eusip

import inspect
import logging
import os
from pathlib import Path

import torch
from psutil import cpu_count
from transformers import T5Config, T5ForConditionalGeneration, T5Tokenizer
from transformers.generation_utils import GenerationMixin
from transformers.modeling_outputs import BaseModelOutputWithPast, Seq2SeqLMOutput

eusip

import time
import torch
import torch.nn.functional as F
from tqdm import trange

from transformers import AutoTokenizer
from onnxruntime import InferenceSession


class GenerativeT5(torch.nn.Module):

eusip

import transformers
import argparse
import numpy as np
import pandas as pd

from huggingface_hub import HfFolder

import evaluate
from datasets import load_dataset, Dataset, load_metric, concatenate_datasets, DatasetDict
from transformers import AutoModelForCausalLM, AutoTokenizer

eusip

activation functions
--------------------
commonly use: ReLU, Sigmoid (0 to 1), Tanh (-1 to 1)
- Sigmoid functions and their combinations generally work better in the case of classifiers
- Sigmoids and tanh functions are sometimes avoided due to the vanishing gradient problem
- ReLU function is a general activation function and is used in most cases these days
- If we encounter a case of dead neurons in our networks the leaky ReLU function is the best choice
- Always keep in mind that ReLU function should only be used in the hidden layers
- As a rule of thumb, you can begin with using ReLU function and then move over to other activation functions in case ReLU doesn’t provide with optimum results