Multi-arch builds of HuggingFace tokenizers
HuggingFace Transformers.js provider for @workglow/ai.
Multi-arch builds of HuggingFace tokenizers
HuggingFace Inference API provider for @workglow/ai.
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
HuggingFace adapter for Agentick — local embeddings via transformers.js
[](https://github.com/huggingface/Mongoku/actions/workflows/ci.yml)
Multi-arch builds of HuggingFace tokenizers
Multi-arch builds of HuggingFace tokenizers
A minimalistic JavaScript implementation of the Jinja templating engine, specifically designed for parsing and rendering ML chat templates.
Typescript client for the Hugging Face Inference Providers and Inference Endpoints
🤗 Tokenizers.js: A pure JS/TS implementation of today's most used tokenizers
Utilities to interact with the Hugging Face hub
A collection of tools to help you deploy, bundle HuggingFace Spaces and related assets with ease.
HuggingFace integration: cache scanning, model discovery, artifact inspection, and downloads
A wrapper for the huggingface api.
Huggingface Server embedding provider for Chroma
HuggingFace tokenizer support for Chonkie - extends @chonkiejs/core with real tokenization
Enable usage of HuggingFace models with embedjs
Multi-arch builds of HuggingFace tokenizers
MCP Server for HuggingFace inference endpoints with custom LoRA and story generation
Enable usage of HuggingFace models with embedjs
nlux React is a library for building conversational AI interfaces, with support for OpenAI, HuggingFace, and more.
Multi-arch builds of HuggingFace tokenizers
huggingface
HuggingFace's API for accessing large language models (LLMs) and embeddings.
Hugging Face provider for LLM Kit
HuggingFace Inference API integration for Synaptic: Embeddings
HuggingFace Hub I/O plugin for dsq
Blazingly fast tokenizer - 50x faster tokenization, 10x smaller model files, 100% accurate drop-in replacement for HuggingFace
TUI and CLI for searching and downloading HuggingFace models
Hugging Face Inference Providers (Router) for chat-rs.
Lightweight synthetic data generation library/CLI.
ASIMOV module for model downloads from the Hugging Face Hub platform.
A unified, multi-backend tokenizer library for LLMs
A Huggingface downloading CLI tool written in Rust.
A complete, production-ready Ruby implementation of the HuggingFace Hub client library. Download models, datasets, and manage repositories with zero Python dependencies. Features smart caching, authentication, progress tracking, and comprehensive error handling.
Fast tokenization for Ruby using HuggingFace's Rust-powered tokenizers library. Supports GPT, BERT, LLaMA, Claude, and any HuggingFace tokenizer.
Gem to invoke API calls to Huggingface and Openai LLMs
Ruby implementation of Google's SigLIP2 model for creating text and image embeddings. Uses ONNX models from HuggingFace onnx-community.
Prescient provides a unified interface for AI providers including local Ollama, Anthropic Claude, OpenAI GPT, and HuggingFace models. Built for AI applications with error handling, health monitoring, and provider switching.
Ruby bindings for the Onde inference engine. Run LLMs and speech-to-text locally with automatic HuggingFace model management, cache inspection, and GPU acceleration.
ignis-dl is the deep-learning layer of the Ignis ecosystem: NN modules (Linear, Embedding, LayerNorm, RMSNorm, Dropout), optimizers (SGD/Adam/AdamW), losses, and a transformer stack (multi-head + grouped-query attention, RoPE, SwiGLU, KV cache) with HuggingFace weight loaders (GPT-2, Llama). Loads real GPT-2 and Llama-3.2 checkpoints and matches HuggingFace logits, and trains transformers from scratch — in Ruby, on native Windows. Installing this pulls the whole stack (ignis + ignis-autograd), so it also serves as the meta-gem.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.