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

[PaddleNLP 3.0] Update README #8681

Merged
merged 35 commits into from
Jul 12, 2024
Merged

[PaddleNLP 3.0] Update README #8681

Show file tree
Hide file tree
Changes from 11 commits
Commits
Show all changes
35 commits
Select commit Hold shift + click to select a range
ca9518c
update
DrownFish19 Jun 28, 2024
8d30c5d
Merge branch 'PaddlePaddle:develop' into dev_update_readme_3.0beta
DrownFish19 Jul 3, 2024
d307fbb
update readme
DrownFish19 Jul 3, 2024
7dfafba
update
DrownFish19 Jul 4, 2024
91886d6
update
DrownFish19 Jul 4, 2024
f5fe743
Merge branch 'PaddlePaddle:develop' into dev_update_readme_3.0beta
DrownFish19 Jul 5, 2024
392ed1f
update
DrownFish19 Jul 5, 2024
ecc0b1a
Merge branch 'dev_update_readme_3.0beta' of github.com:DrownFish19/Pa…
DrownFish19 Jul 5, 2024
99617ec
update
DrownFish19 Jul 5, 2024
7745c49
update
DrownFish19 Jul 5, 2024
774c45b
update
DrownFish19 Jul 5, 2024
7a46e6a
update
DrownFish19 Jul 5, 2024
c6d2104
update README(EN)
DrownFish19 Jul 8, 2024
6f5e235
correct broken links in readme
jzhang533 Jul 10, 2024
ae6c69d
Merge branch 'PaddlePaddle:develop' into dev_update_readme_3.0beta
DrownFish19 Jul 10, 2024
bacb006
add markdownlint
DrownFish19 Jul 10, 2024
dc88f8f
update
DrownFish19 Jul 10, 2024
7f68f68
add check_spaces
DrownFish19 Jul 10, 2024
b09c85e
update
DrownFish19 Jul 10, 2024
1924426
Merge remote-tracking branch 'paddlenlp-zhangjun/update-break-links-i…
DrownFish19 Jul 10, 2024
46a55c9
Merge branch 'PaddlePaddle:develop' into dev_update_readme_3.0beta
DrownFish19 Jul 10, 2024
f35db62
Merge branch 'develop' into dev_update_readme_3.0beta
DrownFish19 Jul 10, 2024
f9efc5d
update readme
DrownFish19 Jul 10, 2024
26a2563
Merge branch 'PaddlePaddle:develop' into dev_update_readme_3.0beta
DrownFish19 Jul 10, 2024
87db3a8
update readme
DrownFish19 Jul 10, 2024
7d0627c
update
DrownFish19 Jul 10, 2024
b4a5862
update
DrownFish19 Jul 10, 2024
68ac2b3
Merge branch 'dev_update_readme_3.0beta' of github.com:DrownFish19/Pa…
DrownFish19 Jul 10, 2024
d3d90a9
update readmes
DrownFish19 Jul 11, 2024
0869e22
Merge branch 'develop' into dev_update_readme_3.0beta
DrownFish19 Jul 11, 2024
0574f12
update
DrownFish19 Jul 11, 2024
f99f61b
update
DrownFish19 Jul 11, 2024
6ad298b
update llm doc index
DrownFish19 Jul 11, 2024
e00e1d1
update
DrownFish19 Jul 11, 2024
2e6b521
add rlhf docs
DrownFish19 Jul 11, 2024
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
47 changes: 33 additions & 14 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,13 +31,13 @@

## News 📢

* **2024.06.27 [PaddleNLP v3.0 Beta](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v3.0.0)**：拥抱大模型，体验全升级。统一大模型工具链，实现国产计算芯片全流程接入；全面支持飞桨4D并行配置、高效精调策略、高效对齐算法、高性能推理等大模型产业级应用流程；自研极致收敛的RsLoRA+算法、自动扩缩容存储机制Unified Checkpoint和通用化支持FastFFN、FusedQKV助力大模型训推；主流模型持续支持更新，提供高效解决方案。
* **2024.06.27 [PaddleNLP v3.0 Beta](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v3.0.0-beta0)**：拥抱大模型，体验全升级。统一大模型工具链，实现国产计算芯片全流程接入；全面支持飞桨4D并行配置、高效精调策略、高效对齐算法、高性能推理等大模型产业级应用流程；自研极致收敛的RsLoRA+算法、自动扩缩容存储机制Unified Checkpoint和通用化支持FastFFN、FusedQKV助力大模型训推；主流模型持续支持更新，提供高效解决方案。

* **2024.04.24 [PaddleNLP v2.8](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.8.0)**：自研极致收敛的RsLoRA+算法，大幅提升PEFT训练收敛速度以及训练效果；引入高性能生成加速到RLHF PPO算法，打破 PPO 训练中生成速度瓶颈，PPO训练性能大幅领先。通用化支持 FastFFN、FusedQKV等多个大模型训练性能优化方式，大模型训练更快、更稳定。

* **2024.01.04 [PaddleNLP v2.7](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.7.1)**： 大模型体验全面升级，统一工具链大模型入口。统一预训练、精调、压缩、推理以及部署等环节的实现代码，到 `PaddleNLP/llm`目录。全新[大模型工具链文档](https://paddlenlp.readthedocs.io/zh/latest/llm/finetune.html)，一站式指引用户从大模型入门到业务部署上线。自动扩缩容存储机制 Unified Checkpoint，大大提高大模型存储的通用性。高效微调升级，支持了高效微调+LoRA同时使用，支持了QLoRA等算法。
* **2024.01.04 [PaddleNLP v2.7](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.7.1)**： 大模型体验全面升级，统一工具链大模型入口。统一预训练、精调、压缩、推理以及部署等环节的实现代码，到 `PaddleNLP/llm`目录。全新[大模型工具链文档](https://paddlenlp.readthedocs.io/zh/latest/llm/pretraining/index.html)，一站式指引用户从大模型入门到业务部署上线。自动扩缩容存储机制 Unified Checkpoint，大大提高大模型存储的通用性。高效微调升级，支持了高效微调+LoRA同时使用，支持了QLoRA等算法。

* **2023.08.15 [PaddleNLP v2.6](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.6.0)**： 发布[全流程大模型工具链](./llm)，涵盖预训练，精调，压缩，推理以及部署等各个环节，为用户提供端到端的大模型方案和一站式的开发体验；内置[4D并行分布式Trainer](./docs/trainer.md)，[高效微调算法LoRA/Prefix Tuning](./llm#33-lora), [自研INT8/INT4量化算法](./llm#6-量化)等等；全面支持[LLaMA 1/2](./llm/llama), [BLOOM](.llm/bloom), [ChatGLM 1/2](./llm/chatglm), [GLM](./llm/glm), [OPT](./llm/opt)等主流大模型
* **2023.08.15 [PaddleNLP v2.6](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.6.0)**： 发布[全流程大模型工具链](./llm)，涵盖预训练，精调，压缩，推理以及部署等各个环节，为用户提供端到端的大模型方案和一站式的开发体验；内置[4D并行分布式Trainer](./docs/trainer.md)，[高效微调算法LoRA/Prefix Tuning](./llm#33-lora), [自研INT8/INT4量化算法](./llm#6-量化)等等；全面支持[LLaMA 1/2](./llm/config/llama), [BLOOM](.llm/config/bloom), [ChatGLM 1/2](./llm/config/chatglm), [GLM](./llm/config/glm), [OPT](./llm/config/opt)等主流大模型
Copy link
Member

@gongel gongel Jul 5, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

bloom地址有问题，GLM要不就不要了。

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

bloom已经修改，GLM删除了



## 特性
Expand All @@ -63,22 +63,41 @@ Unified Checkpoint大模型存储格式在模型参数分布上支持动态扩

## 模型支持

| Model | Pretrain | SFT | LoRA | Prefix Tuning | DPO | RLHF | Quantization | Weight convert |
|--------------------------------------------|:--------:|:---:|:----:|:-------------:|:---:|:----:|:------------:|:--------------:|
| [LLaMA](./llm/config/llama) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| [Qwen](./llm/config/qwen) | ✅ | ✅ | ✅ | ✅ | ✅ | 🚧 | 🚧 | ✅ |
| [Mixtral](./llm/config/mixtral) | ✅ | ✅ | ✅ | ❌ | 🚧 | 🚧 | 🚧 | 🚧 |
| [Baichuan/Baichuan2](./llm/config/llama) | ✅ | ✅ | ✅ | ✅ | ✅ | 🚧 | ✅ | ✅ |
| [ChatGLM-6B](./llm/config/chatglm) | ❌ | ✅ | ✅ | ✅ | 🚧 | 🚧 | ✅ | ❌ |
| [ChatGLM2/ChatGLM3](./llm/config/chatglm2) | ❌ | ✅ | ✅ | ✅ | 🚧 | 🚧 | ✅ | ✅ |
| [Bloom](./llm/config/bloom) | ❌ | ✅ | ✅ | ✅ | 🚧 | 🚧 | ✅ | ✅ |
| [GPT-3](./llm/config/gpt-3) | ✅ | ✅ | 🚧 | 🚧 | 🚧 | 🚧 | 🚧 | ✅ |
| [OPT](./llm/config/opt) | 🚧 | ✅ | ✅ | 🚧 | 🚧 | 🚧 | 🚧 | ✅ |
| Model | Pretrain | SFT | LoRA | Prefix Tuning | DPO | RLHF | Quantization | Weight convert |
|---------------------------------------------|:--------:|:---:|:----:|:-------------:|:---:|:----:|:------------:|:--------------:|
| [LLaMA](./llm/config/llama) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| [Qwen](./llm/config/qwen) | ✅ | ✅ | ✅ | ✅ | ✅ | 🚧 | 🚧 | ✅ |
| [Mixtral](./llm/config/mixtral) | ✅ | ✅ | ✅ | ❌ | 🚧 | 🚧 | 🚧 | 🚧 |
| [Baichuan/Baichuan2](./llm/config/baichuan) | ✅ | ✅ | ✅ | ✅ | ✅ | 🚧 | ✅ | ✅ |
| [ChatGLM-6B](./llm/config/chatglm) | ❌ | ✅ | ✅ | ✅ | 🚧 | 🚧 | ✅ | ❌ |
| [ChatGLM2/ChatGLM3](./llm/config/chatglm2) | ❌ | ✅ | ✅ | ✅ | 🚧 | 🚧 | ✅ | ✅ |
| [Bloom](./llm/config/bloom) | ❌ | ✅ | ✅ | ✅ | 🚧 | 🚧 | ✅ | ✅ |
| [GPT-3](./llm/config/gpt-3) | ✅ | ✅ | 🚧 | 🚧 | 🚧 | 🚧 | 🚧 | ✅ |
| [OPT](./llm/config/opt) | 🚧 | ✅ | ✅ | 🚧 | 🚧 | 🚧 | 🚧 | ✅ |

* ✅: Supported
* 🚧: In Progress
* ❌: Not Supported

| 模型系列 | 模型参数 |
|:----------------------------------:|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [LLaMA](./llm/config/llama) | facebook/llama-7b, facebook/llama-13b, facebook/llama-30b, facebook/llama-65b |
| [LLama2](./llm/config/llama) | meta-llama/Llama-2-7b, meta-llama/Llama-2-7b-chat, meta-llama/Llama-2-13b, meta-llama/Llama-2-13b-chat, meta-llama/Llama-2-70b, meta-llama/Llama-2-70b-chat |
| [LLama3](./llm/config/llama) | meta-llama/Meta-Llama-3-8B, meta-llama/Meta-Llama-3-8B-Instruct, meta-llama/Meta-Llama-3-70B, meta-llama/Meta-Llama-3-70B-Instruct |
| [Baichuan](./llm/config/baichuan) | baichuan-inc/Baichuan-7B, baichuan-inc/Baichuan-13B-Base, baichuan-inc/Baichuan-13B-Chat |
| [Baichuan2](./llm/config/baichuan) | baichuan-inc/Baichuan2-7B-Base, baichuan-inc/Baichuan2-7B-Chat, baichuan-inc/Baichuan2-13B-Base, baichuan-inc/Baichuan2-13B-Chat |
| [Bloom](./llm/config/bloom) | bigscience/bloom-560m, bigscience/bloom-560m-bf16, bigscience/bloom-1b1, bigscience/bloom-3b, bigscience/bloom-7b1, bigscience/bloomz-560m, bigscience/bloomz-1b1, bigscience/bloomz-3b, bigscience/bloomz-7b1-mt, bigscience/bloomz-7b1-p3, bigscience/bloomz-7b1, bellegroup/belle-7b-2m |
| [ChatGLM](./llm/config/chatglm/) | THUDM/chatglm-6b, THUDM/chatglm-6b-v1.1 |
| [ChatGLM2](./llm/config/chatglm2) | THUDM/chatglm2-6b |
| [ChatGLM3](./llm/config/chatglm2) | THUDM/chatglm3-6b |
| [Gemma](./llm/config/gemma) | google/gemma-7b, google/gemma-7b-it, google/gemma-2b, google/gemma-2b-it |
| [Mistral](./llm/config/mistral) | mistralai/Mistral-7B-Instruct-v0.3, mistralai/Mistral-7B-v0.1 |
| [Mixtral](./llm/config/mixtral) | mistralai/Mixtral-8x7B-Instruct-v0.1 |
| [OPT](./llm/config/opt) | facebook/opt-125m, facebook/opt-350m, facebook/opt-1.3b, facebook/opt-2.7b, facebook/opt-6.7b, facebook/opt-13b, facebook/opt-30b, facebook/opt-66b, facebook/opt-iml-1.3b, opt-iml-max-1.3b |
| [Qwen](./llm/config/qwen/) | qwen/qwen-7b, qwen/qwen-7b-chat, qwen/qwen-14b, qwen/qwen-14b-chat, qwen/qwen-72b, qwen/qwen-72b-chat, |
| [Qwen1.5](./llm/config/qwen/) | Qwen/Qwen1.5-0.5B, Qwen/Qwen1.5-0.5B-Chat, Qwen/Qwen1.5-1.8B, Qwen/Qwen1.5-1.8B-Chat, Qwen/Qwen1.5-4B, Qwen/Qwen1.5-4B-Chat, Qwen/Qwen1.5-7B, Qwen/Qwen1.5-7B-Chat, Qwen/Qwen1.5-14B, Qwen/Qwen1.5-14B-Chat, Qwen/Qwen1.5-32B, Qwen/Qwen1.5-32B-Chat, Qwen/Qwen1.5-72B, Qwen/Qwen1.5-72B-Chat, Qwen/Qwen1.5-110B, Qwen/Qwen1.5-110B-Chat, Qwen/Qwen1.5-MoE-A2.7B, Qwen/Qwen1.5-MoE-A2.7B-Chat |
| [Qwen2](./llm/config/qwen/) | Qwen/Qwen2-0.5B, Qwen/Qwen2-0.5B-Instruct, Qwen/Qwen2-1.5B, Qwen/Qwen2-1.5B-Instruct, Qwen/Qwen2-7B, Qwen/Qwen2-7B-Instruct, Qwen/Qwen2-72B, Qwen/Qwen2-72B-Instruct, Qwen/Qwen2-57B-A14B, Qwen/Qwen2-57B-A14B-Instruct |

详细列表👉[模型参数支持](https://github.com/PaddlePaddle/PaddleNLP/issues/8663)

------------------------------------------------------------------------------------------
Expand Down
4 changes: 2 additions & 2 deletions README_en.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,11 +31,11 @@

## News 📢

* **2024.06.27 [PaddleNLP v3.0 Beta](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v3.0.0)**：Embrace large models and experience a complete upgrade. With a unified large model toolchain, we achieve full-process access to domestically produced computing chips. We fully support industrial-level application processes for large models, such as PaddlePaddle's 4D parallel configuration, efficient fine-tuning strategies, efficient alignment algorithms, and high-performance reasoning. Our developed RsLoRA+ algorithm, full checkpoint storage mechanism Unified Checkpoint, and generalized support for FastFNN and FusedQKV all contribute to the training and inference of large models. We continuously support updates to mainstream models for providing efficient solutions.
* **2024.06.27 [PaddleNLP v3.0 Beta](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v3.0.0-beta0)**：Embrace large models and experience a complete upgrade. With a unified large model toolchain, we achieve full-process access to domestically produced computing chips. We fully support industrial-level application processes for large models, such as PaddlePaddle's 4D parallel configuration, efficient fine-tuning strategies, efficient alignment algorithms, and high-performance reasoning. Our developed RsLoRA+ algorithm, full checkpoint storage mechanism Unified Checkpoint, and generalized support for FastFNN and FusedQKV all contribute to the training and inference of large models. We continuously support updates to mainstream models for providing efficient solutions.

* **2024.04.24 [PaddleNLP v2.8](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.8.0)**：Our self-developed RsLoRA+ algorithm with extreme convergence significantly improves the convergence speed and training effectiveness of PEFT training. By introducing high-performance generation acceleration into the RLHF PPO algorithm, we have broken through the generation speed bottleneck in PPO training, achieving a significant lead in PPO training performance. We generally support multiple large model training performance optimization methods such as FastFFN and FusedQKV, making large model training faster and more stable.

* **2024.01.04 [PaddleNLP v2.7](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.7.0)**: The LLM experience is fully upgraded, and the tool chain LLM entrance is unified. Unify the implementation code of pre-training, fine-tuning, compression, inference and deployment to the `PaddleNLP/llm` directory. The new [LLM Toolchain Documentation](https://paddlenlp.readthedocs.io/zh/latest/llm/finetune.html) provides one-stop guidance for users from getting started with LLM to business deployment and launch. The full breakpoint storage mechanism Unified Checkpoint greatly improves the versatility of LLM storage. Efficient fine-tuning upgrade supports the simultaneous use of efficient fine-tuning + LoRA, and supports QLoRA and other algorithms.
* **2024.01.04 [PaddleNLP v2.7](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.7.0)**: The LLM experience is fully upgraded, and the tool chain LLM entrance is unified. Unify the implementation code of pre-training, fine-tuning, compression, inference and deployment to the `PaddleNLP/llm` directory. The new [LLM Toolchain Documentation](https://paddlenlp.readthedocs.io/zh/latest/llm/pretraining/index.html) provides one-stop guidance for users from getting started with LLM to business deployment and launch. The full breakpoint storage mechanism Unified Checkpoint greatly improves the versatility of LLM storage. Efficient fine-tuning upgrade supports the simultaneous use of efficient fine-tuning + LoRA, and supports QLoRA and other algorithms.

* **2023.08.15 [PaddleNLP v2.6](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.6.0)**: Release [Full-process LLM toolchain](./llm) , covering all aspects of pre-training, fine-tuning, compression, inference and deployment, providing users with end-to-end LLM solutions and one-stop development experience; built-in [4D parallel distributed Trainer](./docs/trainer.md ), [Efficient fine-tuning algorithm LoRA/Prefix Tuning](./llm/README.md#2-%E7%B2%BE%E8%B0%83), [Self-developed INT8/INT4 quantization algorithm](./llm/README.md#4-%E9%87%8F%E5%8C%96), etc.; fully supports [LLaMA 1/2](./llm/config/llama), [BLOOM](./llm/config/bloom), [ChatGLM 1/2](./llm/config/chatglm), [OPT](./llm/config/opt) and other mainstream LLMs.

Expand Down
Loading