Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-29 10:59:32 +01:00
Code Issues Packages Projects Releases Wiki Activity

Change training file encoding

Browse Source
This commit is contained in:
oobabooga 2023-04-07 11:15:52 -03:00
parent 6762e62a40
commit 768354239b
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modules/training.py
View File

@ -152,7 +152,7 @@ def do_train(lora_name: str, micro_batch_size: int, batch_size: int, epochs: int
# == Prep the dataset, format, etc == # == Prep the dataset, format, etc ==
if raw_text_file not in ['None', '']: if raw_text_file not in ['None', '']:
print("Loading raw text file dataset...") 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() raw_text = file.read()
tokens = shared.tokenizer.encode(raw_text) 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 del raw_text # Note: could be a gig for a large dataset, so delete redundant data as we go to be safe on RAM