A fast multimodal LLM for real-time voice

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

Chatbot继续沿着LLM前进，近期更新小参数量SLM的和训练脚本，支持本地训练。新增ChatAgent,实现各种有实际场景价值的Agent实现。

NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

[ICLR-2025-SLLM Spotlight 🔥]MobiLlama : Small Language Model tailored for edge devices

Survey of Small Language Models from Penn State, ...

利用免费的大模型api来结合你的私域数据来生成sft训练数据 支持llamafactory等工具的训练数据格式synthetic data

PySLM: A Python Library for 3D Printing and Additive Manufacturing

Python package for high-performance spatial light modulator (SLM) control and holography. Supports features from aberration-corrected 3D point clouds to automated Fourier-domain calibrations.

🦜🪺 Parakeet is a GoLang library, made to simplify the development of small generative AI applications with Ollama 🦙.

"Generative AI in Action" book's code repository

An experiment that applies Google Research's `ReasoningBank` technique to Small Language Models. This experiment hopes to show that the same gains from the ReasoningBank paper also applies to much smaller, less capable models.

Some experiments around AI to learn.

A powerful 130-million-parameter model trained from scratch as part of a truly open-source stack, including a custom tokenizer, dataset, and optimizer.

[Kaggle-2nd] Lightweight yet Effective Chinese LLM.

Build low-code, event-driven AI applications and workflows using **any** OpenAI API-compatible framework.

Code repository dedicated to experimenting and research with tiny reasoning language model

Local/Offline Machine Learning Resources

libSLM is a c++ library for generating and transfering to SLM Machine Systems

Simple and lightweight tool to fine-tune GPT models (like GPT-2 and GPT-Neo) using your own data — built with Python and Transformers. Adapt powerful language models to your domain with ease.

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

Embedding-driven, context-aware text chunking for Semantic Kernel and RAG workflows in .NET

Natural language control for Python CLI tools using locally-trained SLMs (CPU inference)

SSPIM is a pattern producer for gray and binary spatial light modulators.

Historical Language Model for London - A specialized LLM trained on 1500-1850 historical English text

The Cuban Language Model

SLMs List that can run on a Pi5 8GB

Lightweight C inference for Qwen3 GGUF. Multiturn prefix caching & batch processing.

Small transformer model for stock market intraday forecasting

Local PC app for everyone to use LLM locally 🫡