Afshin Oroojlooy
Afshin Oroojlooy
Since Google has got the images from different websites, what is the ownership status of images? Does google own the images? In other words, are we allowed to use these...
### Checklist - [ ] 1. I have searched related issues but cannot get the expected help. - [X] 2. The bug has not been fixed in the latest version....
### 📚 The doc issue I did not see any info about the data size for the pre-train and fine-tuning stages for InternVL 1.5 and 2.0. Do you use the...
In the released dataset [LLaVA-OneVision-Data](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data ), I see that there are several datasets (see below list) which their name include `cauldron`. Was wondering what does that mean? ``` robut_sqa(cauldron) robut_wikisql(cauldron)...
Do you have any plan to get involved in OpenVLM leaderboard? https://huggingface.co/spaces/opencompass/open_vlm_leaderboard I think that needs some efforts from your side, but given the performance of VILA provides you good...
### Describe the issue Issue: I wanted to run the pre-train code `https://github.com/haotian-liu/LLaVA/blob/main/scripts/v1_5/pretrain.sh`, but it ends to a device mis-match error. It seems that the whole LLM model is on...
### Feature request As I see in https://huggingface.github.io/text-generation-inference/#/Text%20Generation%20Inference there is no `detokenize` function available. ### Motivation This is a major requirement for many applications, as vllm also provides that. ###...