LLaVA-NeXT
LLaVA-NeXT copied to clipboard
LLaVA-VL
Hi, I can only find a subset of the image from the dataset in [huggingface](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data) And I don't find multi-image datas in the dataset. for example, tqa is a multi-image...
想问下论文中提到的LLaVA-158K数据有开源么 https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data 这里好像没找到这个数据
不是引流，只是考虑到可能大家会有些不构成 issue 的小问题，有个群会比较好。 后续如果官方有需要，我愿意转让群管理 我的微信 dreamingforhope ，若二维码失效可添加我 
Hello, I finetuned LLaVA onevision with Qwen2-7B. In the finetuning script, I set it to finetune just the adapter. When I am trying to inference my model, I am using...
In the file `llava/model/llava_arch.py` under the class `LlavaMetaForCausalLM` there is a function`prepare_inputs_labels_for_multimodal` that is called when calling the `generate` and `forward` functions. In lines 411 and 412, the input embeds...
不是引流，只是考虑到可能大家会有些不构成 issue 的小问题，有个群会比较好。 后续如果官方有需要，我愿意转让群管理 我的微信 dreamingforhope ，若二维码失效可添加我 
Have the authors cleaned the datasets? ``` [{'from': 'gpt', 'value': 'Help me write a Twitter post considering the following images.\n'}, {'from': 'human', 'value': "I'm sorry, I can't assist with that...
There are some issues with the online OneVision-7B Demo. When two images are input for inference, it fails to return a result. @Luodian @ZhangYuanhan-AI @Luodian 
I am using a pretrain adapter with deepspeed --pretrain_mm_mlp_adapter /home/srikanth/api-webapp/checkpoints/llava-v1.5-llama-3-8b-pretrain/mm_projector.bin but this throws an error "AttributeError: 'PreTrainedTokenizerFast' object has no attribute 'legacy'" The pretrained adapter was not created with the...
