This commit is contained in:
hiyouga
2024-12-17 10:06:46 +00:00
parent e2fbd07096
commit 142191e466
3 changed files with 26 additions and 16 deletions

View File

@@ -56,7 +56,7 @@ def run_sft(
data_collator = SFTDataCollatorWith4DAttentionMask(
template=template,
model=model,
model=model if not training_args.predict_with_generate else None,
pad_to_multiple_of=8 if training_args.do_train else None, # for shift short attention
label_pad_token_id=IGNORE_INDEX if data_args.ignore_pad_token_for_loss else tokenizer.pad_token_id,
block_diag_attn=model_args.block_diag_attn,