Active Learning for Text Classification in Python

Local LLM Powered Recursive Search & Smart Knowledge Explorer

Doge Family of Small Language Models

"Generative AI in Action" book's code repository

Wonderful Matrices to Build Small Language Models

Remma-O1: An open-source Language Model with 1.17B Params, built on pytorch from scratch. Work in Progress!!! Open for collaboration.

A Python library to train task-specific LLMs without training data, for offline NLP and Text Classification tasks, such as Guardrail Models and Intent Classification 🤖🚀

SQL AI Agent - Talk to your DB in Natural Language

Ollama RAG using SQL Database

LeCarnet is a 2 M+ corpus of simple French stories

A lightweight voice companion, optimized for macOS.

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

Code for the paper "Deep neural networks and humans both benefit from compositional structure"

Federated Fine-Tuning of LLMs on Apple Silicon with Flower.ai and MLX-LM

full text search your meme/screenshot folder with small LMs x traditional OCR

[KDD 2025] Code for the paper "On the Necessity of World Knowledge for Mitigating Missing Labels in Extreme Classification"

A fine-tuned version of SmolLM2-360M-Instruct-bnb-4bit specialized for parsing unstructured calendar event requests into structured JSON data.

An HF's Smolagent to automate molecular dynamics simulations using GROMACS.

TinyLLM is a research project focused on developing and training compact, specialized language models using publicly available datasets from platforms like Hugging Face. The project aims to explore diverse architectures and build expertise toward creating a high-performance coding model rivaling the capabilities of claude code

This repository implements a 𝐒𝐦𝐚𝐥𝐥 𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐌𝐨𝐝𝐞𝐥 (𝐒𝐋𝐌) designed for lightweight and efficient natural language processing tasks. Unlike large-scale models, an SLM provides 𝐟𝐚𝐬𝐭𝐞𝐫 𝐢𝐧𝐟𝐞𝐫𝐞𝐧𝐜𝐞, 𝐥𝐨𝐰𝐞𝐫 𝐦𝐞𝐦𝐨𝐫𝐲 𝐮𝐬𝐚𝐠𝐞, 𝐚𝐧𝐝 𝐜𝐨𝐬𝐭-𝐞𝐟𝐟𝐞𝐜𝐭𝐢𝐯𝐞 𝐝𝐞𝐩𝐥𝐨𝐲𝐦𝐞𝐧𝐭