abodacs

abodacs

Install FreeBSD 14.0 on Hetzner server

Hetzner no longer offers direct install of FreeBSD, but we can do it ourselves. Here is how :)

Boot the hetzner server in Hetnzer Debain based rescue mode. ssh into it. then:

wget https://mfsbsd.vx.sk/files/iso/14/amd64/mfsbsd-14.0-RELEASE-amd64.iso

qemu-system-x86_64 \

abodacs

// Updated: Aug. 15, 2024
// Run: node testRegex.js testText.txt
// Used in https://jina.ai/tokenizer
const fs = require('fs');
const util = require('util');

// Define variables for magic numbers
const MAX_HEADING_LENGTH = 7;
const MAX_HEADING_CONTENT_LENGTH = 200;
const MAX_HEADING_UNDERLINE_LENGTH = 200;

abodacs

import regex as re
import requests

MAX_HEADING_LENGTH = 7
MAX_HEADING_CONTENT_LENGTH = 200
MAX_HEADING_UNDERLINE_LENGTH = 200
MAX_HTML_HEADING_ATTRIBUTES_LENGTH = 100
MAX_LIST_ITEM_LENGTH = 200
MAX_NESTED_LIST_ITEMS = 6
MAX_LIST_INDENT_SPACES = 7

abodacs

# REQUIRES torchao, torch nightly (or torch 2.5) and transformers

from transformers import AutoTokenizer, AutoModelForCausalLM, TorchAoConfig
from transformers import TextStreamer
import torch
from tqdm import tqdm
import os
os.environ["TOKENIZERS_PARALLELISM"] = "false"  # To prevent long warnings :)

torch.set_float32_matmul_precision('high')

abodacs

var $debugHelper = $debugHelper || {};
$debugHelper = function () {
    var href = "lib/debugger.css";
    var addCss = function () {
        if (styleStyleIsLoaded(href) === true) {
            return;
        }
        const head = document.head;
        const link = document.createElement("link");
        link.type = "text/css";

abodacs

require("dotenv").config();
const H = require("highland");
const axios = require("axios");
const fs = require("fs").promises;

const exportDirectory = "./export";
const apiUrl = "https://api.intercom.io";

// config axios for the authorized API request
const apiClient = axios.create({

abodacs

import torch
from diffusers import FluxPipeline
from torch import nn


class ModelOffloaderV2:
    def __init__(self, model: nn.Module, record_stream: bool = False):
        # move model to pinned memory. keep a model copy in CPU pinned memory.
        for p in model.parameters():
            p.data = p.data.cpu().pin_memory()

abodacs

# Train GPT-2 in five minutes -- for free
#
# ```bash
# pip install modal
# modal setup
# modal run wrapper.py
# ```
#
# Note that the end-to-end latency the first time is more like 25 minutes:
# - five minutes to install Torch (rip)

abodacs

import multiprocessing

manager = multiprocessing.Manager()
all_hashes_set = manager.dict()
def deduplicate(examples, all_hashes_set):
    print(len(all_hashes_set))
    input_ids = examples['input_ids']
    hashes = [
        hash(tuple(input_ids[i]))
        for i in range(len(input_ids))