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

4
src/llamafactory/chat/base_engine.py
View File

@@ -22,7 +22,7 @@ if TYPE_CHECKING:
from vllm import AsyncLLMEngine
from ..data import Template
from ..data.mm_plugin import ImageInput, VideoInput
from ..data.mm_plugin import AudioInput, ImageInput, VideoInput
from ..hparams import DataArguments, FinetuningArguments, GeneratingArguments, ModelArguments
@@ -68,6 +68,7 @@ class BaseEngine(ABC):
tools: Optional[str] = None,
images: Optional[Sequence["ImageInput"]] = None,
videos: Optional[Sequence["VideoInput"]] = None,
audios: Optional[Sequence["AudioInput"]] = None,
**input_kwargs,
) -> List["Response"]:
r"""
@@ -83,6 +84,7 @@ class BaseEngine(ABC):
tools: Optional[str] = None,
images: Optional[Sequence["ImageInput"]] = None,
videos: Optional[Sequence["VideoInput"]] = None,
audios: Optional[Sequence["AudioInput"]] = None,
**input_kwargs,
) -> AsyncGenerator[str, None]:
r"""