训练(耗费时间)

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

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

### 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....

Thanks for sharing this great project. Here I have a question on the 2D pixel shuffle. The vit_embeds has the shape of [N, L, C], and it is first reshaped...

Hello, I have 2 x A100 GPUs with a total of 160GB VRAM. I attempted to fine-tune the OpenGVLab/InternVL-Chat-V1-5 model by following the steps provided in the InternVL documentation. However,...

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

### Motivation 感谢解答 ### Related resources _No response_ ### Additional context _No response_