1 Issue closed by 1 person

• [Question] where can download OCR-VQA data?

  #1781 closed Nov 24, 2024

9 Issues opened by 7 people

• [Question] demo website error https://llava.hliu.cc/

  #1786 opened Nov 27, 2024

• [Question] llava 预训练中断，继续预训练默认加载模型报错

  #1785 opened Nov 27, 2024

• [Question] Model parameters during finetuning (prints me only mm_projector parameters)

  #1784 opened Nov 26, 2024

• [Question] Does llava support dynamic image tokens input?

  #1783 opened Nov 26, 2024

• [Discussion] loss function of finetune llava 1.5 with sft

  #1782 opened Nov 25, 2024

• [Question] when run v1.5/pretrain.sh , there are some errors

  #1780 opened Nov 24, 2024

• [Question] pretrain data

  #1779 opened Nov 24, 2024

• [Question] I trained the llava-1.5-13B model, but when evaluating, the inference answer is always empty and the speed is very slow.

  #1778 opened Nov 23, 2024

• [Usage] Batch evaluation using sqlang doesn't support llava-v1.5 model

  #1777 opened Nov 23, 2024

11 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• [Usage] Batch inference with Llava 1.5

  #709 commented on Nov 23, 2024 • 0 new comments

• You are using a model of type llava to instantiate a model of type llava_llama. This is not supported for all configurations of models and can yield errors.

  #1646 commented on Nov 23, 2024 • 0 new comments

• [Question] Pretrain LLaVA

  #1717 commented on Nov 24, 2024 • 0 new comments

• [Question] evaluation problem in textVQA

  #1664 commented on Nov 26, 2024 • 0 new comments

• TypeError: pad_sequence(): argument 'padding_value' (position 3) must be float, not NoneType

  #1167 commented on Nov 26, 2024 • 0 new comments

• How to fine tune Lora without images……

  #1585 commented on Nov 27, 2024 • 0 new comments

• [Question] Text only training?

  #1467 commented on Nov 27, 2024 • 0 new comments

• Need either a `state_dict` or a `save_folder` containing offloaded weights.

  #1600 commented on Nov 28, 2024 • 0 new comments

• [Usage] Infer on model finetuned using finetune_qlora.sh

  #1771 commented on Nov 29, 2024 • 0 new comments

• [Question] How to use in-context learning in LLaVA?

  #1357 commented on Nov 29, 2024 • 0 new comments

• Anyres compatible fine-tuning of llava-1.6 mistral 7b and 34b

  #1347 commented on Nov 25, 2024 • 0 new comments