A pure JavaScript implementation of a BPE tokenizer (Encoder/Decoder) for GPT-2 / GPT-3 / GPT-4 and other OpenAI models
Javascript BPE Encoder Decoder for GPT-2 / GPT-3. The "gpt-3-encoder" module provides functions for encoding and decoding text using the Byte Pair Encoding (BPE) algorithm. It can be used to process text data for input into machine learning models, or to
Javascript BPE Encoder Decoder for GPT-2 / GPT-3. The "gpt-3-encoder" module provides functions for encoding and decoding text using the Byte Pair Encoding (BPE) algorithm. It can be used to process text data for input into machine learning models, or to
Estimate and count tokens (incl. exact OpenAI BPE) and input costs for LLM API calls
TypeScript/JavaScript bindings for LOOM neural network framework with WebAssembly support - GPU-accelerated machine learning in the browser