ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[model] support audio (#6701)

Browse Source 
* support qwen2_audio

* improve code

* lint

* fix

* fix

* fix

---------

Co-authored-by: hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: 5eacb5629e4d7733cd992a63747a1335f2c6a929
This commit is contained in:
Zhangchi Feng
2025-02-05 04:59:09 +08:00
committed by GitHub
parent 9feb78e7b4
commit 8f401e37f8
35 changed files with 675 additions and 213 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/llamafactory/model/patcher.py
View File

@@ -78,13 +78,14 @@ def patch_processor(
model_args: "ModelArguments",
) -> None:
setattr(processor, "tokenizer", tokenizer)
setattr(processor, "image_seqlen", get_image_seqlen(config))
setattr(processor, "image_resolution", model_args.image_resolution)
setattr(processor, "patch_size", get_patch_size(config, processor))
setattr(processor, "video_resolution", model_args.video_resolution)
setattr(processor, "video_fps", model_args.video_fps)
setattr(processor, "video_maxlen", model_args.video_maxlen)
setattr(processor, "vision_feature_select_strategy", get_vision_feature_select_strategy(config, processor))
if getattr(config, "vision_config", None) is not None: # visual models
setattr(processor, "image_seqlen", get_image_seqlen(config))
setattr(processor, "image_resolution", model_args.image_resolution)
setattr(processor, "patch_size", get_patch_size(config, processor))
setattr(processor, "video_resolution", model_args.video_resolution)
setattr(processor, "video_fps", model_args.video_fps)
setattr(processor, "video_maxlen", model_args.video_maxlen)
setattr(processor, "vision_feature_select_strategy", get_vision_feature_select_strategy(config, processor))
def patch_config(