Gabor Gulyas

Fixing learned weight for continuous learning

1

I'm building a model by iteratively adding new input variables. It would be brilliant to continue teaching a model by inheriting from another one (by simply just creating a copy...

wei value not 100% per row after dropout

1

It doesn't make sense to me, but ``` wei = q @ k.transpose(-2,-1) * k.shape[-1]**-0.5 # (B, T, hs) @ (B, hs, T) -> (B, T, T) wei = wei.masked_fill(self.tril[:T,...

struct.error: unpack requires a buffer of 4 bytes

5

I wanted to use the simple bicycle example under Windows 11 accelerate launch train.py --gin_configs=configs/360.gin --gin_bindings="Config.data_dir = 'data/bicycle'" --gin_bindings="Config.exp_name = 'bicycle'" --gin_bindings="Config.factor = 4" and got this error