visualDust

Download and convert llama-7b model to huggingface format

This is a refined version of huggingface/LLaMA2 Usage tips.

Go to somewhere you want to put the original llama2 7b model weights, maybe in the download folder. Create a folder called LLaMA:

cd ~/downloads (or maybe somewhere else)
mkdir LLaMA
cd LLaMA

visualDust

import time
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision.datasets as datasets
import neetbox
from torchvision import transforms
from torch.utils.data import DataLoader
from neetbox import logger

visualDust

def one_hot_encode(
    mask: torch.Tensor,
    num_classes: int,
    ignored_label: Union[str, int] = "negative",
):
    """Convert the mask to a one-hot encoded representation by @visualDust

    Args:
        mask (torch.Tensor): indexed label image. Should types int
        num_classes (int): number of classes

visualDust

Other      10 hrs 40 mins █████████▊░░░░░░░░░░░  47.0%
Fish To... 3 hrs 26 mins  ███▏░░░░░░░░░░░░░░░░░  15.1%
Markdown   2 hrs 20 mins  ██▏░░░░░░░░░░░░░░░░░░  10.3%
Browsing   1 hr 36 mins   █▍░░░░░░░░░░░░░░░░░░░   7.1%
Searching  1 hr 23 mins   █▎░░░░░░░░░░░░░░░░░░░   6.1%

visualDust

visualDust

visualDust