asehmi

Pretty print tables summarizing properties of tensor arrays in numpy, pytorch, jax, etc.

asehmi

import os
import argparse
import requests
from urllib.parse import urlparse
from tqdm import tqdm
from joblib import Parallel, delayed
from tenacity import retry, stop_after_attempt, wait_fixed


@retry(stop=stop_after_attempt(5), wait=wait_fixed(2))

asehmi

#!/bin/bash

# pip install nougat-ocr
# see https://github.com/facebookresearch/nougat for details and license 

DEFAULT_BATCHSIZE=4

usage() {
    echo "Usage: $0 <path_to_directory> [--batchsize BATCHSIZE]"
    exit 1

asehmi

"""
hf_hub_download.py

This script allows you to download a snapshot repository from the Hugging Face Hub to a local directory without needing Git or loading the model.

Usage:
    python hf_hub_download.py <repo_id> [options]

Arguments:
    <repo_id>               Repository ID in the format "organization/repository".

asehmi

"""
Class for correcting text using a pretrained model grammar synthesis model.

-  models are available here: https://hf.co/models?other=grammar%20synthesis

requirements for this snippet:
pip install -U transformers accelerate

NOTE: if you want to use 9-bit to fit the model on a smaller GPU, you need bitsandbytes:
pip install -U transformers accelerate bitsandbytes

asehmi

import torch
import torch.nn.functional as F

from torch import Tensor
from transformers import AutoTokenizer, AutoModel
from pandas import DataFrame
from typing import List, Union
from tqdm.auto import tqdm, trange

asehmi

You:

I want you to act as a hypothetical python package generator and engineer. Create a python package called “remind”

ChatGPT:

As a text-based AI, I am unable to create actual Python packages or code files. However, I can help you design the structure of the package and provide you with code snippets that you can use to create the package yourself.

Package name: remind

Description: A Python package to create, manage, and schedule reminders for tasks and events.

asehmi

# -*- coding: utf-8 -*-
"""

caption_image.py - basic captioning example using lavis

usage: caption_image.py [-h] -i IMAGE_PATH [-m MODEL_TYPE] [-d DEVICE] [-v VERBOSE]
# lavis

https://github.com/salesforce/LAVIS
"""

asehmi

"""
define fn for extracting articles


Example usage:

url = 'https://www.businessinsider.com/hundreds-google-workers-walk-out-zurich-protest-over-layoffs-2023-3'
markdown = extract_article(url)
print(markdown)
"""

asehmi

"""

a script in Python that given a directory path as input, converts all images in the directory to PDF files. Several other argswitches are available for convenience.

"""
import argparse
import logging
import os
import pprint as pp
import sys