frozenleaves/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-20 12:54:18 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] add qwen3vl 4b + 8b (#9275)

Browse Source
This commit is contained in:
Yaowei Zheng
2025-10-15 15:00:36 +08:00
committed by GitHub
parent c867e28093
commit 1037f63311
3 changed files with 24 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
requirements.txt
View File

@ -1,6 +1,6 @@
# core deps # core deps
transformers>=4.49.0,<=4.56.2,!=4.52.0; python_version < '3.10' transformers>=4.49.0,<=4.56.2,!=4.52.0; python_version < '3.10'
transformers>=4.49.0,<=4.57.0,!=4.52.0; python_version >= '3.10' transformers>=4.49.0,<=4.57.1,!=4.52.0; python_version >= '3.10'
datasets>=2.16.0,<=4.0.0 datasets>=2.16.0,<=4.0.0
accelerate>=1.3.0,<=1.11.0 accelerate>=1.3.0,<=1.11.0
peft>=0.14.0,<=0.17.1 peft>=0.14.0,<=0.17.1

28
src/llamafactory/extras/constants.py
View File

@ -3193,14 +3193,22 @@ register_model_group(
register_model_group( register_model_group(
models={ models={
"Qwen3-VL-235B-A22B-Instruct": { "Qwen3-VL-4B-Instruct": {
DownloadSource.DEFAULT: "Qwen/Qwen3-VL-235B-A22B-Instruct", DownloadSource.DEFAULT: "Qwen/Qwen3-VL-4B-Instruct",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-235B-A22B-Instruct", DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-4B-Instruct",
},
"Qwen3-VL-8B-Instruct": {
DownloadSource.DEFAULT: "Qwen/Qwen3-VL-8B-Instruct",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-8B-Instruct",
}, },
"Qwen3-VL-30B-A3B-Instruct": { "Qwen3-VL-30B-A3B-Instruct": {
DownloadSource.DEFAULT: "Qwen/Qwen3-VL-30B-A3B-Instruct", DownloadSource.DEFAULT: "Qwen/Qwen3-VL-30B-A3B-Instruct",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-30B-A3B-Instruct", DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-30B-A3B-Instruct",
}, },
"Qwen3-VL-235B-A22B-Instruct": {
DownloadSource.DEFAULT: "Qwen/Qwen3-VL-235B-A22B-Instruct",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-235B-A22B-Instruct",
},
}, },
template="qwen3_vl_nothink", template="qwen3_vl_nothink",
multimodal=True, multimodal=True,
@ -3209,14 +3217,22 @@ register_model_group(
register_model_group( register_model_group(
models={ models={
"Qwen3-VL-235B-A22B-Thinking": { "Qwen3-VL-4B-Thinking": {
DownloadSource.DEFAULT: "Qwen/Qwen3-VL-235B-A22B-Thinking", DownloadSource.DEFAULT: "Qwen/Qwen3-VL-4B-Thinking",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-235B-A22B-Thinking", DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-4B-Thinking",
},
"Qwen3-VL-8B-Thinking": {
DownloadSource.DEFAULT: "Qwen/Qwen3-VL-8B-Thinking",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-8B-Thinking",
}, },
"Qwen3-VL-30B-A3B-Thinking": { "Qwen3-VL-30B-A3B-Thinking": {
DownloadSource.DEFAULT: "Qwen/Qwen3-VL-30B-A3B-Thinking", DownloadSource.DEFAULT: "Qwen/Qwen3-VL-30B-A3B-Thinking",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-30B-A3B-Thinking", DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-30B-A3B-Thinking",
}, },
"Qwen3-VL-235B-A22B-Thinking": {
DownloadSource.DEFAULT: "Qwen/Qwen3-VL-235B-A22B-Thinking",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-235B-A22B-Thinking",
},
}, },
template="qwen3_vl", template="qwen3_vl",
multimodal=True, multimodal=True,

2
src/llamafactory/extras/misc.py
View File

@ -94,7 +94,7 @@ def check_version(requirement: str, mandatory: bool = False) -> None:
def check_dependencies() -> None: def check_dependencies() -> None:
r"""Check the version of the required packages.""" r"""Check the version of the required packages."""
check_version("transformers>=4.49.0,<=4.57.0") check_version("transformers>=4.49.0,<=4.57.1")
check_version("datasets>=2.16.0,<=4.0.0") check_version("datasets>=2.16.0,<=4.0.0")
check_version("accelerate>=1.3.0,<=1.11.0") check_version("accelerate>=1.3.0,<=1.11.0")
check_version("peft>=0.14.0,<=0.17.1") check_version("peft>=0.14.0,<=0.17.1")