mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2024-11-26 01:30:20 +01:00
Change training file encoding
This commit is contained in:
parent
6762e62a40
commit
768354239b
@ -152,7 +152,7 @@ def do_train(lora_name: str, micro_batch_size: int, batch_size: int, epochs: int
|
||||
# == Prep the dataset, format, etc ==
|
||||
if raw_text_file not in ['None', '']:
|
||||
print("Loading raw text file dataset...")
|
||||
with open(clean_path('training/datasets', f'{raw_text_file}.txt'), 'r') as file:
|
||||
with open(clean_path('training/datasets', f'{raw_text_file}.txt'), 'r', encoding='utf-8') as file:
|
||||
raw_text = file.read()
|
||||
tokens = shared.tokenizer.encode(raw_text)
|
||||
del raw_text # Note: could be a gig for a large dataset, so delete redundant data as we go to be safe on RAM
|
||||
|
Loading…
Reference in New Issue
Block a user