OpenChatKit 环境搭建

事先安装过 cuda 11.8  cudnn 8.6 和 TensorRT 

安装miniconda

下载源代码：

$ git clone --recursive https://github.com/togethercomputer/OpenChatKit.git

安装miniconda： 

$ wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh

$ sh ./Miniconda3-latest-Linux-x86_64.sh

$ /home/mklguy/miniconda3/bin/conda init

mklguy@mklguy--PC:~/ex/OpenChatKit$ /home/mklguy/miniconda3/bin/conda env create -f environment.yml

在V-P-N的挟持下，创建成功：

在~/.bashrc中会出现这么一段，导致每次进入系统后，会先进入conda环境：

# >>> conda initialize >>>
# !! Contents within this block are managed by 'conda init' !!
__conda_setup="$('/home/mklguy/miniconda3/bin/conda' 'shell.bash' 'hook' 2> /dev/null)"
if [ $? -eq 0 ]; then
    eval "$__conda_setup"
else
    if [ -f "/home/mklguy/miniconda3/etc/profile.d/conda.sh" ]; then
        . "/home/mklguy/miniconda3/etc/profile.d/conda.sh"
    else
        export PATH="/home/mklguy/miniconda3/bin:$PATH"
    fi
fi
unset __conda_setup
# <<< conda initialize <<<

备份文件后删掉这段试试。

$ source .bashrc

也可以使用 pip3再安装整个系统可用的 pytorch：

$ pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu118

用经典案例做一个测试：

from __future__ import print_function

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.optim.lr_scheduler import StepLR
import argparse

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.dropout1 = nn.Dropout(0.25)
        self.dropout2 = nn.Dropout(0.5)
        self.fc1 = nn.Linear(9216, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = F.relu(x)
        x = F.max_pool2d(x, 2)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = F.log_softmax(x, dim=1)
        return output


def train(args, model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))
            if args.dry_run:
                break


def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item()  # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True)  # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)

    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))


def main():
    # Training settings
    parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
    parser.add_argument('--batch-size', type=int, default=64, metavar='N',
                        help='input batch size for training (default: 64)')
    parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
                        help='input batch size for testing (default: 1000)')
    parser.add_argument('--epochs', type=int, default=14, metavar='N',
                        help='number of epochs to train (default: 14)')
    parser.add_argument('--lr', type=float, default=1.0, metavar='LR',
                        help='learning rate (default: 1.0)')
    parser.add_argument('--gamma', type=float, default=0.7, metavar='M',
                        help='Learning rate step gamma (default: 0.7)')
    parser.add_argument('--no-cuda', action='store_true', default=False,
                        help='disables CUDA training')
    parser.add_argument('--dry-run', action='store_true', default=False,
                        help='quickly check a single pass')
    parser.add_argument('--seed', type=int, default=1, metavar='S',
                        help='random seed (default: 1)')
    parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                        help='how many batches to wait before logging training status')
    parser.add_argument('--save-model', action='store_true', default=False,
                        help='For Saving the current Model')
    args = parser.parse_args()
    use_cuda = not args.no_cuda and torch.cuda.is_available()

    torch.manual_seed(args.seed)

    device = torch.device("cuda" if use_cuda else "cpu")

    train_kwargs = {'batch_size': args.batch_size}
    test_kwargs = {'batch_size': args.test_batch_size}
    if use_cuda:
        cuda_kwargs = {'num_workers': 1,
                       'pin_memory': True,
                       'shuffle': True}
        train_kwargs.update(cuda_kwargs)
        test_kwargs.update(cuda_kwargs)

    transform=transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.1307,), (0.3081,))
        ])
    dataset1 = datasets.MNIST('../data', train=True, download=True,
                       transform=transform)
    dataset2 = datasets.MNIST('../data', train=False,
                       transform=transform)
    train_loader = torch.utils.data.DataLoader(dataset1,**train_kwargs)
    test_loader = torch.utils.data.DataLoader(dataset2, **test_kwargs)

    model = Net().to(device)
    optimizer = optim.Adadelta(model.parameters(), lr=args.lr)

    scheduler = StepLR(optimizer, step_size=1, gamma=args.gamma)
    for epoch in range(1, args.epochs + 1):
        train(args, model, device, train_loader, optimizer, epoch)
        test(model, device, test_loader)
        scheduler.step()

    if args.save_model:
        torch.save(model.state_dict(), "mnist_cnn.pt")


if __name__ == '__main__':
    main()

$ python3 hello_mnist.py

99%

安装git 的lfs，

$ git lfs install

遇到git版本低的问题，最终如下解决：

$ sudo apt-get autoremove git

##:: /bin/sh: msgfmt: command not found
$ sudo apt-get install gettext

##:: /bin/sh: 1: asciidoc: not found
$ sudo apt-get install asciidoc

##:: /bin/sh: 1: docbook2x-texi: not found
$ sudo apt-get install docbook2X


$ sudo apt-get install   texinfo perl openjade dh-autoreconf autoconf libcurl4-gnutls-dev libexpat1-dev gettext zlib1g-dev libssl-dev asciidoc xmlto docbook2x

$ wget https://www.kernel.org/pub/software/scm/git/git-2.40.0.tar.gz

        $ make prefix=/usr all doc info ;# as yourself
        # make prefix=/usr install install-doc install-html install-info ;# as root

$ wget https://github.com/git-lfs/git-lfs/releases/download/v3.3.0/git-lfs-linux-amd64-v3.3.0.tar.gz
$ sudo ./install.sh

##:: OK了

安装 huggingface的 transformers：

$ pip3 install transformers

下载参数数据并测试：

from transformers import pipeline
pipe = pipeline(model='togethercomputer/GPT-NeoXT-Chat-Base-20B')
pipe('''<human>: Hello!\n<bot>:''')

上面第二句的执行是这样的：第一波至少下载接近50GB的参数：