Dr.Q quinsulon
aditya-malte
/ smallberta_pretraining.ipynb
Created
February 22, 2020 13:41
smallBERTa_Pretraining.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
jinglescode
/ transformer-pytorch.py
Last active
June 7, 2020 06:53
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import math | |
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| from torch.nn import TransformerEncoder, TransformerEncoderLayer | |
| class TransformerModel(nn.Module): | |
| def __init__(self, ntoken, ninp, nhead, nhid, nlayers, dropout=0.5): |
thomwolf
/ loading_wikipedia.py
Last active
January 12, 2025 13:34
Load full English Wikipedia dataset in HuggingFace nlp library
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import os; import psutil; import timeit | |
| from datasets import load_dataset | |
| mem_before = psutil.Process(os.getpid()).memory_info().rss >> 20 | |
| wiki = load_dataset("wikipedia", "20200501.en", split='train') | |
| mem_after = psutil.Process(os.getpid()).memory_info().rss >> 20 | |
| print(f"RAM memory used: {(mem_after - mem_before)} MB") | |
| s = """batch_size = 1000 | |
| for i in range(0, len(wiki), batch_size): |
OlderNewer