pszemraj

import os

import numpy as np

from datasets import ClassLabel, Dataset, DatasetDict


def split_dataset(
    dataset: Dataset,
    test_size=0.025,

pszemraj

import logging

import torch


def configure_tf32():
    """
    Enable TF32 precision for GPUs with compute capability >= 8.0 (Ampere+).
    """
    if not torch.cuda.is_available():

pszemraj

import argparse
import logging
import time
from datetime import datetime
from pathlib import Path
from typing import Optional

from huggingface_hub import upload_folder
from watchdog.events import PatternMatchingEventHandler
from watchdog.observers import Observer

pszemraj

import re
from itertools import chain


def calculate_readability(code_string:str) -> float:
    code = code_string.splitlines()

    # Heuristic 1: Line length
    max_line_length = 80
    long_lines = sum(1 for line in code if len(line) > max_line_length)

pszemraj

"""
generic & basic sbert-like embedder class for the  jina-bert model

Usage:

model = EmbeddingModel("jinaai/jina-embeddings-v2-base-en")
embeddings = model.encode(
        ["How is the weather today?", "What is the current weather like today?"]
    )
print(model.cos_sim(embeddings[0], embeddings[1]))

pszemraj

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))

pszemraj

import logging
import gzip
from pathlib import Path
import fire
from tqdm import tqdm
from tokenizers import (
    Tokenizer,
    decoders,
    models,
    normalizers,

pszemraj

#!/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

mlabonne

# Example usage:
# python merge_peft.py --base_model=meta-llama/Llama-2-7b-hf --peft_model=./qlora-out --hub_id=alpaca-qlora

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

import argparse

def get_args():

xenova