Helw150

from typing import List, Optional, Tuple, Union
from torchtyping import TensorType

from transformers.adapters.modeling import Adapter
from transformers.adapters import (
    BartAdapterModel,
    RobertaAdapterModel,
    BertAdapterModel,
    AdapterConfig,
)

Helw150

from transformers import AutoTokenizer, T5ForConditionalGeneration

# Model Init
n_gpu = 8
tokenizer = AutoTokenizer.from_pretrained("google/flan-ul2")
model = T5ForConditionalGeneration.from_pretrained("google/flan-ul2")
heads_per_gpu = len(model.encoder.block) // n_gpu 
device_map = {
    gpu: list(
        range(

Helw150

# See https://huggingface.co/docs/datasets/upload_dataset for more details

from datasets import load_dataset

dataset_name = "PUT_YOUR_NAME_HERE"
data_files = {"train": "train.csv", "dev": "dev.csv", "test": "test.csv"}
dataset = load_dataset("namespace/your_dataset_name", data_files=data_files)
datasets.push_to_hub(f"SALT-NLP/{dataset_name}", private=True)

Helw150

from gensim import utils

def save2gensim(fname, word2vec_dict):
  vectors = list(word2vec_dict.values())
  vector_size = vectors[0].shape[0]
  total_vec = len(vectors)
  with utils.smart_open(fname, 'wb') as fout:
    fout.write(utils.to_utf8("%s %s\n" % (total_vec, vector_size)))
    # store in sorted order: most frequent words at the top
    for word, vector in word2vec_dict.items():

Helw150

#!/usr/bin/env python
"""Counts the number of times a word occurs in a very large text file"""

from __future__ import print_function
import os
import sys
import argparse
import textacy
import multiprocessing
from tqdm import tqdm

Helw150

// Disable bold. 
term_.prefs_.set('enable-bold', false) 

// Use this for Zenburn
term_.prefs_.set('background-color', "#3F3F3F");
term_.prefs_.set('foreground-color', "#DCDCCC");

base03 =     "#002b36";
base02 =     "#073642";
base01 =     "#586e75";

Helw150

# i/p = array of numbers
# create a binary tree such that each subtree is a min-heap and the inorder traversal // of the binary tree is same as the array provided

# [5, 7, 10, 8, 1, 4]

#                       1
#                     /    \
#                   5        4
#                     \
#                       7

Helw150

# This function takes Open Graph info and just returns the articles
def returnArticles(og_array):
    article_urls = []
    for og in og_array:
        is_article = False
        for prop in og:
            if hasattr(prop, "property"):
                if prop["property"] == "og:type":
                    if prop["content"] == "article":
                        is_article = True

Helw150

import boto3

def get_id_from_name(name):
    description = [instance for r in response['Reservations'] for instance in r['Instances'] for tag in instance['Tags'] if tag['Key'] == 'Name' if tag['Value'] == name]
    return description['InstanceId']

def start_instance_by_name(name):
    ec2 = boto3.client('ec2')
    instance_id = get_id_from_name(name)
    # Do a dryrun first to verify permissions

Helw150

def brand_from_url(url):
  domain_list = urlparse(url).netloc.split('.')
  if(len(domain_list) < 3):
    brand= domain_list[0]
  else:
    brand = domain_list[1]
  return brand