Zach
Zach
not for text to text
The Path leads to what? Is it the hf_ckpt converted folder? To the previous fine tuned alpaca-lora folder?
remove the os.environ, when you run your code do the following CUDA_VISIBLE_DEVICES=2,7 torchrun --nproc_per_node=2 --master_port=1234 fileName.py Its safer to do this instead of using os environ
Have you tried using torchrun?
How many gpus are needed to train 65B? I have been able to train 30B but I am pretty sure that was the limit for my capabilities.
Do you have a guess for the amount of VRAM you'd need for 65B? I'd be curious to try it out
How to load a model pre-trained on a 52k dataset and continue fine-tuning with another dataset.json?
Just going to put a . in here as I'm facing the same issue. I've talked with T-Atlas a little bit over e-mail and we're hitting the exact same wall
What dataset are you using? Are you fine tuning the already fine tuned model?
> > What dataset are you using? Are you fine tuning the already fine tuned model? > > I tried to fine-tune it with some safe question and answer data...
I got this error when I converted the weights to HF model (I'm assuming you ran the convert file, export_hf_checkpoint.py). You have two options if you're running inference on the...