๐Ÿ† #2,449 overall#94 of 148 in Tokenization & Preprocessing

cohere-ai /magikarp

Code for the paper "Fishing for Magikarp"

$ git clone https://github.com/cohere-ai/magikarp.git
GitHub social preview for cohere-ai/magikarp
Stars
191
191
Forks
18
18
Language
Python
License
Apache-2.0
Created
Apr 29, 2024
2.4 years old
Last push
Jul 10, 2026

Categories

GitHub topics

More in Tokenization & Preprocessing

Tokenization & Preprocessing

AgentOps-AI/tokencost

Easy token price estimates for 400+ LLMs. TokenOps.

๐Ÿค– Language Models
PythonMITupdated Sep 5, 2025
GitHub โ†—โ˜… 2Kโ‘‚ 106
Tokenization & Preprocessing

FoundationVision/UniTok

[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding

๐Ÿค– Language Models
PythonMITupdated Nov 14, 2025
GitHub โ†—โ˜… 533โ‘‚ 14
Tokenization & Preprocessing

analyticalrohit/llms-from-scratch

Build a ChatGPT like LLM from scratch in PyTorch, explained step by step.

๐Ÿค– Language Models
Jupyter NotebookMITupdated Jun 8, 2026
GitHub โ†—โ˜… 383โ‘‚ 87
Tokenization & Preprocessing

bminixhofer/zett

Code for Zero-Shot Tokenizer Transfer

๐Ÿค– Language Models
Pythonno licenseupdated Jan 14, 2025
GitHub โ†—โ˜… 147โ‘‚ 11
Tokenization & Preprocessing

toon-format/toon

๐ŸŽ’ Token-Oriented Object Notation (TOON) โ€“ compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.

TypeScriptMITupdated Sep 3, 2026
GitHub โ†—โ˜… 25.4Kโ‘‚ 1.1K
Tokenization & Preprocessing

marcelroed/gigatoken

Language model tokenization at GB/s

๐Ÿง  Natural Language Processing
RustMITupdated Sep 2, 2026
GitHub โ†—โ˜… 4.1Kโ‘‚ 220

Data from GitHub ยท snapshot Sep 24, 2026