ros/LlamaFactory
1
0
Fork 0
mirror of https://github.com/hiyouga/LlamaFactory.git synced 2026-02-02 08:33:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

[model] support keye-vl-8b (#8776)

Browse Source
This commit is contained in:
Kingsley
2025-07-29 21:24:08 +08:00
committed by GitHub
parent 4e0bf35eb4
commit 52882d01c3
4 changed files with 41 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -211,10 +211,10 @@ class MultiModalDataCollatorForSeq2Seq(DataCollatorForSeq2Seq):
if (
self.model is not None
and getattr(self.model.config, "model_type", None)
in ["glm4v", "qwen2_vl", "qwen2_5_vl", "qwen2_5_omni_thinker"]
in ["glm4v", "Keye", "qwen2_vl", "qwen2_5_vl", "qwen2_5_omni_thinker"]
and ("position_ids" not in features or features["position_ids"].dim() != 3)
):
raise ValueError("Qwen2-VL/Qwen2.5-Omni model requires 3D position ids for mrope.")
raise ValueError(f"{self.model.config.model_type} requires 3D position ids for mrope.")
if "cross_attention_mask" in mm_inputs: # for mllama inputs when pad_to_multiple_of is enabled
cross_attention_mask = mm_inputs.pop("cross_attention_mask")