Peijie Wang

URL problems

1

There seems to be a problem with the URL Twittman's 4x_FatalPixels_340000_G.pth: https://de-next.owncube.com/index.php/s/mDGmi7NgdyyQRXL/download?path=%2F&files=4x_FatalPixels_340000_G.pth

acc does't improve while training 100 epochs

8

 training loss, valid acc don' improve

when run train.py, in scheduler.py, error: cannot import name 'LRScheduler' from 'torch.optim.lr_scheduler'

### Question does LLaVA1.5 supports for multipile images input now? If yes, how to do this

ValueError: The checkpoint you are trying to load has model type `llava_llama` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

12

I just follw the step, but when I run the following code : # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Efficient-Large-Model/Llama-3-VILA1.5-8B") it raise an error:ValueError: The checkpoint...

when I run the following code: from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("lmms-lab/llava-next-interleave-qwen-7b") I met the error:ValueError: The checkpoint you are trying to load has model type `llava_qwen` but Transformers...

pip install git+https://github.com/huggingface/transformers@21fac7abba2a37fae86106f87fcf9974fd1e3830 accelerate

2

pip install不上啊，是不是国内被墙了，大家是怎么安装这个环境的