InternVL
InternVL copied to clipboard
OpenGVLab
[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
How to perform CPT on internvl3.5? Can you provide relevant code?
### 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. -...
LazySupervisedDataset的token_length计算感觉存在问题。在线计算token_length的时候，第一次计算的token_length是input_id的长度。而保存到字典conv2length中的value却是input_id加上图片token的长度。 ``` if self.group_by_length: self.conv2length = {} # Using a dictionary to speed up token length calculation self.length = [] for data_item in self.raw_data: data_item = json.loads(data_item) if 'length' in...
### Motivation File "internvl_chat/internvl/patch/pad_data_collator.py", line 104, in concat_pad_data_collator batch[k] = torch.stack([f[k] for f in features]) RuntimeError: stack expects each tensor to be equal size, but got [8145] at entry 0...
I had saw someone applied "InternVL/internvl_chat/internvl/train/internvl_chat_finetune.py" to finetune InternVL3.5 and but i want to confirm is it a official way to do that ? check list : 1. Conversation template...
### 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. -...
when I use the data to sft, there's about 1 million data consist of coco and my own data, when training with 8x80G A100 ， in report it will training...
### Checklist - [ ] 1. I have searched related issues but cannot get the expected help. - [ ] 2. The bug has not been fixed in the latest...
Dear InternVL3.5 Team, Thanks for your great work. I try to use LMDeploy to deploy the InternVL3.5-38B and input a video to let VLM response to my question. When I...
