[model] support audio (#6701)

* support qwen2_audio * improve code * lint * fix * fix * fix --------- Co-authored-by: hiyouga <hiyouga@buaa.edu.cn> Former-commit-id: 5eacb5629e4d7733cd992a63747a1335f2c6a929
2025-02-05 04:59:09 +08:00
parent 9feb78e7b4
commit 8f401e37f8
35 changed files with 675 additions and 213 deletions
--- a/scripts/stat_utils/cal_ppl.py
+++ b/scripts/stat_utils/cal_ppl.py
@@ -49,6 +49,7 @@ class PairwiseDataCollatorWithPadding(MultiModalDataCollatorForSeq2Seq):
                    "labels": feature["chosen_input_ids"] if self.train_on_prompt else feature["chosen_labels"],
                    "images": feature["images"],
                    "videos": feature["videos"],
+                    "audios": feature["audios"],
                }
            )