diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..18cf7be --- /dev/null +++ b/.gitattributes @@ -0,0 +1 @@ +notebooks/** linguist-vendored \ No newline at end of file diff --git a/LICENSE b/LICENSE deleted file mode 100644 index 261eeb9..0000000 --- a/LICENSE +++ /dev/null @@ -1,201 +0,0 @@ - Apache License - Version 2.0, January 2004 - http://www.apache.org/licenses/ - - TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION - - 1. Definitions. - - "License" shall mean the terms and conditions for use, reproduction, - and distribution as defined by Sections 1 through 9 of this document. - - "Licensor" shall mean the copyright owner or entity authorized by - the copyright owner that is granting the License. - - "Legal Entity" shall mean the union of the acting entity and all - other entities that control, are controlled by, or are under common - control with that entity. For the purposes of this definition, - "control" means (i) the power, direct or indirect, to cause the - direction or management of such entity, whether by contract or - otherwise, or (ii) ownership of fifty percent (50%) or more of the - outstanding shares, or (iii) beneficial ownership of such entity. - - "You" (or "Your") shall mean an individual or Legal Entity - exercising permissions granted by this License. - - "Source" form shall mean the preferred form for making modifications, - including but not limited to software source code, documentation - source, and configuration files. - - "Object" form shall mean any form resulting from mechanical - transformation or translation of a Source form, including but - not limited to compiled object code, generated documentation, - and conversions to other media types. - - "Work" shall mean the work of authorship, whether in Source or - Object form, made available under the License, as indicated by a - copyright notice that is included in or attached to the work - (an example is provided in the Appendix below). - - "Derivative Works" shall mean any work, whether in Source or Object - form, that is based on (or derived from) the Work and for which the - editorial revisions, annotations, elaborations, or other modifications - represent, as a whole, an original work of authorship. For the purposes - of this License, Derivative Works shall not include works that remain - separable from, or merely link (or bind by name) to the interfaces of, - the Work and Derivative Works thereof. - - "Contribution" shall mean any work of authorship, including - the original version of the Work and any modifications or additions - to that Work or Derivative Works thereof, that is intentionally - submitted to Licensor for inclusion in the Work by the copyright owner - or by an individual or Legal Entity authorized to submit on behalf of - the copyright owner. For the purposes of this definition, "submitted" - means any form of electronic, verbal, or written communication sent - to the Licensor or its representatives, including but not limited to - communication on electronic mailing lists, source code control systems, - and issue tracking systems that are managed by, or on behalf of, the - Licensor for the purpose of discussing and improving the Work, but - excluding communication that is conspicuously marked or otherwise - designated in writing by the copyright owner as "Not a Contribution." - - "Contributor" shall mean Licensor and any individual or Legal Entity - on behalf of whom a Contribution has been received by Licensor and - subsequently incorporated within the Work. - - 2. Grant of Copyright License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - copyright license to reproduce, prepare Derivative Works of, - publicly display, publicly perform, sublicense, and distribute the - Work and such Derivative Works in Source or Object form. - - 3. Grant of Patent License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - (except as stated in this section) patent license to make, have made, - use, offer to sell, sell, import, and otherwise transfer the Work, - where such license applies only to those patent claims licensable - by such Contributor that are necessarily infringed by their - Contribution(s) alone or by combination of their Contribution(s) - with the Work to which such Contribution(s) was submitted. If You - institute patent litigation against any entity (including a - cross-claim or counterclaim in a lawsuit) alleging that the Work - or a Contribution incorporated within the Work constitutes direct - or contributory patent infringement, then any patent licenses - granted to You under this License for that Work shall terminate - as of the date such litigation is filed. - - 4. Redistribution. You may reproduce and distribute copies of the - Work or Derivative Works thereof in any medium, with or without - modifications, and in Source or Object form, provided that You - meet the following conditions: - - (a) You must give any other recipients of the Work or - Derivative Works a copy of this License; and - - (b) You must cause any modified files to carry prominent notices - stating that You changed the files; and - - (c) You must retain, in the Source form of any Derivative Works - that You distribute, all copyright, patent, trademark, and - attribution notices from the Source form of the Work, - excluding those notices that do not pertain to any part of - the Derivative Works; and - - (d) If the Work includes a "NOTICE" text file as part of its - distribution, then any Derivative Works that You distribute must - include a readable copy of the attribution notices contained - within such NOTICE file, excluding those notices that do not - pertain to any part of the Derivative Works, in at least one - of the following places: within a NOTICE text file distributed - as part of the Derivative Works; within the Source form or - documentation, if provided along with the Derivative Works; or, - within a display generated by the Derivative Works, if and - wherever such third-party notices normally appear. The contents - of the NOTICE file are for informational purposes only and - do not modify the License. You may add Your own attribution - notices within Derivative Works that You distribute, alongside - or as an addendum to the NOTICE text from the Work, provided - that such additional attribution notices cannot be construed - as modifying the License. - - You may add Your own copyright statement to Your modifications and - may provide additional or different license terms and conditions - for use, reproduction, or distribution of Your modifications, or - for any such Derivative Works as a whole, provided Your use, - reproduction, and distribution of the Work otherwise complies with - the conditions stated in this License. - - 5. Submission of Contributions. Unless You explicitly state otherwise, - any Contribution intentionally submitted for inclusion in the Work - by You to the Licensor shall be under the terms and conditions of - this License, without any additional terms or conditions. - Notwithstanding the above, nothing herein shall supersede or modify - the terms of any separate license agreement you may have executed - with Licensor regarding such Contributions. - - 6. Trademarks. This License does not grant permission to use the trade - names, trademarks, service marks, or product names of the Licensor, - except as required for reasonable and customary use in describing the - origin of the Work and reproducing the content of the NOTICE file. - - 7. Disclaimer of Warranty. Unless required by applicable law or - agreed to in writing, Licensor provides the Work (and each - Contributor provides its Contributions) on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or - implied, including, without limitation, any warranties or conditions - of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A - PARTICULAR PURPOSE. You are solely responsible for determining the - appropriateness of using or redistributing the Work and assume any - risks associated with Your exercise of permissions under this License. - - 8. Limitation of Liability. In no event and under no legal theory, - whether in tort (including negligence), contract, or otherwise, - unless required by applicable law (such as deliberate and grossly - negligent acts) or agreed to in writing, shall any Contributor be - liable to You for damages, including any direct, indirect, special, - incidental, or consequential damages of any character arising as a - result of this License or out of the use or inability to use the - Work (including but not limited to damages for loss of goodwill, - work stoppage, computer failure or malfunction, or any and all - other commercial damages or losses), even if such Contributor - has been advised of the possibility of such damages. - - 9. Accepting Warranty or Additional Liability. While redistributing - the Work or Derivative Works thereof, You may choose to offer, - and charge a fee for, acceptance of support, warranty, indemnity, - or other liability obligations and/or rights consistent with this - License. However, in accepting such obligations, You may act only - on Your own behalf and on Your sole responsibility, not on behalf - of any other Contributor, and only if You agree to indemnify, - defend, and hold each Contributor harmless for any liability - incurred by, or claims asserted against, such Contributor by reason - of your accepting any such warranty or additional liability. - - END OF TERMS AND CONDITIONS - - APPENDIX: How to apply the Apache License to your work. - - To apply the Apache License to your work, attach the following - boilerplate notice, with the fields enclosed by brackets "[]" - replaced with your own identifying information. (Don't include - the brackets!) The text should be enclosed in the appropriate - comment syntax for the file format. We also recommend that a - file or class name and description of purpose be included on the - same "printed page" as the copyright notice for easier - identification within third-party archives. - - Copyright [yyyy] [name of copyright owner] - - Licensed under the Apache License, Version 2.0 (the "License"); - you may not use this file except in compliance with the License. - You may obtain a copy of the License at - - http://www.apache.org/licenses/LICENSE-2.0 - - Unless required by applicable law or agreed to in writing, software - distributed under the License is distributed on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - See the License for the specific language governing permissions and - limitations under the License. diff --git a/README.md b/README.md index acdb765..047063b 100644 --- a/README.md +++ b/README.md @@ -19,11 +19,11 @@ Tips: 图片完全由AI生成 ### 已支持模型 - [Qwen](https://github.com/QwenLM/Qwen.git) - - [x] [QWEN Lora微调] + - [x] [QWEN Lora、Dora微调] ### 已支持tricks及原理讲解 所有相关的trciks及讲解都在llm_tricks文件夹下 -- Dora +- [Dora代码讲解（llm_tricks/dora/READEME.md）](./llm_tricks/dora/READEME.md) ## 🤓Quick Start 不同的微调方法有不同的配置，但大体都是类似的。常规的参数在utils下的args.py。 @@ -52,4 +52,6 @@ LLM Dojo 期待你的加入！🪂 *** **愉快学习！** 📘 + +项目学习了优秀开源项目，感谢huggingface等国内小伙伴的开源项目 *** diff --git a/llm_tricks/dora/READEME.md b/llm_tricks/dora/READEME.md index fcf6a99..ed9b953 100644 --- a/llm_tricks/dora/READEME.md +++ b/llm_tricks/dora/READEME.md @@ -1,12 +1,13 @@ # DoRA: Weight-Decomposed Low-Rank Adaptation -此为Dora微调方法的实现(目前huggingface也已集成dora，故使用可以直接使用huggingface，本模块可以作为详细的理论学习) +此为Dora微调方法的实现(目前**huggingface也已集成dora**，故使用可以直接使用huggingface如下，本模块可以作为详细的**理论学习**)⚽ +huggingface中使用如下，基于lora的基础上，增加use_dora参数即可。本项目的训练框架也支持dora训练。 ```python from peft import LoraConfig # Initialize DoRA configuration -config = ( +config = LoraConfig( use_dora=True, ... ) ``` @@ -17,12 +18,27 @@ config = ( Implementation of "DoRA: Weight-Decomposed Low-Rank Adaptation" (Liu et al, 2024) https://arxiv.org/pdf/2402.09353.pdf +## 😸技术博客链接 + +- [知乎:Dora原理及代码讲解](https://zhuanlan.zhihu.com/p/695269522) + ## Tips： Dora是基于Lora的变体，故也对Lora进行了简单的示例。 DoRA可以分两步描述，其中第一步是将预训练的权重矩阵分解为幅度向量（m）和方向矩阵（V）。第二步是将LoRA应用于方向矩阵V并单独训练幅度向量m。 +## 如何使用 + + +dora_example.py 中有详细完整的 LoRA及DoRA训练与验证，建立了一个小的模型从训练到验证等全部过程。 + +lora_and_dora.ipynb 用于自己调试及学习，可以在其中逐步运行以理解其原理。 + +运行以下代码可得到实验结果 +```shell +python dora_example.py +``` ## 实验结果如下： 运行 dora_example.py。超参数设置参考文件内。小模型具有局限性，具体dora和lora的实际效果对比还需要更多的实验。 diff --git a/llm_tricks/dora/lora_and_dora.ipynb b/llm_tricks/dora/lora_and_dora.ipynb index bd3fc04..84e2ccf 100644 --- a/llm_tricks/dora/lora_and_dora.ipynb +++ b/llm_tricks/dora/lora_and_dora.ipynb @@ -16,6 +16,7 @@ "import torch.nn as nn\n", "import torch\n", "\n", + "# 构建LoraLayer\n", "class LoRALayer(nn.Module):\n", " def __init__(self, in_dim, out_dim, rank, alpha):\n", " super().__init__()\n", diff --git a/main_train.py b/main_train.py index bedca2e..88d2998 100644 --- a/main_train.py +++ b/main_train.py @@ -104,7 +104,9 @@ def load_model(model_kwargs): model = prepare_model_for_kbit_training(model, use_gradient_checkpointing=train_args.gradient_checkpointing) elif args.train_mode == 'lora': - # 找到所有linear层 + # 是否使用dora + model_kwargs.update(use_dora=args.use_dora) + model = load_model(model_kwargs) if hasattr(model, 'enable_input_require_grads'): # 不加可能报错 diff --git a/requirements.txt b/requirements.txt index 1d007d7..d6e1320 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,5 +1,5 @@ accelerate==0.21.0 -transformers==4.34 +transformers peft==0.4.0 bitsandbytes==0.39.0 loguru==0.7.0 diff --git a/train_args/sft/lora/qwen_lora.py b/train_args/sft/lora/qwen_lora.py index 515365b..0988add 100644 --- a/train_args/sft/lora/qwen_lora.py +++ b/train_args/sft/lora/qwen_lora.py @@ -25,7 +25,6 @@ class TrainArgument(TrainingArguments): warmup_steps: int = field(default=100, metadata={"help": "Linear warmup over warmup_steps."}) optim: Union[OptimizerNames, str] = field(default='paged_adamw_32bit', metadata={"help": "The optimizer to use."}) seed: int = field(default=42, metadata={"help": "Random seed that will be set at the beginning of training."}) - fp16: bool = field(default=True, metadata={"help": "Whether to use fp16 (mixed) precision instead of 32-bit"}) report_to: Optional[List[str]] = field(default='tensorboard', metadata={ "help": "The list of integrations to report the results and logs to."}) save_strategy: Union[IntervalStrategy, str] = field(default="steps", @@ -34,4 +33,9 @@ class TrainArgument(TrainingArguments): max_grad_norm: float = field(default=1.0, metadata={"help": "Max gradient norm."}) remove_unused_columns: Optional[bool] = field(default=False, metadata={ "help": "Remove columns not required by the model when using an nlp.Dataset."}) - bf16: bool = True + bf16: bool = field(default=True, metadata={ + "help": ("Whether to use bf16 (mixed) precision instead of 32-bit. Requires Ampere or higher NVIDIA" + " architecture or using CPU (use_cpu) or Ascend NPU. This is an experimental API and it may change." + ) + }) + fp16: bool = field(default=False, metadata={"help": "Whether to use fp16 (mixed) precision instead of 32-bit"}) diff --git a/utils/args.py b/utils/args.py index ef3131b..248a4fe 100644 --- a/utils/args.py +++ b/utils/args.py @@ -9,6 +9,11 @@ class TemplateName(Enum): YI = 'Yi' +class TrainMode(Enum): + QLORA = 'qlora' + LORA = 'lora' + + @dataclass class CommonArgs: """ @@ -18,7 +23,12 @@ class CommonArgs: train_data_path: Optional[str] = field(metadata={"help": "训练集路径"}) model_name_or_path: str = field(metadata={"help": "下载的所需模型路径"}) template_name: TemplateName = field(default=TemplateName.QWEN, metadata={"help": "sft时的数据格式"}) - train_mode: str = field(default="qlora", metadata={"help": "选择采用的训练方式：[qlora, lora]"}) + + # 微调方法相关选择与配置 + train_mode: TrainMode = field(default=TrainMode.LORA, metadata={"help": "选择采用的训练方式：[qlora, lora]"}) + use_dora: bool = field(default=False, metadata={"help": "仅在train_mode==lora时可以使用。是否使用Dora(一个基于lora的变体) " + "目前只支持linear and Conv2D layers."}) + task_type: str = field(default="sft", metadata={"help": "预训练任务：[pretrain, sft, dpo]"}) # lora相关配置