Skip to content

Commit fdd6c2a

Browse files
Jintao-HuangJintao-Huang
committed
[model] support Qwen3-30B-A3B-Instruct-2507 (#5149)
1 parent c7baf18 commit fdd6c2a

File tree

3 files changed

+12
-0
lines changed

3 files changed

+12
-0
lines changed

‎docs/source/Instruction/支持的模型和数据集.md‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -212,12 +212,16 @@
212212
|[Qwen/Qwen3-235B-A22B-FP8](https://modelscope.cn/models/Qwen/Qwen3-235B-A22B-FP8)|qwen3_moe|qwen3|transformers>=4.51|✘|-|[Qwen/Qwen3-235B-A22B-FP8](https://huggingface.co/Qwen/Qwen3-235B-A22B-FP8)|
213213
|[swift/Qwen3-30B-A3B-AWQ](https://modelscope.cn/models/swift/Qwen3-30B-A3B-AWQ)|qwen3_moe|qwen3|transformers>=4.51|✘|-|[cognitivecomputations/Qwen3-30B-A3B-AWQ](https://huggingface.co/cognitivecomputations/Qwen3-30B-A3B-AWQ)|
214214
|[swift/Qwen3-235B-A22B-AWQ](https://modelscope.cn/models/swift/Qwen3-235B-A22B-AWQ)|qwen3_moe|qwen3|transformers>=4.51|✘|-|[cognitivecomputations/Qwen3-235B-A22B-AWQ](https://huggingface.co/cognitivecomputations/Qwen3-235B-A22B-AWQ)|
215+
|[Qwen/Qwen3-30B-A3B-Instruct-2507](https://modelscope.cn/models/Qwen/Qwen3-30B-A3B-Instruct-2507)|qwen3_moe|qwen3|transformers>=4.51|✔|-|[Qwen/Qwen3-30B-A3B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507)|
216+
|[Qwen/Qwen3-30B-A3B-Instruct-2507-FP8](https://modelscope.cn/models/Qwen/Qwen3-30B-A3B-Instruct-2507-FP8)|qwen3_moe|qwen3|transformers>=4.51|✘|-|[Qwen/Qwen3-30B-A3B-Instruct-2507-FP8](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507-FP8)|
215217
|[Qwen/Qwen3-235B-A22B-Instruct-2507](https://modelscope.cn/models/Qwen/Qwen3-235B-A22B-Instruct-2507)|qwen3_moe|qwen3|transformers>=4.51|✔|-|[Qwen/Qwen3-235B-A22B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507)|
216218
|[Qwen/Qwen3-235B-A22B-Instruct-2507-FP8](https://modelscope.cn/models/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8)|qwen3_moe|qwen3|transformers>=4.51|✘|-|[Qwen/Qwen3-235B-A22B-Instruct-2507-FP8](https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8)|
217219
|[swift/Qwen3-235B-A22B-Instruct-2507-AWQ](https://modelscope.cn/models/swift/Qwen3-235B-A22B-Instruct-2507-AWQ)|qwen3_moe|qwen3|transformers>=4.51|✘|-|-|
218220
|[Qwen/Qwen3-Coder-480B-A35B-Instruct](https://modelscope.cn/models/Qwen/Qwen3-Coder-480B-A35B-Instruct)|qwen3_moe|qwen3|transformers>=4.51|✔|coding|[Qwen/Qwen3-Coder-480B-A35B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct)|
219221
|[Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8](https://modelscope.cn/models/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8)|qwen3_moe|qwen3|transformers>=4.51|✘|coding|[Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8](https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8)|
220222
|[swift/Qwen3-Coder-480B-A35B-Instruct-AWQ](https://modelscope.cn/models/swift/Qwen3-Coder-480B-A35B-Instruct-AWQ)|qwen3_moe|qwen3|transformers>=4.51|✘|coding|-|
223+
|[Qwen/Qwen3-30B-A3B-Thinking-2507](https://modelscope.cn/models/Qwen/Qwen3-30B-A3B-Thinking-2507)|qwen3_moe_thinking|qwen3_thinking|transformers>=4.51|✔|-|[Qwen/Qwen3-30B-A3B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507)|
224+
|[Qwen/Qwen3-30B-A3B-Thinking-2507-FP8](https://modelscope.cn/models/Qwen/Qwen3-30B-A3B-Thinking-2507-FP8)|qwen3_moe_thinking|qwen3_thinking|transformers>=4.51|✘|-|[Qwen/Qwen3-30B-A3B-Thinking-2507-FP8](https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507-FP8)|
221225
|[Qwen/Qwen3-235B-A22B-Thinking-2507](https://modelscope.cn/models/Qwen/Qwen3-235B-A22B-Thinking-2507)|qwen3_moe_thinking|qwen3_thinking|transformers>=4.51|✔|-|[Qwen/Qwen3-235B-A22B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507)|
222226
|[Qwen/Qwen3-235B-A22B-Thinking-2507-FP8](https://modelscope.cn/models/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8)|qwen3_moe_thinking|qwen3_thinking|transformers>=4.51|✘|-|[Qwen/Qwen3-235B-A22B-Thinking-2507-FP8](https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8)|
223227
|[swift/Qwen3-235B-A22B-Thinking-2507-AWQ](https://modelscope.cn/models/swift/Qwen3-235B-A22B-Thinking-2507-AWQ)|qwen3_moe_thinking|qwen3_thinking|transformers>=4.51|✘|-|-|

‎docs/source_en/Instruction/Supported-models-and-datasets.md‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -212,12 +212,16 @@ The table below introduces the models integrated with ms-swift:
212212
|[Qwen/Qwen3-235B-A22B-FP8](https://modelscope.cn/models/Qwen/Qwen3-235B-A22B-FP8)|qwen3_moe|qwen3|transformers>=4.51|✘|-|[Qwen/Qwen3-235B-A22B-FP8](https://huggingface.co/Qwen/Qwen3-235B-A22B-FP8)|
213213
|[swift/Qwen3-30B-A3B-AWQ](https://modelscope.cn/models/swift/Qwen3-30B-A3B-AWQ)|qwen3_moe|qwen3|transformers>=4.51|✘|-|[cognitivecomputations/Qwen3-30B-A3B-AWQ](https://huggingface.co/cognitivecomputations/Qwen3-30B-A3B-AWQ)|
214214
|[swift/Qwen3-235B-A22B-AWQ](https://modelscope.cn/models/swift/Qwen3-235B-A22B-AWQ)|qwen3_moe|qwen3|transformers>=4.51|✘|-|[cognitivecomputations/Qwen3-235B-A22B-AWQ](https://huggingface.co/cognitivecomputations/Qwen3-235B-A22B-AWQ)|
215+
|[Qwen/Qwen3-30B-A3B-Instruct-2507](https://modelscope.cn/models/Qwen/Qwen3-30B-A3B-Instruct-2507)|qwen3_moe|qwen3|transformers>=4.51|✔|-|[Qwen/Qwen3-30B-A3B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507)|
216+
|[Qwen/Qwen3-30B-A3B-Instruct-2507-FP8](https://modelscope.cn/models/Qwen/Qwen3-30B-A3B-Instruct-2507-FP8)|qwen3_moe|qwen3|transformers>=4.51|✘|-|[Qwen/Qwen3-30B-A3B-Instruct-2507-FP8](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507-FP8)|
215217
|[Qwen/Qwen3-235B-A22B-Instruct-2507](https://modelscope.cn/models/Qwen/Qwen3-235B-A22B-Instruct-2507)|qwen3_moe|qwen3|transformers>=4.51|✔|-|[Qwen/Qwen3-235B-A22B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507)|
216218
|[Qwen/Qwen3-235B-A22B-Instruct-2507-FP8](https://modelscope.cn/models/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8)|qwen3_moe|qwen3|transformers>=4.51|✘|-|[Qwen/Qwen3-235B-A22B-Instruct-2507-FP8](https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8)|
217219
|[swift/Qwen3-235B-A22B-Instruct-2507-AWQ](https://modelscope.cn/models/swift/Qwen3-235B-A22B-Instruct-2507-AWQ)|qwen3_moe|qwen3|transformers>=4.51|✘|-|-|
218220
|[Qwen/Qwen3-Coder-480B-A35B-Instruct](https://modelscope.cn/models/Qwen/Qwen3-Coder-480B-A35B-Instruct)|qwen3_moe|qwen3|transformers>=4.51|✔|coding|[Qwen/Qwen3-Coder-480B-A35B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct)|
219221
|[Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8](https://modelscope.cn/models/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8)|qwen3_moe|qwen3|transformers>=4.51|✘|coding|[Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8](https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8)|
220222
|[swift/Qwen3-Coder-480B-A35B-Instruct-AWQ](https://modelscope.cn/models/swift/Qwen3-Coder-480B-A35B-Instruct-AWQ)|qwen3_moe|qwen3|transformers>=4.51|✘|coding|-|
223+
|[Qwen/Qwen3-30B-A3B-Thinking-2507](https://modelscope.cn/models/Qwen/Qwen3-30B-A3B-Thinking-2507)|qwen3_moe_thinking|qwen3_thinking|transformers>=4.51|✔|-|[Qwen/Qwen3-30B-A3B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507)|
224+
|[Qwen/Qwen3-30B-A3B-Thinking-2507-FP8](https://modelscope.cn/models/Qwen/Qwen3-30B-A3B-Thinking-2507-FP8)|qwen3_moe_thinking|qwen3_thinking|transformers>=4.51|✘|-|[Qwen/Qwen3-30B-A3B-Thinking-2507-FP8](https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507-FP8)|
221225
|[Qwen/Qwen3-235B-A22B-Thinking-2507](https://modelscope.cn/models/Qwen/Qwen3-235B-A22B-Thinking-2507)|qwen3_moe_thinking|qwen3_thinking|transformers>=4.51|✔|-|[Qwen/Qwen3-235B-A22B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507)|
222226
|[Qwen/Qwen3-235B-A22B-Thinking-2507-FP8](https://modelscope.cn/models/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8)|qwen3_moe_thinking|qwen3_thinking|transformers>=4.51|✘|-|[Qwen/Qwen3-235B-A22B-Thinking-2507-FP8](https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8)|
223227
|[swift/Qwen3-235B-A22B-Thinking-2507-AWQ](https://modelscope.cn/models/swift/Qwen3-235B-A22B-Thinking-2507-AWQ)|qwen3_moe_thinking|qwen3_thinking|transformers>=4.51|✘|-|-|

‎swift/llm/model/model/qwen.py‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -553,6 +553,8 @@ def _get_cast_dtype(self) -> torch.dtype:
553553
Model('swift/Qwen3-235B-A22B-AWQ', 'cognitivecomputations/Qwen3-235B-A22B-AWQ'),
554554
]),
555555
ModelGroup([
556+
Model('Qwen/Qwen3-30B-A3B-Instruct-2507', 'Qwen/Qwen3-30B-A3B-Instruct-2507'),
557+
Model('Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', 'Qwen/Qwen3-30B-A3B-Instruct-2507-FP8'),
556558
Model('Qwen/Qwen3-235B-A22B-Instruct-2507', 'Qwen/Qwen3-235B-A22B-Instruct-2507'),
557559
Model('Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', 'Qwen/Qwen3-235B-A22B-Instruct-2507-FP8'),
558560
# awq
@@ -576,6 +578,8 @@ def _get_cast_dtype(self) -> torch.dtype:
576578
LLMModelType.qwen3_moe_thinking,
577579
[
578580
ModelGroup([
581+
Model('Qwen/Qwen3-30B-A3B-Thinking-2507', 'Qwen/Qwen3-30B-A3B-Thinking-2507'),
582+
Model('Qwen/Qwen3-30B-A3B-Thinking-2507-FP8', 'Qwen/Qwen3-30B-A3B-Thinking-2507-FP8'),
579583
Model('Qwen/Qwen3-235B-A22B-Thinking-2507', 'Qwen/Qwen3-235B-A22B-Thinking-2507'),
580584
Model('Qwen/Qwen3-235B-A22B-Thinking-2507-FP8', 'Qwen/Qwen3-235B-A22B-Thinking-2507-FP8'),
581585
# awq

0 commit comments

Comments
 (0)