slms

Federated Learning for LLMs.

Upload your data → Get a fine-tuned SLM. Free.

The official implementation of "A Language Modeling Approach to Diacritic-Free Hebrew TTS"

Automatically exported from code.google.com/p/audiotools

Zest. Natural Language to CLI commands tool from Spicy Lemonade.

Fine-tuning open-source large and small instruct/chat language models (LLMs & SLMs) from the Hugging Face Model Hub using public datasets.

Azure IoT Operations with Edge AI in-a-Box

Tool-calling AI agents that run locally.

Kurtis is a fine-tuning, inference and evaluation tool built for SLMs (Small Language Models), such as Huggingface's SmolLM2.

This project demonstrates how to evaluate the use of LLMs and SLMs for extracting structured data from documents using .NET

Microtensor - Bittensor subnet 92. Frontier accuracy at a fraction of the size, gated on a verified deployment envelope.

[ICLR 2026 Accepted paper] BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models

🧳 SayHalo – AI-powered (gen-ai) SLM Aggregator for seamless chat experience. 💬🤖 Built with Next.js, TypeScript, Tailwind & Resend. ⚡✨ Early access available now! 🔥

AetherArena- Agentic Desktop Assistant

A comprehensive research project comparing different Retrieval-Augmented Generation (RAG) techniques applied to medical question-answering in obstetrics.

SLM-T-Q-Relay implements a query routing mechanism within a tree of small language models, where each node either answers or forwards queries to the most relevant model.

A ternary-aware edge-native transformer stack built from scratch.

The official transformers wrapper for Echo-DSRN, a recurrent language model.

I'm lazy... That's why I'm doing this...

OpenEye is an open-source AI framework designed to enable fully native, offline AI execution on constrained edge hardware. While most modern AI systems depend on cloud-based inference and large-scale models, OpenEye introduces a decentralized architecture that allows AI to run directly on-device.