This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks

Wonderful Matrices to Build Small Language Models

SLM-SQL: An Exploration of Small Language Models for Text-to-SQL

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

An Android App recreating the Simon Says game. Uses MediaPipe to run an LLM on device

Code for paper "Achieving Sparse Activation in Small Language Models"

This repository provides everything you need to perform Supervised Fine-Tuning (SFT) of the Qwen2.5-Coder-1.5B-Instruct model—or any of its larger variants (7B, 14B, 32B)—on the Qwen Models, using the nvidia/OpenCodeReasoning dataset.

A Streamlit demo using an SLM (Phi) and RAG to showcase how an AI can help users with learning functionality on a website

Small agent powered by IBM Granite.

Enhancing Reasoning Skills in Small Persian Medical Language Models Can Outperform Large-Scale Data Training

TinyGPT - 9M Parameters

AtomMind is a lightweight Small Scientific Language Model (Sslm) for reasoning across Math, Physics, Chemistry, and Biology using domain experts, symbolic reasoning, and optimization modules. It supports optional memory and self-monitoring to improve problem-solving and accuracy.

The frontend code used by the 'Zest' Natural Language to CLI commands tool from Spicy Lemonade

GraphRAG-powered Small Language Model for experimentation and statistical analysis Q&A

Applied Decision Architecture Matrix - Small Language Model

Pruning, Quantization recipe for Small Language Model

A HuggingFace Transformer.js Demo Running Generative AI Model in Web Browser

Probing whether reasoning can be structurally crystallised into a small LLM via cyclic domain training + gap phases. Testing emergence at 300M parameters from scratch. SAE-based interpretability. Pruning crossover as depth measurement. Open collaboration.

A comprehensive Natural Language Processing project focused on clinical dialogue analysis, featuring medical text classification, summarization and generation using traditional machine learning, custom deep learning architectures, and transformer-based fine-tuning approaches.

Transformer-based Calculator