Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix link & bug #2902

Merged
merged 1 commit into from
Jan 10, 2025
Merged

fix link & bug #2902

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions docs/source/Instruction/支持的模型和数据集.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -413,7 +413,7 @@
|[LLM-Research/Phi-3-medium-128k-instruct](https://modelscope.cn/models/LLM-Research/Phi-3-medium-128k-instruct)|phi3|phi3|transformers>=4.36|-|[microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)|
|[LLM-Research/Phi-3.5-mini-instruct](https://modelscope.cn/models/LLM-Research/Phi-3.5-mini-instruct)|phi3|phi3|transformers>=4.36|-|[microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)|
|[LLM-Research/Phi-3.5-MoE-instruct](https://modelscope.cn/models/LLM-Research/Phi-3.5-MoE-instruct)|phi3_moe|phi3|transformers>=4.36|-|[microsoft/Phi-3.5-MoE-instruct](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct)|
|[microsoft/phi-4](https://modelscope.cn/models/microsoft/phi-4)|phi4|phi4|transformers>=4.36|-|[LLM-Research/phi-4](https://huggingface.co/LLM-Research/phi-4)|
|[LLM-Research/phi-4](https://modelscope.cn/models/LLM-Research/phi-4)|phi4|phi4|transformers>=4.36|-|[microsoft/phi-4](https://huggingface.co/microsoft/phi-4)|
|[AI-ModelScope/gemma-2b-it](https://modelscope.cn/models/AI-ModelScope/gemma-2b-it)|gemma|gemma|transformers>=4.38|-|[google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it)|
|[AI-ModelScope/gemma-2b](https://modelscope.cn/models/AI-ModelScope/gemma-2b)|gemma|gemma|transformers>=4.38|-|[google/gemma-2b](https://huggingface.co/google/gemma-2b)|
|[AI-ModelScope/gemma-7b](https://modelscope.cn/models/AI-ModelScope/gemma-7b)|gemma|gemma|transformers>=4.38|-|[google/gemma-7b](https://huggingface.co/google/gemma-7b)|
Expand Down Expand Up @@ -593,9 +593,9 @@
|[AI-ModelScope/llava-llama-3-8b-v1_1-transformers](https://modelscope.cn/models/AI-ModelScope/llava-llama-3-8b-v1_1-transformers)|llava_llama3_hf|llava_llama3_hf|transformers>=4.36|vision|[xtuner/llava-llama-3-8b-v1_1-transformers](https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-transformers)|
|[AI-ModelScope/llava-v1.6-mistral-7b](https://modelscope.cn/models/AI-ModelScope/llava-v1.6-mistral-7b)|llava1_6_mistral|llava1_6_mistral|transformers>=4.34|vision|[liuhaotian/llava-v1.6-mistral-7b](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b)|
|[AI-ModelScope/llava-v1.6-34b](https://modelscope.cn/models/AI-ModelScope/llava-v1.6-34b)|llava1_6_yi|llava1_6_yi|transformers>=4.34|vision|[liuhaotian/llava-v1.6-34b](https://huggingface.co/liuhaotian/llava-v1.6-34b)|
|[AI-Modelscope/llava-next-72b](https://modelscope.cn/models/AI-Modelscope/llava-next-72b)|llava_next_qwen|llava_next_qwen|transformers>=4.42, av|vision|[lmms-lab/llava-next-72b](https://huggingface.co/lmms-lab/llava-next-72b)|
|[AI-Modelscope/llava-next-110b](https://modelscope.cn/models/AI-Modelscope/llava-next-110b)|llava_next_qwen|llava_next_qwen|transformers>=4.42, av|vision|[lmms-lab/llava-next-110b](https://huggingface.co/lmms-lab/llava-next-110b)|
|[AI-Modelscope/llama3-llava-next-8b](https://modelscope.cn/models/AI-Modelscope/llama3-llava-next-8b)|llama3_llava_next|llama3_llava_next|transformers>=4.42, av|vision|[lmms-lab/llama3-llava-next-8b](https://huggingface.co/lmms-lab/llama3-llava-next-8b)|
|[AI-ModelScope/llava-next-72b](https://modelscope.cn/models/AI-ModelScope/llava-next-72b)|llava_next_qwen|llava_next_qwen|transformers>=4.42, av|vision|[lmms-lab/llava-next-72b](https://huggingface.co/lmms-lab/llava-next-72b)|
|[AI-ModelScope/llava-next-110b](https://modelscope.cn/models/AI-ModelScope/llava-next-110b)|llava_next_qwen|llava_next_qwen|transformers>=4.42, av|vision|[lmms-lab/llava-next-110b](https://huggingface.co/lmms-lab/llava-next-110b)|
|[AI-ModelScope/llama3-llava-next-8b](https://modelscope.cn/models/AI-ModelScope/llama3-llava-next-8b)|llama3_llava_next|llama3_llava_next|transformers>=4.42, av|vision|[lmms-lab/llama3-llava-next-8b](https://huggingface.co/lmms-lab/llama3-llava-next-8b)|
|[deepseek-ai/deepseek-vl-1.3b-chat](https://modelscope.cn/models/deepseek-ai/deepseek-vl-1.3b-chat)|deepseek_vl|deepseek_vl|-|vision|[deepseek-ai/deepseek-vl-1.3b-chat](https://huggingface.co/deepseek-ai/deepseek-vl-1.3b-chat)|
|[deepseek-ai/deepseek-vl-7b-chat](https://modelscope.cn/models/deepseek-ai/deepseek-vl-7b-chat)|deepseek_vl|deepseek_vl|-|vision|[deepseek-ai/deepseek-vl-7b-chat](https://huggingface.co/deepseek-ai/deepseek-vl-7b-chat)|
|[deepseek-ai/deepseek-vl2-tiny](https://modelscope.cn/models/deepseek-ai/deepseek-vl2-tiny)|deepseek_vl2|deepseek_vl2|transformers<4.42|vision|[deepseek-ai/deepseek-vl2-tiny](https://huggingface.co/deepseek-ai/deepseek-vl2-tiny)|
Expand Down
8 changes: 4 additions & 4 deletions docs/source_en/Instruction/Supported-models-and-datasets.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -413,7 +413,7 @@ The table below introduces the models integrated with ms-swift:
|[LLM-Research/Phi-3-medium-128k-instruct](https://modelscope.cn/models/LLM-Research/Phi-3-medium-128k-instruct)|phi3|phi3|transformers>=4.36|-|[microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)|
|[LLM-Research/Phi-3.5-mini-instruct](https://modelscope.cn/models/LLM-Research/Phi-3.5-mini-instruct)|phi3|phi3|transformers>=4.36|-|[microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)|
|[LLM-Research/Phi-3.5-MoE-instruct](https://modelscope.cn/models/LLM-Research/Phi-3.5-MoE-instruct)|phi3_moe|phi3|transformers>=4.36|-|[microsoft/Phi-3.5-MoE-instruct](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct)|
|[microsoft/phi-4](https://modelscope.cn/models/microsoft/phi-4)|phi4|phi4|transformers>=4.36|-|[LLM-Research/phi-4](https://huggingface.co/LLM-Research/phi-4)|
|[LLM-Research/phi-4](https://modelscope.cn/models/LLM-Research/phi-4)|phi4|phi4|transformers>=4.36|-|[microsoft/phi-4](https://huggingface.co/microsoft/phi-4)|
|[AI-ModelScope/gemma-2b-it](https://modelscope.cn/models/AI-ModelScope/gemma-2b-it)|gemma|gemma|transformers>=4.38|-|[google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it)|
|[AI-ModelScope/gemma-2b](https://modelscope.cn/models/AI-ModelScope/gemma-2b)|gemma|gemma|transformers>=4.38|-|[google/gemma-2b](https://huggingface.co/google/gemma-2b)|
|[AI-ModelScope/gemma-7b](https://modelscope.cn/models/AI-ModelScope/gemma-7b)|gemma|gemma|transformers>=4.38|-|[google/gemma-7b](https://huggingface.co/google/gemma-7b)|
Expand Down Expand Up @@ -593,9 +593,9 @@ The table below introduces the models integrated with ms-swift:
|[AI-ModelScope/llava-llama-3-8b-v1_1-transformers](https://modelscope.cn/models/AI-ModelScope/llava-llama-3-8b-v1_1-transformers)|llava_llama3_hf|llava_llama3_hf|transformers>=4.36|vision|[xtuner/llava-llama-3-8b-v1_1-transformers](https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-transformers)|
|[AI-ModelScope/llava-v1.6-mistral-7b](https://modelscope.cn/models/AI-ModelScope/llava-v1.6-mistral-7b)|llava1_6_mistral|llava1_6_mistral|transformers>=4.34|vision|[liuhaotian/llava-v1.6-mistral-7b](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b)|
|[AI-ModelScope/llava-v1.6-34b](https://modelscope.cn/models/AI-ModelScope/llava-v1.6-34b)|llava1_6_yi|llava1_6_yi|transformers>=4.34|vision|[liuhaotian/llava-v1.6-34b](https://huggingface.co/liuhaotian/llava-v1.6-34b)|
|[AI-Modelscope/llava-next-72b](https://modelscope.cn/models/AI-Modelscope/llava-next-72b)|llava_next_qwen|llava_next_qwen|transformers>=4.42, av|vision|[lmms-lab/llava-next-72b](https://huggingface.co/lmms-lab/llava-next-72b)|
|[AI-Modelscope/llava-next-110b](https://modelscope.cn/models/AI-Modelscope/llava-next-110b)|llava_next_qwen|llava_next_qwen|transformers>=4.42, av|vision|[lmms-lab/llava-next-110b](https://huggingface.co/lmms-lab/llava-next-110b)|
|[AI-Modelscope/llama3-llava-next-8b](https://modelscope.cn/models/AI-Modelscope/llama3-llava-next-8b)|llama3_llava_next|llama3_llava_next|transformers>=4.42, av|vision|[lmms-lab/llama3-llava-next-8b](https://huggingface.co/lmms-lab/llama3-llava-next-8b)|
|[AI-ModelScope/llava-next-72b](https://modelscope.cn/models/AI-ModelScope/llava-next-72b)|llava_next_qwen|llava_next_qwen|transformers>=4.42, av|vision|[lmms-lab/llava-next-72b](https://huggingface.co/lmms-lab/llava-next-72b)|
|[AI-ModelScope/llava-next-110b](https://modelscope.cn/models/AI-ModelScope/llava-next-110b)|llava_next_qwen|llava_next_qwen|transformers>=4.42, av|vision|[lmms-lab/llava-next-110b](https://huggingface.co/lmms-lab/llava-next-110b)|
|[AI-ModelScope/llama3-llava-next-8b](https://modelscope.cn/models/AI-ModelScope/llama3-llava-next-8b)|llama3_llava_next|llama3_llava_next|transformers>=4.42, av|vision|[lmms-lab/llama3-llava-next-8b](https://huggingface.co/lmms-lab/llama3-llava-next-8b)|
|[deepseek-ai/deepseek-vl-1.3b-chat](https://modelscope.cn/models/deepseek-ai/deepseek-vl-1.3b-chat)|deepseek_vl|deepseek_vl|-|vision|[deepseek-ai/deepseek-vl-1.3b-chat](https://huggingface.co/deepseek-ai/deepseek-vl-1.3b-chat)|
|[deepseek-ai/deepseek-vl-7b-chat](https://modelscope.cn/models/deepseek-ai/deepseek-vl-7b-chat)|deepseek_vl|deepseek_vl|-|vision|[deepseek-ai/deepseek-vl-7b-chat](https://huggingface.co/deepseek-ai/deepseek-vl-7b-chat)|
|[deepseek-ai/deepseek-vl2-tiny](https://modelscope.cn/models/deepseek-ai/deepseek-vl2-tiny)|deepseek_vl2|deepseek_vl2|transformers<4.42|vision|[deepseek-ai/deepseek-vl2-tiny](https://huggingface.co/deepseek-ai/deepseek-vl2-tiny)|
Expand Down
10 changes: 9 additions & 1 deletion swift/llm/argument/base_args/base_args.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -241,7 +241,14 @@ def get_template(self, processor: 'Processor') -> 'Template':
logger.info(f'default_system: {template.template_meta.default_system}')
return template

def get_model_processor(self, *, model=None, model_type=None, model_revision=None, task_type=None, **kwargs):
def get_model_processor(self,
*,
model=None,
model_type=None,
model_revision=None,
task_type=None,
num_labels=None,
**kwargs):
if self.tuner_backend == 'unsloth':
return load_by_unsloth(self)
kwargs.update(self.get_model_kwargs())
Expand All @@ -250,5 +257,6 @@ def get_model_processor(self, *, model=None, model_type=None, model_revision=Non
kwargs['model_type'] = model_type or self.model_type
kwargs['model_revision'] = model_revision or self.model_revision
kwargs['task_type'] = task_type or self.task_type
kwargs['num_labels'] = num_labels or self.num_labels

return get_model_tokenizer(**kwargs)
6 changes: 3 additions & 3 deletions swift/llm/model/model/llava.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -334,7 +334,7 @@ def _new_forward(*args, **kwargs):
MLLMModelType.llama3_llava_next,
[
ModelGroup([
Model('AI-Modelscope/llama3-llava-next-8b', 'lmms-lab/llama3-llava-next-8b'),
Model('AI-ModelScope/llama3-llava-next-8b', 'lmms-lab/llama3-llava-next-8b'),
], ),
],
TemplateType.llama3_llava_next,
Expand Down Expand Up @@ -379,8 +379,8 @@ def _new_forward(*args, **kwargs):
ModelMeta(
MLLMModelType.llava_next_qwen, [
ModelGroup([
Model('AI-Modelscope/llava-next-72b', 'lmms-lab/llava-next-72b'),
Model('AI-Modelscope/llava-next-110b', 'lmms-lab/llava-next-110b'),
Model('AI-ModelScope/llava-next-72b', 'lmms-lab/llava-next-72b'),
Model('AI-ModelScope/llava-next-110b', 'lmms-lab/llava-next-110b'),
], ),
],
TemplateType.llava_next_qwen,
Expand Down
13 changes: 11 additions & 2 deletions swift/llm/train/rlhf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,10 +30,19 @@ def _prepare_model_tokenizer(self):
model_type = getattr(args, f'{key}_model_type')
model_revision = getattr(args, f'{key}_model_revision')
adapters = args.adapters if key == 'ref' else args.reward_adapters
task_type = args.task_type if origin_key == 'ref' else 'seq_cls'
if origin_key == 'ref':
task_type = args.task_type
num_labels = None
else:
task_type = 'seq_cls'
num_labels = 1
# Be aware of the unexpected behavior caused by double monkey patching.
model = args.get_model_processor(
model=model_id_or_path, model_type=model_type, model_revision=model_revision, task_type=task_type)[0]
model=model_id_or_path,
model_type=model_type,
model_revision=model_revision,
task_type=task_type,
num_labels=num_labels)[0]

model = prepare_adapter(args, model, adapters)
if origin_key in {'ref', 'reward'}:
Expand Down
5 changes: 3 additions & 2 deletions tests/llm/test_run.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
if __name__ == '__main__':
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0,1'
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'

import os
Expand Down Expand Up @@ -242,13 +242,14 @@ def test_rlhf(self):
if rlhf_type != 'kto' else 'AI-ModelScope/ultrafeedback-binarized-preferences-cleaned-kto#100')
train_kwargs = {}
if rlhf_type == 'ppo':
train_kwargs['reward_model_type'] = 'Qwen/Qwen2-1.5B-Instruct'
train_kwargs['reward_model'] = 'Qwen/Qwen2-1.5B-Instruct'
output = rlhf_main(
RLHFArguments(
rlhf_type=rlhf_type,
model='Qwen/Qwen2-1.5B-Instruct',
dataset=dataset,
eval_steps=5,
split_dataset_ratio=0.05,
**train_kwargs,
**kwargs))
if rlhf_type == 'ppo':
Expand Down
Loading