p12475398
/
LLaMA-Factory-Mirror
forked from p04798526/LLaMA-Factory-Mirror
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix bug in DPO data collator

This commit is contained in:
hiyouga 2023-09-08 20:45:07 +08:00
parent b34797a845
commit 90bd085ae4
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": if self.tokenizer.padding_side == "left":
start, end = feature.size(0) - answer_len, feature.size(0) start, end = feature.size(0) - answer_len, feature.size(0)
else: 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 = self.label_pad_token_id * torch.ones_like(feature)
padded_tensor[start:end] = feature[start:end] padded_tensor[start:end] = feature[start:end]
padded_labels.append(padded_tensor) padded_labels.append(padded_tensor)