423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-11-07 22:00:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix

Browse Source
This commit is contained in:
kingsley 2025-09-27 20:32:39 +08:00
parent 0c017bac01
commit 9afe70c6b9
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/llamafactory/data/collator.py
View File

@ -194,7 +194,7 @@ class MultiModalDataCollatorForSeq2Seq(DataCollatorForSeq2Seq):
elif "video_second_per_grid" in mm_inputs: # for qwen2.5 omni elif "video_second_per_grid" in mm_inputs: # for qwen2.5 omni
rope_index_kwargs["second_per_grids"] = mm_inputs.get("video_second_per_grid") rope_index_kwargs["second_per_grids"] = mm_inputs.get("video_second_per_grid")
if getattr(self.model.config, "model_type", None) == "qwen2_5_omni_thinker": # for qwen2.5 omni if getattr(self.model.config, "model_type", None) in ["qwen2_5_omni_thinker", "qwen3_omni_moe_thinker"]: # for qwen2.5 omni
rope_index_kwargs["use_audio_in_video"] = getattr(self.processor, "use_audio_in_video", False) rope_index_kwargs["use_audio_in_video"] = getattr(self.processor, "use_audio_in_video", False)
feature_attention_mask = mm_inputs.get("feature_attention_mask", None) feature_attention_mask = mm_inputs.get("feature_attention_mask", None)
if feature_attention_mask is not None: # FIXME: need to get video image lengths if feature_attention_mask is not None: # FIXME: need to get video image lengths
@ -211,7 +211,7 @@ class MultiModalDataCollatorForSeq2Seq(DataCollatorForSeq2Seq):
if ( if (
self.model is not None self.model is not None
and getattr(self.model.config, "model_type", None) and getattr(self.model.config, "model_type", None)
in ["glm4v", "Keye", "qwen2_vl", "qwen2_5_vl", "qwen2_5_omni_thinker"] in ["glm4v", "Keye", "qwen2_vl", "qwen2_5_vl", "qwen2_5_omni_thinker", "qwen3_omni_moe_thinker"]
and ("position_ids" not in features or features["position_ids"].dim() != 3) and ("position_ids" not in features or features["position_ids"].dim() != 3)
): ):
raise ValueError(f"{self.model.config.model_type} requires 3D position ids for mrope.") raise ValueError(f"{self.model.config.model_type} requires 3D position ids for mrope.")