nowfound

Life & fun · October 11, 2024

Byte-Pair Encoding tokenizer for training LLMs on large datasets

Byte-Pair Encoding tokenizer for training large language models on huge datasets - jmaczan/bpe-tokenizer

Byte-Pair Encoding tokenizer for training LLMs on large datasets launched on October 11, 2024 with 5 votes, #1,922 of 5,185 launches that month and more than 50% of that year's launches. The site was still online in September 2026, 2 years on.

What it does

from bpe_tokenizer import BPETokenizer BPETokenizer (). train ( dataset_path = "./path/to/dataset.txt" ) CLI python bpe_tokenizer.py train --training_dataset path_to_your_dataset.txt --vocabulary_size 5000 --training_output path_to_output_tokenizer.json defaults: from bpe_tokenizer import BPETokenizer BPETokenizer (). tokenize ( text_to_be_tokenized ) CLI python bpe_tokenizer.py tokenize --tokenizer_data path_to_tokenizer_data.json --run_data tokenize.json defaults: { "data" : " Study hard what interests you the most in the most undisciplined, irreverent and original manner possible - Richard Feynmann " } Detokenize from bpe_tokenizer import BPETokenizer BPETokenizer (). detokenize (…from github.com

Does a similar job

all alternatives →
  • Wordllama – Things you can do with the token embeddings of an LLM2024 · github.com · ▲370

    After working with LLMs for long enough, I found myself wanting a lightweight utility for doing various small tasks to prepare inputs, locate information and create evaluators. This library is two things: a very simple model and utilities that inference it (eg. fuzzy deduplication). The target platform is CPU, and it’s intended to be light, fast and pip installable — a library that lowers the barrier to working with strings semantically. You don’t need to install pytorch to use it, or any deep learning runtimes. How can this be accomplished? The model is simply token embeddings that are…

  • Explore large language models with 512MB of RAM2023 · github.com · ▲138

    Explore large language models in 512MB of RAM. Contribute to jncraton/languagemodels development by creating an account on GitHub.

  • HuggingFace – Fast tokenization library for deep-learning NLP pipelines2020 · github.com · ▲168

    💥 Fast State-of-the-Art Tokenizers optimized for Research and Production - huggingface/tokenizers

  • Fine-grained stylistic control of LLMs using model arithmetic2023 · github.com · ▲85

    We developed a new framework that enables flexible control of generated text in language models. By combining several models and/or system prompts in one mathematical formula, it lets you tweak your style and combine model outputs with ease. A handy tool for those working with LLMs, looking for more fine-grained control of stylistic output. More details in our paper: https://arxiv.org/abs/2311.14479. Feedback and potential applications are welcome.

  • PT
  • Fully client-side GPT2 prediction visualizer2023 · perplexity.vercel.app · ▲153

    Hi HN! I've found this visualization tool immensely helpful over the years for getting an intuition for how an LLM "sees" some piece of text, and with a bit of elbow grease decided to move all compute to client side so I could make it publicly available. I've found it particularly useful for - Understanding exactly how repetition and patterns affect a small LM's ability to predict correctly - Understanding different tokenization patterns and how it affects model output - Getting a general sense of how "hard" different prediction tasks are for GPT-style models Known problems (that I probably…

More life & fun this month

the category →

Source: Show HN post ↗

Launched alongside, October 2024

the whole month →
  • buzzabout▲1,267

    Audience insights from 1B+ online discussions in 2 mins

    AI · 2024 · buzzabout.ai

  • bolt.new▲1,230

    Build and scale high-performing websites & apps using your words. Join millions and start building today.

    AI · 2024 · bolt.new

  • Feta▲1,217

    Run smarter stand-ups, build better products

    AI · 2024 · feta.io

  • Trag▲955

    AI code review companion

    AI · 2024 · usetrag.com

  • Turn Notion databases into portals & apps with no code

    Dev tools · 2024 · softr.io

  • One inbox for all your work discussions

    Work · 2024 · generalcollaboration.com