diff --git a/LLaMA-Efficient-Tuning/.gitattributes b/LLaMA-Efficient-Tuning/.gitattributes
new file mode 100644
index 0000000000000000000000000000000000000000..dfe0770424b2a19faf507a501ebfc23be8f54e7b
--- /dev/null
+++ b/LLaMA-Efficient-Tuning/.gitattributes
@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto
diff --git a/LLaMA-Efficient-Tuning/.gitignore b/LLaMA-Efficient-Tuning/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..68bc17f9ff2104a9d7b6777058bb4c343ca72609
--- /dev/null
+++ b/LLaMA-Efficient-Tuning/.gitignore
@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+# Usually these files are written by a python script from a template
+# before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+# For a library or package, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+# However, in case of collaboration, if having platform-specific dependencies or dependencies
+# having no cross-platform support, pipenv may install dependencies that don't work, or not
+# install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+# This is especially recommended for binary packages to ensure reproducibility, and is more
+# commonly ignored for libraries.
+# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+# in version control.
+# https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+# and can be added to the global gitignore or merged into this file. For a more nuclear
+# option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
diff --git a/LLaMA-Efficient-Tuning/LICENSE b/LLaMA-Efficient-Tuning/LICENSE
new file mode 100644
index 0000000000000000000000000000000000000000..b09cd7856d58590578ee1a4f3ad45d1310a97f87
--- /dev/null
+++ b/LLaMA-Efficient-Tuning/LICENSE
@@ -0,0 +1,201 @@
+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/LLaMA-Efficient-Tuning/README.md b/LLaMA-Efficient-Tuning/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9d1ea252d45a33c100f8a61ce986d8e1ecf0d343
--- /dev/null
+++ b/LLaMA-Efficient-Tuning/README.md
@@ -0,0 +1,482 @@
+# LLaMA Efficient Tuning
+
+[](https://github.com/hiyouga/LLaMA-Efficient-Tuning/stargazers)
+[](LICENSE)
+[](https://github.com/hiyouga/LLaMA-Efficient-Tuning/commits/main)
+[](https://pypi.org/project/llmtuner/)
+[](https://pypi.org/project/llmtuner/)
+[](https://github.com/hiyouga/LLaMA-Efficient-Tuning/pulls)
+[](https://discord.gg/7HGMsdxqJ)
+
+👋 Join our [WeChat](assets/wechat.jpg).
+
+\[ English | [中文](README_zh.md) \]
+
+## Changelog
+
+[23/09/10] Now we support using **[FlashAttention](https://github.com/Dao-AILab/flash-attention)** for the LLaMA models. Try `--flash_attn` argument to enable FlashAttention-2 if you are using RTX4090, A100 or H100 GPUs (experimental feature).
+
+[23/08/18] Now we support **resuming training**, upgrade `transformers` to `4.31.0` to enjoy this feature.
+
+[23/08/12] Now we support **RoPE scaling** to extend the context length of the LLaMA models. Try `--rope_scaling linear` argument in training and `--rope_scaling dynamic` argument at inference to extrapolate the position embeddings.
+
+[23/08/11] Now we support **[DPO training](https://arxiv.org/abs/2305.18290)** for instruction-tuned models. See [this example](#dpo-training) to train your models.
+
+[23/07/31] Now we support **dataset streaming**. Try `--streaming` and `--max_steps 10000` arguments to load your dataset in streaming mode.
+
+[23/07/29] We release two instruction-tuned 13B models at Hugging Face. See these Hugging Face Repos ([LLaMA-2](https://huggingface.co/hiyouga/Llama-2-Chinese-13b-chat) / [Baichuan](https://huggingface.co/hiyouga/Baichuan-13B-sft)) for details.
+
+[23/07/18] Now we develop an **all-in-one Web UI** for training, evaluation and inference. Try `train_web.py` to fine-tune models in your Web browser. Thank [@KanadeSiina](https://github.com/KanadeSiina) and [@codemayq](https://github.com/codemayq) for their efforts in the development.
+
+[23/07/09] Now we release **[FastEdit](https://github.com/hiyouga/FastEdit)** ⚡🩹, an easy-to-use package for editing the factual knowledge of large language models efficiently. Please follow [FastEdit](https://github.com/hiyouga/FastEdit) if you are interested.
+
+[23/06/29] We provide a **reproducible example** of training a chat model using instruction-following datasets, see [Baichuan-7B-sft](https://huggingface.co/hiyouga/Baichuan-7B-sft) for details.
+
+[23/06/22] Now we align the [demo API](src/api_demo.py) with the [OpenAI's](https://platform.openai.com/docs/api-reference/chat) format where you can insert the fine-tuned model in **arbitrary ChatGPT-based applications**.
+
+[23/06/03] Now we support quantized training and inference (aka **[QLoRA](https://github.com/artidoro/qlora)**). Try `--quantization_bit 4/8` argument to work with quantized models.
+
+## Supported Models
+
+| Model | Model size | Default module | Template |
+| -------------------------------------------------------- | --------------------------- | ----------------- | --------- |
+| [LLaMA](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | q_proj,v_proj | - |
+| [LLaMA-2](https://huggingface.co/meta-llama) | 7B/13B/70B | q_proj,v_proj | llama2 |
+| [BLOOM](https://huggingface.co/bigscience/bloom) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - |
+| [BLOOMZ](https://huggingface.co/bigscience/bloomz) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - |
+| [Falcon](https://huggingface.co/tiiuae/falcon-7b) | 7B/40B | query_key_value | - |
+| [Baichuan](https://github.com/baichuan-inc/Baichuan-13B) | 7B/13B | W_pack | baichuan |
+| [Baichuan2](https://github.com/baichuan-inc/Baichuan2) | 7B/13B | W_pack | baichuan2 |
+| [InternLM](https://github.com/InternLM/InternLM) | 7B/20B | q_proj,v_proj | intern |
+| [Qwen](https://github.com/QwenLM/Qwen-7B) | 7B | c_attn | chatml |
+| [XVERSE](https://github.com/xverse-ai/XVERSE-13B) | 13B | q_proj,v_proj | xverse |
+| [ChatGLM2](https://github.com/THUDM/ChatGLM2-6B) | 6B | query_key_value | chatglm2 |
+| [Phi-1.5](https://huggingface.co/microsoft/phi-1_5) | 1.5B | Wqkv | - |
+
+> [!NOTE]
+> **Default module** is used for the `--lora_target` argument, you can use `--lora_target all` to specify all the available modules.
+>
+> For the "base" models, the `--template` argument can be chosen from `default`, `alpaca`, `vicuna` etc. But make sure to use the corresponding template for the "chat" models.
+
+## Supported Training Approaches
+
+| Approach | Full-parameter | Partial-parameter | LoRA | QLoRA |
+| ---------------------- | ------------------ | ------------------ | ------------------ | ------------------ |
+| Pre-Training | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| Supervised Fine-Tuning | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| Reward Modeling | | | :white_check_mark: | :white_check_mark: |
+| PPO Training | | | :white_check_mark: | :white_check_mark: |
+| DPO Training | :white_check_mark: | | :white_check_mark: | :white_check_mark: |
+
+> [!NOTE]
+> Use `--quantization_bit 4/8` argument to enable QLoRA.
+
+## Provided Datasets
+
+- For pre-training:
+ - [Wiki Demo (en)](data/wiki_demo.txt)
+ - [RefinedWeb (en)](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)
+ - [StarCoder (en)](https://huggingface.co/datasets/bigcode/starcoderdata)
+ - [Wikipedia (en)](https://huggingface.co/datasets/olm/olm-wikipedia-20221220)
+ - [Wikipedia (zh)](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered)
+- For supervised fine-tuning:
+ - [Stanford Alpaca (en)](https://github.com/tatsu-lab/stanford_alpaca)
+ - [Stanford Alpaca (zh)](https://github.com/ymcui/Chinese-LLaMA-Alpaca)
+ - [GPT-4 Generated Data (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
+ - [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1)
+ - [Self-cognition (zh)](data/self_cognition.json)
+ - [ShareGPT (zh)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT/tree/main/Chinese-instruction-collection)
+ - [Guanaco Dataset (multilingual)](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset)
+ - [BELLE 2M (zh)](https://huggingface.co/datasets/BelleGroup/train_2M_CN)
+ - [BELLE 1M (zh)](https://huggingface.co/datasets/BelleGroup/train_1M_CN)
+ - [BELLE 0.5M (zh)](https://huggingface.co/datasets/BelleGroup/train_0.5M_CN)
+ - [BELLE Dialogue 0.4M (zh)](https://huggingface.co/datasets/BelleGroup/generated_chat_0.4M)
+ - [BELLE School Math 0.25M (zh)](https://huggingface.co/datasets/BelleGroup/school_math_0.25M)
+ - [BELLE Multiturn Chat 0.8M (zh)](https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M)
+ - [LIMA (en)](https://huggingface.co/datasets/GAIR/lima)
+ - [CodeAlpaca 20k (en)](https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k)
+ - [Alpaca CoT (multilingual)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT)
+ - [MathInstruct (en)](https://huggingface.co/datasets/TIGER-Lab/MathInstruct)
+ - [Firefly 1.1M (zh)](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M)
+ - [Web QA (zh)](https://huggingface.co/datasets/suolyer/webqa)
+ - [UltraChat (en)](https://github.com/thunlp/UltraChat)
+ - [WebNovel (zh)](https://huggingface.co/datasets/zxbsmk/webnovel_cn)
+ - [Ad Gen (zh)](https://huggingface.co/datasets/HasturOfficial/adgen)
+- For reward modeling or DPO training:
+ - [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
+ - [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1)
+ - [GPT-4 Generated Data (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
+
+Please refer to [data/README.md](data/README.md) for details.
+
+Some datasets require confirmation before using them, so we recommend logging in with your Hugging Face account using these commands.
+
+```bash
+pip install --upgrade huggingface_hub
+huggingface-cli login
+```
+
+## Requirement
+
+- Python 3.8+ and PyTorch 1.13.1+
+- 🤗Transformers, Datasets, Accelerate, PEFT and TRL
+- sentencepiece, protobuf and tiktoken
+- jieba, rouge-chinese and nltk (used at evaluation)
+- gradio and matplotlib (used in web_demo.py)
+- uvicorn, fastapi and sse-starlette (used in api_demo.py)
+
+And **powerful GPUs**!
+
+## Getting Started
+
+### Data Preparation (optional)
+
+Please refer to `data/example_dataset` for checking the details about the format of dataset files. You can either use a single `.json` file or a [dataset loading script](https://huggingface.co/docs/datasets/dataset_script) with multiple files to create a custom dataset.
+
+> [!NOTE]
+> Please update `data/dataset_info.json` to use your custom dataset. About the format of this file, please refer to `data/README.md`.
+
+### Dependence Installation (optional)
+
+```bash
+git clone https://github.com/hiyouga/LLaMA-Efficient-Tuning.git
+conda create -n llama_etuning python=3.10
+conda activate llama_etuning
+cd LLaMA-Efficient-Tuning
+pip install -r requirements.txt
+```
+
+If you want to enable the quantized LoRA (QLoRA) on the Windows platform, you will be required to install a pre-built version of `bitsandbytes` library, which supports CUDA 11.1 to 12.1.
+
+```bash
+pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.39.1-py3-none-win_amd64.whl
+```
+
+### All-in-one Web UI
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python src/train_web.py
+```
+
+We **strongly recommend** using the all-in-one Web UI for newcomers since it can also generate training scripts automatically, even without a GPU environment.
+
+> [!WARNING]
+> Currently the web UI only supports training on **a single GPU**.
+
+### Train on a single GPU
+
+> [!IMPORTANT]
+> If you want to train models on multiple GPUs, please refer to [Distributed Training](#distributed-training).
+
+#### Pre-Training
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
+ --stage pt \
+ --model_name_or_path path_to_llama_model \
+ --do_train \
+ --dataset wiki_demo \
+ --finetuning_type lora \
+ --lora_target q_proj,v_proj \
+ --output_dir path_to_pt_checkpoint \
+ --overwrite_cache \
+ --per_device_train_batch_size 4 \
+ --gradient_accumulation_steps 4 \
+ --lr_scheduler_type cosine \
+ --logging_steps 10 \
+ --save_steps 1000 \
+ --learning_rate 5e-5 \
+ --num_train_epochs 3.0 \
+ --plot_loss \
+ --fp16
+```
+
+#### Supervised Fine-Tuning
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
+ --stage sft \
+ --model_name_or_path path_to_llama_model \
+ --do_train \
+ --dataset alpaca_gpt4_en \
+ --template default \
+ --finetuning_type lora \
+ --lora_target q_proj,v_proj \
+ --output_dir path_to_sft_checkpoint \
+ --overwrite_cache \
+ --per_device_train_batch_size 4 \
+ --gradient_accumulation_steps 4 \
+ --lr_scheduler_type cosine \
+ --logging_steps 10 \
+ --save_steps 1000 \
+ --learning_rate 5e-5 \
+ --num_train_epochs 3.0 \
+ --plot_loss \
+ --fp16
+```
+
+#### Reward Modeling
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
+ --stage rm \
+ --model_name_or_path path_to_llama_model \
+ --do_train \
+ --dataset comparison_gpt4_en \
+ --template default \
+ --finetuning_type lora \
+ --lora_target q_proj,v_proj \
+ --resume_lora_training False \
+ --checkpoint_dir path_to_sft_checkpoint \
+ --output_dir path_to_rm_checkpoint \
+ --per_device_train_batch_size 2 \
+ --gradient_accumulation_steps 4 \
+ --lr_scheduler_type cosine \
+ --logging_steps 10 \
+ --save_steps 1000 \
+ --learning_rate 1e-6 \
+ --num_train_epochs 1.0 \
+ --plot_loss \
+ --fp16
+```
+
+#### PPO Training
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
+ --stage ppo \
+ --model_name_or_path path_to_llama_model \
+ --do_train \
+ --dataset alpaca_gpt4_en \
+ --template default \
+ --finetuning_type lora \
+ --lora_target q_proj,v_proj \
+ --resume_lora_training False \
+ --checkpoint_dir path_to_sft_checkpoint \
+ --reward_model path_to_rm_checkpoint \
+ --output_dir path_to_ppo_checkpoint \
+ --per_device_train_batch_size 2 \
+ --gradient_accumulation_steps 4 \
+ --lr_scheduler_type cosine \
+ --logging_steps 10 \
+ --save_steps 1000 \
+ --learning_rate 1e-5 \
+ --num_train_epochs 1.0 \
+ --plot_loss \
+ --fp16
+```
+
+#### DPO Training
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
+ --stage dpo \
+ --model_name_or_path path_to_llama_model \
+ --do_train \
+ --dataset comparison_gpt4_en \
+ --template default \
+ --finetuning_type lora \
+ --lora_target q_proj,v_proj \
+ --resume_lora_training False \
+ --checkpoint_dir path_to_sft_checkpoint \
+ --output_dir path_to_dpo_checkpoint \
+ --per_device_train_batch_size 2 \
+ --gradient_accumulation_steps 4 \
+ --lr_scheduler_type cosine \
+ --logging_steps 10 \
+ --save_steps 1000 \
+ --learning_rate 1e-5 \
+ --num_train_epochs 1.0 \
+ --plot_loss \
+ --fp16
+```
+
+### Distributed Training
+
+#### Use Huggingface Accelerate
+
+```bash
+accelerate config # configure the environment
+accelerate launch src/train_bash.py # arguments (same as above)
+```
+
+Example config for LoRA training
+
+```yaml
+compute_environment: LOCAL_MACHINE
+distributed_type: MULTI_GPU
+downcast_bf16: 'no'
+gpu_ids: all
+machine_rank: 0
+main_training_function: main
+mixed_precision: fp16
+num_machines: 1
+num_processes: 4
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false
+```
+
+Example config for full-parameter training with DeepSpeed ZeRO-2
+
+```json
+{
+ "train_batch_size": "auto",
+ "train_micro_batch_size_per_gpu": "auto",
+ "gradient_accumulation_steps": "auto",
+ "gradient_clipping": "auto",
+ "zero_allow_untested_optimizer": true,
+ "fp16": {
+ "enabled": "auto",
+ "loss_scale": 0,
+ "initial_scale_power": 16,
+ "loss_scale_window": 1000,
+ "hysteresis": 2,
+ "min_loss_scale": 1
+ },
+ "zero_optimization": {
+ "stage": 2,
+ "allgather_partitions": true,
+ "allgather_bucket_size": 5e8,
+ "reduce_scatter": true,
+ "reduce_bucket_size": 5e8,
+ "overlap_comm": false,
+ "contiguous_gradients": true
+ }
+}
+```
+
+LoRA 训练的 Accelerate 配置示例
+
+```yaml
+compute_environment: LOCAL_MACHINE
+distributed_type: MULTI_GPU
+downcast_bf16: 'no'
+gpu_ids: all
+machine_rank: 0
+main_training_function: main
+mixed_precision: fp16
+num_machines: 1
+num_processes: 4
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false
+```
+
+使用 DeepSpeed ZeRO-2 进行全参数训练的 DeepSpeed 配置示例
+
+```json
+{
+ "train_batch_size": "auto",
+ "train_micro_batch_size_per_gpu": "auto",
+ "gradient_accumulation_steps": "auto",
+ "gradient_clipping": "auto",
+ "zero_allow_untested_optimizer": true,
+ "fp16": {
+ "enabled": "auto",
+ "loss_scale": 0,
+ "initial_scale_power": 16,
+ "loss_scale_window": 1000,
+ "hysteresis": 2,
+ "min_loss_scale": 1
+ },
+ "zero_optimization": {
+ "stage": 2,
+ "allgather_partitions": true,
+ "allgather_bucket_size": 5e8,
+ "reduce_scatter": true,
+ "reduce_bucket_size": 5e8,
+ "overlap_comm": false,
+ "contiguous_gradients": true
+ }
+}
+```
+
+