423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-16 00:28:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix bug in DPO data collator

Browse Source 
Former-commit-id: 4fc262cdf1347691e253bdfbd96568db5a49c086
This commit is contained in:
hiyouga 2023-09-08 20:45:07 +08:00
parent e70b3e8947
commit 692b132dbf
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/tuner/dpo/collator.py
View File

@ -16,7 +16,7 @@ class DPODataCollatorWithPadding(DataCollatorForSeq2Seq):
if self.tokenizer.padding_side == "left":
start, end = feature.size(0) - answer_len, feature.size(0)
else:
start, end = prompt_len, answer_len
start, end = prompt_len, prompt_len + answer_len
padded_tensor = self.label_pad_token_id * torch.ones_like(feature)
padded_tensor[start:end] = feature[start:end]
padded_labels.append(padded_tensor)