LLaMA-Adapter

LLaMA-Adapter copied to clipboard

Errors throwns when finetuning

4

When i run on a single GPU i get the following errors: /usr/local/lib/python3.8/dist-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: '/usr/local/lib/python3.8/dist-packages/torchvision/image.so: undefined symbol: _ZN3c104cuda20CUDACachingAllocator9allocatorE'If you don't plan on using image...

Petrichoeur

which GPU could I used if I want to do alpaca_finetuning_v1 on a single GPU?

2

see title，thanks

pengwei-iie

Issues with fine-tuning on the ScienceQA dataset.

4

I have some problems fine-tuning llama_adapter on the ScienceQA dataset. I'm not quite sure how to write a prompt on the ScienceQA dataset according to the current template. Is it...

Gary3410

what about gpuduring training? I use 16G*4, batch size to 1, and then OOM

2

pengwei-iie

multi-gpu

1

"AssertionError: Loading a checkpoint for MP=1 but world size is 2" when I set --nproc_per_node to 2. How to run on 2 16G gpu? because it OOM when inference. Thanks

pengwei-iie

Multi-image inputs to the model

1

Hi, I was wondering if it is possible to prompt the model with more than one image input since in the implementation the incorporation of the visual tokens is a...

vishaal27

Alpaca finetuning issues

3

Thanks for your wonderful work！ I had a problem when fine-tuning the model. https://github.com/ZrrSkywalker/LLaMA-Adapter/blob/5f1b37e0e2f3ab2e423ea71234c89829fa271ad7/alpaca_finetuning_v1/llama/model.py#L80-L85 https://github.com/ZrrSkywalker/LLaMA-Adapter/blob/5f1b37e0e2f3ab2e423ea71234c89829fa271ad7/llama/model.py#L78-L83 The `self.n_local_heads` in training and inference are not the same, will this affect the deployment...

Gary3410

Error when running example.py

1

Hi, I want to run example.py in windows 11, but I get weird errors (sockets): (llama_adapter) C:\Users\jjovan\llama\ai\LLaMA-Adapter>python -m torch.distributed.run --nproc_per_node 1 example.py --ckpt_dir .\7B --tokenizer_path .\7B\tokenizer.model --adapter_path .\7B\ NOTE: Redirects...

reddiamond1234

When Training code will be Released? I have prepared the japanese Version after training on my dataset, I would like to see its efficiency.

4

ankur92009

Error while inference

2

After installing all dependencies, when I run the torchrun command I get this error: **raise RuntimeError("Distributed package doesn't have NCCL " "built in")** I can't figure out what am I...

satani99