fix mrope

Former-commit-id: 55bee1d333549ca19858b3f5c1b7b86926e5fb09
This commit is contained in:
hiyouga
2024-12-12 15:08:17 +00:00
parent cfff136b2a
commit fb22651faf
11 changed files with 32 additions and 9 deletions

View File

@@ -56,6 +56,7 @@ def run_sft(
data_collator = SFTDataCollatorWith4DAttentionMask(
template=template,
model=model,
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,