Skip to content

Commit c9e4f33

Browse files
committed
[model] support dots1 (#4560)
1 parent 541af35 commit c9e4f33

File tree

6 files changed

+31
-0
lines changed

6 files changed

+31
-0
lines changed

docs/source/Instruction/支持的模型和数据集.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -547,6 +547,8 @@
547547
|[XiaomiMiMo/MiMo-7B-RL-Zero](https://modelscope.cn/models/XiaomiMiMo/MiMo-7B-RL-Zero)|mimo|qwen|transformers>=4.37|✘|-|[XiaomiMiMo/MiMo-7B-RL-Zero](https://huggingface.co/XiaomiMiMo/MiMo-7B-RL-Zero)|
548548
|[XiaomiMiMo/MiMo-7B-RL](https://modelscope.cn/models/XiaomiMiMo/MiMo-7B-RL)|mimo|qwen|transformers>=4.37|✘|-|[XiaomiMiMo/MiMo-7B-RL](https://huggingface.co/XiaomiMiMo/MiMo-7B-RL)|
549549
|[XiaomiMiMo/MiMo-7B-RL-0530](https://modelscope.cn/models/XiaomiMiMo/MiMo-7B-RL-0530)|mimo_rl|mimo_rl|transformers>=4.37|✘|-|[XiaomiMiMo/MiMo-7B-RL-0530](https://huggingface.co/XiaomiMiMo/MiMo-7B-RL-0530)|
550+
|[rednote-hilab/dots.llm1.base](https://modelscope.cn/models/rednote-hilab/dots.llm1.base)|dots1|dots1|transformers>=4.53.0.dev0|✘|-|[rednote-hilab/dots.llm1.base](https://huggingface.co/rednote-hilab/dots.llm1.base)|
551+
|[rednote-hilab/dots.llm1.inst](https://modelscope.cn/models/rednote-hilab/dots.llm1.inst)|dots1|dots1|transformers>=4.53.0.dev0|✘|-|[rednote-hilab/dots.llm1.inst](https://huggingface.co/rednote-hilab/dots.llm1.inst)|
550552
|[answerdotai/ModernBERT-base](https://modelscope.cn/models/answerdotai/ModernBERT-base)|modern_bert|dummy|transformers>=4.48|✘|bert|[answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base)|
551553
|[answerdotai/ModernBERT-large](https://modelscope.cn/models/answerdotai/ModernBERT-large)|modern_bert|dummy|transformers>=4.48|✘|bert|[answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large)|
552554
|[iic/gte-modernbert-base](https://modelscope.cn/models/iic/gte-modernbert-base)|modern_bert_gte|dummy|transformers>=4.48|✘|bert, embedding|[Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base)|

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

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -547,6 +547,8 @@ The table below introduces the models integrated with ms-swift:
547547
|[XiaomiMiMo/MiMo-7B-RL-Zero](https://modelscope.cn/models/XiaomiMiMo/MiMo-7B-RL-Zero)|mimo|qwen|transformers>=4.37|✘|-|[XiaomiMiMo/MiMo-7B-RL-Zero](https://huggingface.co/XiaomiMiMo/MiMo-7B-RL-Zero)|
548548
|[XiaomiMiMo/MiMo-7B-RL](https://modelscope.cn/models/XiaomiMiMo/MiMo-7B-RL)|mimo|qwen|transformers>=4.37|✘|-|[XiaomiMiMo/MiMo-7B-RL](https://huggingface.co/XiaomiMiMo/MiMo-7B-RL)|
549549
|[XiaomiMiMo/MiMo-7B-RL-0530](https://modelscope.cn/models/XiaomiMiMo/MiMo-7B-RL-0530)|mimo_rl|mimo_rl|transformers>=4.37|✘|-|[XiaomiMiMo/MiMo-7B-RL-0530](https://huggingface.co/XiaomiMiMo/MiMo-7B-RL-0530)|
550+
|[rednote-hilab/dots.llm1.base](https://modelscope.cn/models/rednote-hilab/dots.llm1.base)|dots1|dots1|transformers>=4.53.0.dev0|✘|-|[rednote-hilab/dots.llm1.base](https://huggingface.co/rednote-hilab/dots.llm1.base)|
551+
|[rednote-hilab/dots.llm1.inst](https://modelscope.cn/models/rednote-hilab/dots.llm1.inst)|dots1|dots1|transformers>=4.53.0.dev0|✘|-|[rednote-hilab/dots.llm1.inst](https://huggingface.co/rednote-hilab/dots.llm1.inst)|
550552
|[answerdotai/ModernBERT-base](https://modelscope.cn/models/answerdotai/ModernBERT-base)|modern_bert|dummy|transformers>=4.48|✘|bert|[answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base)|
551553
|[answerdotai/ModernBERT-large](https://modelscope.cn/models/answerdotai/ModernBERT-large)|modern_bert|dummy|transformers>=4.48|✘|bert|[answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large)|
552554
|[iic/gte-modernbert-base](https://modelscope.cn/models/iic/gte-modernbert-base)|modern_bert_gte|dummy|transformers>=4.48|✘|bert, embedding|[Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base)|

swift/llm/model/constant.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -116,6 +116,7 @@ class LLMModelType:
116116
moonlight = 'moonlight'
117117
mimo = 'mimo'
118118
mimo_rl = 'mimo_rl'
119+
dots1 = 'dots1'
119120

120121

121122
class BertModelType:

swift/llm/model/model/llm.py

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -328,3 +328,18 @@ def forward(self, **kwargs):
328328
model_arch=ModelArch.llama,
329329
architectures=['MiMoForCausalLM'],
330330
requires=['transformers>=4.37']))
331+
332+
register_model(
333+
ModelMeta(
334+
LLMModelType.dots1,
335+
[
336+
ModelGroup([
337+
Model('rednote-hilab/dots.llm1.base', 'rednote-hilab/dots.llm1.base'),
338+
Model('rednote-hilab/dots.llm1.inst', 'rednote-hilab/dots.llm1.inst'),
339+
])
340+
],
341+
TemplateType.dots1,
342+
get_model_tokenizer_with_flash_attn,
343+
architectures=['Dots1ForCausalLM'],
344+
requires=['transformers>=4.53.0.dev0'],
345+
))

swift/llm/template/constant.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -82,6 +82,7 @@ class LLMTemplateType:
8282
orion = 'orion'
8383
moonlight = 'moonlight'
8484
mimo_rl = 'mimo_rl'
85+
dots1 = 'dots1'
8586

8687
aya = 'aya'
8788
c4ai = 'c4ai'

swift/llm/template/template/llm.py

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -279,3 +279,13 @@ class TeleChatTemplateMeta(TemplateMeta):
279279
LLMTemplateType.mimo_rl,
280280
default_system='You are MiMo, an AI assistant developed by Xiaomi.',
281281
))
282+
283+
register_template(
284+
TemplateMeta(
285+
LLMTemplateType.dots1,
286+
prefix=['<|system|>{{SYSTEM}}<|endofsystem|>'],
287+
prompt=['<|userprompt|>{{QUERY}}<|endofuserprompt|><|response|>'],
288+
chat_sep=['<|endofresponse|>'],
289+
suffix=['<|endofresponse|>'],
290+
default_system='You are a helpful assistant.',
291+
))

0 commit comments

Comments
 (0)