AIGym Custom Tokenizer (CL200K)

Overview

The AIGym CL200K Tokenizer is a custom tokenizer designed for pretraining large language models. It is based on Meta-Llama-3-8B and trained on the AIGym Pretraining Corpus.

Features

  • Built on Meta-Llama-3-8B
  • Supports a vocabulary size of 200K tokens
  • Optimized for educational, programming, multilingual, and mathematical texts
  • Includes custom PAD token

Usage

Loading the Tokenizer

To use the tokenizer:

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("AIGym/cl200k")
text = "Hello, world!"
tokens = tokenizer.encode(text)
print(tokens)
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.