From 090b0d28627a2da2a326942a0f1dad69869c93b1 Mon Sep 17 00:00:00 2001 From: gongjy <2474590974@qq.com> Date: Sat, 5 Oct 2024 10:52:13 +0800 Subject: [PATCH] update readme --- README.md | 21 ++++++++++++++------- README_en.md | 21 ++++++++++++++------- 2 files changed, 28 insertions(+), 14 deletions(-) diff --git a/README.md b/README.md index 677273b..57ea5f6 100644 --- a/README.md +++ b/README.md @@ -133,22 +133,29 @@ CPU: Intel(R) Core(TM) i9-10980XE CPU @ 3.00GHz ```bash pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple ``` + * 1.克隆项目代码 ```text git clone https://github.com/jingyaogong/minimind-v ``` -* 2.如果需要自己训练 - * 2.1 下载数据集 ([百度网盘](https://pan.baidu.com/s/1Nz36OBBvVBGEx-PwIb7ofg?pwd=6666) or [HuggingFace](https://hf-mirror.com/datasets/jingyaogong/minimind-v_dataset))文件到`./dataset` +* 2.下载 `clip-vit-base-patch32` 模型，放到 `./model/clip_model` 目录下： + ```bash + cd ./model/clip_model & git clone https://hf-mirror.com/openai/clip-vit-base-patch32 + ``` + +* 3.如果需要自己训练 + + * 3.1 下载数据集 ([百度网盘](https://pan.baidu.com/s/1Nz36OBBvVBGEx-PwIb7ofg?pwd=6666) or [HuggingFace](https://hf-mirror.com/datasets/jingyaogong/minimind-v_dataset))文件到`./dataset` 目录下，并解压`pretrain_images.zip` 和 `sft_images.zip` - * 2.2 在`./model/LMConfig.py` 中调整model的参数配置 + * 3.2 在`./model/LMConfig.py` 中调整model的参数配置 > 这里仅需调整dim和n_layers参数，分别是`(512+8)`或`(768+16)`，对应于`minimind-v-v1-small`和`minimind-v-v1` - * 2.3 下载MiniMind语言模型的[预训练权重文件](https://pan.baidu.com/s/1LE1SPoPYGS7VNtT1tpf7DA?pwd=6666) + * 3.3 下载MiniMind语言模型的[预训练权重文件](https://pan.baidu.com/s/1LE1SPoPYGS7VNtT1tpf7DA?pwd=6666) ，放到到`./out/`目录下，命名为`*_llm.pth` - * 2.4 `python 1-pretrain_vlm.py` 执行预训练，得到 `*_vlm_pretrain.pth` 作为预训练的输出权重 - * 2.5 `python 2-sft_vlm.py` 执行指令微调，得到 `*_vlm_sft.pth` 作为指令微调的输出权重 + * 3.4 `python 1-pretrain_vlm.py` 执行预训练，得到 `*_vlm_pretrain.pth` 作为预训练的输出权重 + * 3.5 `python 2-sft_vlm.py` 执行指令微调，得到 `*_vlm_sft.pth` 作为指令微调的输出权重 -* 3.测试自己训练的模型推理效果 +* 4.测试自己训练的模型推理效果 * 确保需要使用的，训练完成的参数权重`*.pth`文件位于`./out/`目录下 * 也可以直接去[训练完成的模型权重](https://pan.baidu.com/s/1LE1SPoPYGS7VNtT1tpf7DA?pwd=6666) 下载使用我训练好的`*.pth`权重文件 diff --git a/README_en.md b/README_en.md index b8fe32f..ac2024a 100644 --- a/README_en.md +++ b/README_en.md @@ -131,20 +131,27 @@ Environment: python 3.9 + Torch 2.1.2 + DDP single-machine multi-GPU training ```bash pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple ``` + * 1. Clone the project code ```text git clone https://github.com/jingyaogong/minimind-v ``` -* 2. If you want to train it yourself - * 2.1 Download all contents of the dataset ([Baidu Netdisk](https://pan.baidu.com/s/1Nz36OBBvVBGEx-PwIb7ofg?pwd=6666) or [HuggingFace](https://hf-mirror.com/datasets/jingyaogong/minimind-v_dataset)) to the `./dataset` directory, and unzip `pretrain_images.zip` and `sft_images.zip` - * 2.2 Adjust the model parameters in `./model/LMConfig.py` +* 2. Download the `clip-vit-base-patch32` model and place it in the `./model/clip_model` directory: + ```bash + cd ./model/clip_model & git clone https://hf-mirror.com/openai/clip-vit-base-patch32 + ``` + +* 3. If you want to train it yourself + + * 3.1 Download all contents of the dataset ([Baidu Netdisk](https://pan.baidu.com/s/1Nz36OBBvVBGEx-PwIb7ofg?pwd=6666) or [HuggingFace](https://hf-mirror.com/datasets/jingyaogong/minimind-v_dataset)) to the `./dataset` directory, and unzip `pretrain_images.zip` and `sft_images.zip` + * 3.2 Adjust the model parameters in `./model/LMConfig.py` > Only need to adjust the dim and n_layers parameters, which are `(512+8)` or `(768+16)`, corresponding to `minimind-v-v1-small` and `minimind-v-v1` - * 2.3 Download the [pre-trained weight file](https://pan.baidu.com/s/1LE1SPoPYGS7VNtT1tpf7DA?pwd=6666) of the MiniMind language model and place it in the `./out/` directory, named `*_llm.pth` - * 2.4 Execute `python 1-pretrain_vlm.py` for pre-training, obtaining `*_vlm_pretrain.pth` as the output weights - * 2.5 Execute `python 2-sft_vlm.py` for instruction fine-tuning, obtaining `*_vlm_sft.pth` as the output weights for fine-tuning + * 3.3 Download the [pre-trained weight file](https://pan.baidu.com/s/1LE1SPoPYGS7VNtT1tpf7DA?pwd=6666) of the MiniMind language model and place it in the `./out/` directory, named `*_llm.pth` + * 3.4 Execute `python 1-pretrain_vlm.py` for pre-training, obtaining `*_vlm_pretrain.pth` as the output weights + * 3.5 Execute `python 2-sft_vlm.py` for instruction fine-tuning, obtaining `*_vlm_sft.pth` as the output weights for fine-tuning -* 3. Test the inference effect of the self-trained model +* 4. Test the inference effect of the self-trained model * Ensure that the used, completed training parameter weights `*.pth` files are located in the `./out/` directory * You can also directly download the [completed model weight files](https://pan.baidu.com/s/1LE1SPoPYGS7VNtT1tpf7DA?pwd=6666) and use the `*.pth` weight files I have trained ```text