Bonsai Demo

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

OpenSSA: Small Specialist Agents based on Domain-Aware Neurosymbolic Agent (DANA) architecture for industrial problem-solving

Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models

[CVPR 2024] Asymmetric Masked Distillation for Pre-Training Small Foundation Models

This repository features a custom-built decoder-only language model (LLM) with a total of 37 million parameters 🔥. I train the model to be able to ask question from a given context

BobVLM – A 1.5B multimodal model built from scratch and pre-trained on a single P100 GPU capable of image descriptions and moderate question answering. 🤗🎉

Overview of self-supervised learning of tiny models, including distillation-based methods (aks. self-supervised distillation) and non-distillation methods.

Code for "On the Surprising Efficacy of Distillation as an Alternative to Pre-Training Small Models"

Help us define the Pareto front of small models for MNIST classification. Frugal AI.

If OpenAI builds engines, VOID builds the chassis.

Provide specialized AI agents that develop, review, debug, and deploy production-ready code efficiently across various programming tasks.

Portable Knowledge — Prepared For AI

LlamaTalks is a modern web application designed to facilitate seamless conversations with powerful language models,

Universal AI agent framework — 1B models compose multi-step plans like 12B with structured context (CTT). 6 domains, 8 MCP tools, 167 tests, zero runtime deps.

A DeepSeek-R1 1.5B model is given a task and left to reason through it autonomously — no code, no guessing. It commits its own progress to GitHub. Currently attempting a Sudoku puzzle. Struggling, honestly.

Local-first coding agent built with small models in mind and tight VRAM budgets.

Fine-tunes a T5-small model on the TellMeWhy dataset using context injection from a large language model (Gemini) to improve causal reasoning for “why” questions in narratives. Combines efficient training with human and automated evaluations to assess impact.

Hermes Agent plugin: bounded runbook-driven workflows for small local models. Deterministic scripts, verifier-first discipline, guarded publication.