Open-source alternatives to Tiktoken

Fairseq is a PyTorch toolkit for sequence-to-sequence modeling, specializing in neural machine translation, automatic speech recognition, and large-scale language model training. It provides a framework for processing and aligning diverse data sources, including text, audio, and video, to support tasks such as speech-to-text conversion and multimodal sequence learning. The project is distinguished by its distributed training capabilities, which utilize parameter sharding, mixed-precision training, and CPU offloading to handle models that exceed single-device memory. It also includes specializ

SentencePiece is a text segmentation engine and tokenization library designed for machine learning workflows. It provides a comprehensive toolkit for transforming raw text into subword units or numerical identifiers, enabling consistent data representation for neural network training and inference. The library supports the training of segmentation models from raw text, allowing for the creation of custom vocabularies tailored to specific domain requirements. The project distinguishes itself through its byte-level encoding and fallback mechanisms, which ensure that every input can be represent

OpenVINO is an AI inference engine and model serving platform designed to execute optimized deep learning models across CPUs, GPUs, and NPUs through a unified API. It includes a model optimization toolkit for converting, quantizing, and compressing models from various frameworks, alongside a specialized generative AI runtime for large language models. The project distinguishes itself through a plugin-based hardware acceleration layer that maps neural network operations to vendor-specific drivers. It features advanced execution mechanisms such as continuous batching, speculative decoding, and

This repository is a comprehensive educational program and deep learning framework designed to teach practical deep learning using PyTorch through notebooks and code examples. It serves as a high-level library for building, training, and deploying neural networks, acting as a model training orchestrator that coordinates PyTorch models, optimizers, and loss functions. The project provides specialized toolkits for computer vision, natural language processing, and tabular data preprocessing. It distinguishes itself through advanced training controls such as discriminative learning rates, a two-w

Compromise is a natural language processing library and rule-based text parser designed to analyze unstructured text. It functions as a toolkit for identifying parts of speech, linguistic patterns, and semantic meaning, while providing specialized engines for named entity recognition and the parsing of temporal and numeric data. The project is distinguished by its linguistic morphological engine, which can conjugate verbs across different tenses and inflect nouns and adjectives. It further allows for linguistic model customization through a plugin system that enables the extension of lexicons

Compromise is a natural language processing library and rule-based engine designed for English text manipulation, analysis, and parsing. It provides a toolkit for tokenizing text, identifying parts of speech, and performing linguistic analysis to achieve semantic understanding of unstructured strings. The project distinguishes itself through its ability to programmatically transform grammar, such as modifying verb tenses, noun plurality, and adjective forms. It also functions as a named entity recognizer capable of extracting people, places, organizations, dates, and contact information from

Smile is a comprehensive JVM machine learning library and statistical computing toolkit. It provides a suite of algorithms for classification, regression, and clustering, implemented natively for Java, Scala, and Kotlin. The project also functions as a deep learning framework, a natural language processing library, and an inference engine for large language models. The library distinguishes itself through GPU acceleration via LibTorch bindings and support for the ONNX model interchange format. It includes specialized capabilities for large language model inference, featuring Byte-Pair Encodin

gpt-neox is a distributed training system and framework for building large-scale autoregressive language models. It implements the transformer architecture and provides a toolkit for training models with billions of parameters by distributing weights across compute clusters. The framework distinguishes itself through extensive support for distributed model parallelism, including pipeline and sequence parallelism, to overcome single-device memory limits. It further supports sparse model architectures using a mixture of experts system with Sinkhorn-based routing. The project covers a broad ran

DeepSeek-Coder is a large language model and foundational neural network architecture designed specifically for software development tasks. It functions as an artificial intelligence assistant capable of interpreting complex programming instructions to generate, transpile, and structure source code. The system distinguishes itself through its ability to perform project-level code generation, analyzing broader context and patterns across entire software projects rather than isolated files. It supports multimodal input processing, allowing for the integration of text and visual data to inform i

Llama2.c is a minimal inference engine designed to execute transformer-based language models using only standard C code. By implementing neural network forward passes without external dependencies or complex runtime environments, it provides a lightweight execution environment for running pre-trained models. The project distinguishes itself through a focus on portability and resource efficiency. It utilizes static memory allocation to avoid dynamic heap management and maps model parameter files directly into the process address space to minimize memory overhead. The implementation relies on s

Qwen is a comprehensive framework for large language model development, serving, and deployment. It provides a complete ecosystem for transformer-based sequence modeling, offering base models alongside specialized tools for instruction-tuned alignment, fine-tuning, and long-context inference. The project is designed to support both research and production environments, enabling users to train, optimize, and host generative models locally or across distributed hardware. The framework distinguishes itself through its focus on high-performance serving and extensibility. It features a high-perfor

This project is a comprehensive, community-driven directory of software resources, libraries, and frameworks for the Java programming language. It serves as a centralized knowledge base designed to help developers discover tools and industry-standard solutions for building and maintaining software applications. The repository distinguishes itself through a hierarchical taxonomy that organizes a vast array of technical components into a structured, navigable tree. By relying on distributed peer contributions, the index remains a living resource that reflects current community-recommended pract

Transformers is a comprehensive library for machine learning that provides a unified interface for training, fine-tuning, and deploying transformer-based models. It supports a wide range of tasks, including text classification, language modeling, question answering, and sequence-to-sequence translation, while offering specialized architectures for both text and vision processing. The framework includes tools for managing the entire model lifecycle, from data preprocessing and tokenization to distributed training and inference. The library features extensive support for model optimization and

HanLP is a natural language processing library and deep learning framework specifically optimized for the Chinese language, while also functioning as a multilingual text processor. It serves as a toolkit for performing linguistic analysis, semantic understanding, and script conversion. The project distinguishes itself through a dedicated focus on Chinese linguistic structures, including a specialized script converter for transforming text between Simplified Chinese, Traditional Chinese, and Pinyin. It further supports domain-specific model training to improve the recognition of professional t

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

This project is a comprehensive educational curriculum and structured learning path covering the full lifecycle of large language models. It provides a guided progression through the theory, architecture, training, and deployment of these models. The curriculum includes specialized guides on transformer architecture, model training tutorials, and frameworks for designing autonomous agents. It also provides dedicated resources for studying model safety and ethics. The material covers a wide range of technical capabilities, including distributed training strategies, parameter-efficient fine-tu

This project is an educational course and set of instructional materials for building large language models from scratch using Python. It provides a step-by-step guide and practical tutorials focused on the internal mechanics of transformer architectures and pre-training workflows. The repository features a framework for implementing and comparing diverse model families, including Llama, GLM, and RWKV. It uses a configuration-driven assembly approach to analyze the structural differences and internal mechanisms of these various architectures. The codebase covers the complete development pipe

This project is a library and command-line interface for local large language model inference. It enables the generation of text completions and chat responses from various model architectures. The project provides tools for weight quantization to reduce memory footprints and incorporates hardware acceleration through GPU offloading to increase computation speed. It also includes utilities for model evaluation by measuring perplexity on specific datasets. Capabilities cover the full inference lifecycle, including binary model loading, template-based prompt structuring, and session persistenc

ChatGLM-6B is an open-source bilingual large language model designed for natural dialogue and text generation in both English and Chinese. It is structured as a dialogue model capable of tasks such as role-playing and information extraction. The project provides implementations for quantized language models, using low-precision weights to reduce GPU memory requirements for local inference. It also supports parameter-efficient fine-tuning, allowing model behavior to be optimized for specific tasks without requiring full retraining. The model includes capabilities for local execution on GPUs a

Grok-1 is an open-weights large language model implementation featuring a sparse mixture-of-experts architecture. It is designed for high-performance text generation and natural language processing by activating only a subset of specialized expert layers per token. The model utilizes 8-bit weight quantization to reduce memory overhead and accelerate loading. To manage its high parameter count, the implementation supports activation sharding, which distributes the memory load across multiple hardware devices during execution. The project covers large-scale model inference, including text comp

gemma.cpp is a C++ inference engine for Gemma, PaliGemma, and Griffin language models, designed to run directly on-device without Python dependencies. It provides a self-contained runtime that loads quantized model weights and performs text generation on CPU or GPU, along with a model checkpoint converter that transforms PyTorch or Keras checkpoints into a compact binary format for fast loading. The engine supports multiple model architectures, including the Griffin recurrent architecture with gated linear recurrent layers and sliding-window attention for efficient long-sequence handling, as

Zincsearch is a high-performance, self-hosted full-text search engine and database written in Go. It provides a lightweight infrastructure for indexing and searching unstructured text data, specializing in log and event analysis through a schemaless indexing model. The system is designed as a resource-efficient alternative to heavier search infrastructure, featuring an API surface compatible with Elasticsearch for indexing and querying documents. It distinguishes itself by packaging the entire server and its built-in web search interface into a single statically linked binary. The engine cov

Prompt-poet is a Python templating engine and software library designed for constructing, tokenizing, and rendering dynamic language model prompts. It separates content from application code by storing prompt definitions as independent files on disk, supporting optional in-memory caching and structured metadata organization with named sections, assigned roles, and conditional logic. The library features modular template composition that decomposes prompts into reusable components and shared variants. It provides runtime Python evaluation to execute custom functions directly inside template st

This is a Python SDK for interacting with large language models via API. It serves as a client library to generate text, process messages, and manage conversational states, while providing a specialized interface for connecting to models hosted across different cloud infrastructure providers. The SDK includes a tool-calling framework that maps Python functions to JSON schemas, allowing models to execute external tools. It also features a built-in token counting utility to estimate input size before transmission and a server-sent events client for receiving model tokens in real time. The libr

Gensim is a natural language processing toolkit designed for large-scale text analysis and the training of semantic vector embeddings. It provides a framework for identifying latent thematic structures within document collections and calculating semantic similarity between text segments using unsupervised statistical algorithms. The project is distinguished by its ability to handle datasets that exceed available system memory through incremental corpus streaming, which processes documents one at a time from disk. It utilizes sparse vector representations and dictionary-based token mapping to

OpenNRE is a natural language processing library and neural relation extraction framework designed to transform unstructured text into structured relational data. It serves as a toolkit for identifying relationship types between entities and generating entity-relation-entity triples to populate and expand knowledge bases. The framework provides tools for both supervised and distantly supervised relation extraction, allowing neural models to be trained on labeled datasets or via automated pipelines that align knowledge base triples with raw text. The project covers a full information extracti

Synonyms is a natural language processing library and semantic similarity engine specifically designed for Chinese text. It functions as a word embedding toolkit and tokenizer that extracts semantic meaning and identifies synonyms by calculating the conceptual closeness between words and sentences. The system provides a toolkit for Chinese word embedding and synonym discovery, allowing for the retrieval of semantically similar words to expand vocabulary. It distinguishes itself through a configuration-driven approach to model loading, which supports the integration of custom word embeddings t