diff --git a/README.md b/README.md index 7ba2b748..3ddf848c 100644 --- a/README.md +++ b/README.md @@ -17,12 +17,37 @@ Preview LLaMA Board at **[🤗 Spaces](https://huggingface.co/spaces/hiyouga/LLaMA-Board)**. -Launch LLaMA Board via `CUDA_VISIBLE_DEVICES=0 python src/train_web.py`. (multiple GPUs are not supported yet) +Launch LLaMA Board via `CUDA_VISIBLE_DEVICES=0 python src/train_web.py`. (multiple GPUs are not supported yet in this mode) Here is an example of altering the self-cognition of an instruction-tuned language model within 10 minutes on a single GPU. https://github.com/hiyouga/LLaMA-Factory/assets/16256802/6ba60acc-e2e2-4bec-b846-2d88920d5ba1 +## Table of Contents + +- [Benchmark](#benchmark) +- [Changelog](#changelog) +- [Supported Models](#supported-models) +- [Supported Training Approaches](#supported-training-approaches) +- [Provided Datasets](#provided-datasets) +- [Requirement](#requirement) +- [Getting Started](#getting-started) +- [Projects using LLaMA Factory](#projects-using-llama-factory) +- [License](#license) +- [Citation](#citation) +- [Acknowledgement](#acknowledgement) + +## Benchmark + +Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ptuning), LLaMA-Factory's LoRA tuning offers up to **3.7 times faster** training speed with a better BLEU score on the advertising text generation task. By leveraging 4-bit quantization technique, LLaMA-Factory's QLoRA further improves the efficiency regarding the GPU memory. + +![benchmark](assets/benchmark.svg) + +- Training Speed: the number of training samples processed per second during the training. (bs=4, cutoff_len=1024) +- BLEU Score: BLEU-4 score on the development set of the [advertising text generation](https://aclanthology.org/D19-1321.pdf) task. (bs=4, cutoff_len=1024) +- GPU Memory: Peak GPU memory usage in the 4-bit quantized training. (bs=1, cutoff_len=1024) +- We adopt `pre_seq_len=128` for ChatGLM's P-Tuning and `lora_rank=32` for LLaMA-Factory's LoRA tuning. + ## Changelog [23/10/21] We supported **[NEFTune](https://arxiv.org/abs/2310.05914)** trick for fine-tuning. Try `--neft_alpha` argument to activate NEFTune, e.g., `--neft_alpha 5`. @@ -477,6 +502,9 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ - **[Sunsimiao](https://github.com/thomas-yanxin/Sunsimiao)**: A large language model specialized in Chinese medical domain, based on Baichuan-7B and ChatGLM-6B. - **[CareGPT](https://github.com/WangRongsheng/CareGPT)**: A series of large language models for Chinese medical domain, based on LLaMA2-7B and Baichuan-13B. +> [!NOTE] +> If you have a project that should be incorporated, please contact via email or create a pull request. + ## License This repository is licensed under the [Apache-2.0 License](LICENSE). diff --git a/README_zh.md b/README_zh.md index dbcee80a..2b1f5905 100644 --- a/README_zh.md +++ b/README_zh.md @@ -23,6 +23,31 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/6ba60acc-e2e2-4bec-b846-2d88920d5ba1 +## 目录 + +- [性能指标](#性能指标) +- [更新日志](#更新日志) +- [模型](#模型) +- [训练方法](#训练方法) +- [数据集](#数据集) +- [软件依赖](#软件依赖) +- [如何使用](#如何使用) +- [使用了 LLaMA Factory 的项目](#使用了-llama-factory-的项目) +- [协议](#协议) +- [引用](#引用) +- [致谢](#致谢) + +## 性能指标 + +与 ChatGLM 官方的 [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ptuning) 微调相比，LLaMA-Factory 的 LoRA 微调提供了 **3.7 倍**的加速比，同时在广告文案生成任务上取得了更高的 BLEU 分数。结合 4 比特量化技术，LLaMA-Factory 的 QLoRA 微调进一步降低了 GPU 显存消耗。 + +![benchmark](assets/benchmark.svg) + +- Training Speed: 训练阶段每秒处理的样本数量。（批处理大小=4，截断长度=1024） +- BLEU Score: [广告文案生成](https://aclanthology.org/D19-1321.pdf)任务验证集上的 BLEU-4 分数。（批处理大小=4，截断长度=1024） +- GPU Memory: 4 比特量化训练的 GPU 显存峰值。（批处理大小=1，截断长度=1024） +- 我们在 ChatGLM 的 P-Tuning 中采用 `pre_seq_len=128`，在 LLaMA-Factory 的 LoRA 微调中采用 `lora_rank=32`。 + ## 更新日志 [23/10/21] 我们支持了 **[NEFTune](https://arxiv.org/abs/2310.05914)** 训练技巧。请使用 `--neft_alpha` 参数启用 NEFTune，例如 `--neft_alpha 5`。 @@ -476,6 +501,9 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ - **[Sunsimiao](https://github.com/thomas-yanxin/Sunsimiao)**: 孙思邈中文医疗大模型 Sumsimiao，基于 Baichuan-7B 和 ChatGLM-6B 在中文医疗数据上微调而得。 - **[CareGPT](https://github.com/WangRongsheng/CareGPT)**: 医疗大模型项目 CareGPT，基于 LLaMA2-7B 和 Baichuan-13B 在中文医疗数据上微调而得。 +> [!NOTE] +> 如果您有项目希望添加至上述列表，请通过邮件联系或者创建一个 PR。 + ## 协议 本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源。 diff --git a/assets/benchmark.svg b/assets/benchmark.svg new file mode 100644 index 00000000..0bf8f9f4 --- /dev/null +++ b/assets/benchmark.svg @@ -0,0 +1,1172 @@ + + + + + + + + 2023-11-18T09:17:37.531653 + image/svg+xml + + + Matplotlib v3.7.1, https://matplotlib.org/ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +