Spaces:

Tonic
/

SmolFactory

Running

Tonic commited on Jul 19

Commit

9a7a5af

verified ·

1 Parent(s): c740b39

removes padding argument in data.py

Files changed (1) hide show

data.py CHANGED Viewed

@@ -263,7 +263,6 @@ class SmolLM3Dataset:
             mlm=False,  # We're doing causal LM, not masked LM
             pad_to_multiple_of=8,  # Pad to multiple of 8 for efficiency
             return_tensors="pt",  # Ensure we return PyTorch tensors
-            padding=True,  # Enable padding
         )
 def create_sample_dataset(output_path: str = "my_dataset"):

             mlm=False,  # We're doing causal LM, not masked LM
             pad_to_multiple_of=8,  # Pad to multiple of 8 for efficiency
             return_tensors="pt",  # Ensure we return PyTorch tensors
         )
 def create_sample_dataset(output_path: str = "my_dataset"):