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
### 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. -...
### Motivation  Thank you for your work. I trained Internvl 70b with Lora on LLM. But I found every times it saved all parameters instead of the adapter_model. How...
### 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. -...
https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B this link only gives an example on how to do batch inference single image per sample. Is it possible to do batch inference for multiple image per sample specifically...
Hi authors, Was trying to run InternVL-8B and InternVL-26B on 4 GPUs, but I got this, ``` File ".cache/huggingface/modules/transformers_modules/main/modeling_internlm2.py", line 656, in forward hidden_states, self_attn_weights, present_key_value = self.attention( File "...python3.8/site-packages/torch/nn/modules/module.py",...
bash video_retrieval.sh ``` Loading checkpoint shards: 0%| | 0/3 [00:00
Hi @czczup, Thanks for open-sourcing such a wonderful job. The amazing performance on video task is surprising. Just a quesiton about how to evaluate the intervl-chat-v1-5 on video benchmark such...
hi, thanks for your great work. I wonder if you have compare your small vit-300m-448px model with other clip models.
In the technical report，Object365 was used for pretrain, but I test mini-4B, it can't do object detection. So, what the detect data format or instructions are used during pretrain?
