Zoof is a high-efficiency Small Language Model (SLM) engineered from scratch. It demonstrates how modern architectural choices and high-quality data can yield competitive performance in the sub-400M parameter regime, even with limited compute.
☆47Jan 13, 2026Updated 6 months ago
Alternatives and similar repositories for zoof
Users that are interested in zoof are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A PyTorch framework for training transformer language models with Mixture of Experts (MoE) architecture support, Mixture of Depths (MoD),…☆21Aug 1, 2026Updated last week
- Local-first agent runtime for MCP workflows with explicit trust controls, replayable runs, and built-in evals.☆32Jul 4, 2026Updated last month
- Natural language control for Python CLI tools using locally-trained SLMs (CPU inference)☆32Apr 10, 2026Updated 3 months ago
- Modular task agnostic training pipeline using LFM2 from Liquid AI with unsloth.☆16Sep 13, 2025Updated 10 months ago
- Group-relative Trajectory-based Policy Optimization: Increasing Quality and Training Stability☆42Feb 23, 2026Updated 5 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- An fully autonomous agent that accesses the browser and performs tasks.☆18Apr 25, 2025Updated last year
- Personal voice assistant, with voice interruption and Twilio support☆18Feb 24, 2025Updated last year
- Compiling strategy guides into reward functions for reinforcement learning. Uses Claude Vision to extract unit tests from game guides, …☆37Jan 30, 2026Updated 6 months ago
- Lightweight C inference for Qwen3 GGUF. Multiturn prefix caching & batch processing.☆25Sep 1, 2025Updated 11 months ago
- *NIX SHELL with Local AI/LLM integration☆26Feb 26, 2025Updated last year
- world's stupidest moe llm in 103M parameters☆20Jul 18, 2025Updated last year
- Load and run Llama from safetensors files in C☆16Oct 24, 2024Updated last year
- A 3D Dolly Zoom experiment run on the web browser.☆16May 16, 2014Updated 12 years ago
- Dynamic per-token early exit for LLM inference. Skip layers tokens don't need☆33Mar 18, 2026Updated 4 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Code for the paper: "StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation"☆40May 16, 2025Updated last year
- Web application for roleplaying with AI-powered characters☆67Jul 8, 2025Updated last year
- Pure C wrapper library to use llama.cpp with Linux and Windows as simple as possible.☆15Jul 28, 2026Updated last week
- Port of the miscellaneous V4L2 tools for QNX 6.5 and above (mainly for devu-uvc project).☆12Mar 26, 2014Updated 12 years ago
- From-scratch implementation of OpenAI's GPT-OSS model in Python. No Torch, No GPUs.☆111Nov 5, 2025Updated 9 months ago
- 🐜🔧 A minimalistic tool to fine-tune your LLMs☆19Aug 17, 2023Updated 2 years ago
- A framework for few-shot evaluation of autoregressive language models.☆16Aug 23, 2023Updated 2 years ago
- Would you like to recreate GPT-2 124m in a cave with a box of scraps and a 4090 in less than two hours? LETS SPEEDRUN!☆39Nov 26, 2025Updated 8 months ago
- ☆65Jun 24, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Ultra-lightweight C++ inference engine for BitMamba-2 (1.58-bit SSM). Runs 1B models on consumer CPUs at 50+ tok/s using <700MB RAM. No h…☆21Jun 2, 2026Updated 2 months ago
- ONNX speech pipeline library for ASR, diarization, VAD, and denoising☆20Jun 14, 2026Updated last month
- An unofficial implementation of SOLAR-10.7B model and the newly proposed interlocked-DUS(iDUS) implementation and experiment details.☆14Mar 20, 2024Updated 2 years ago
- VITS Inference using ONNX Runtime on C++☆13Dec 25, 2023Updated 2 years ago
- A Docker-based OpenAI-compatible Text-to-Speech API server powered by Kyutai's TTS models with GPU acceleration support.☆22Jul 12, 2025Updated last year
- this is a dungeon ai run locally that use your llm in the terminal with multiple players from 2 to 5☆17Jan 25, 2026Updated 6 months ago
- A char level language model ,this repo is just for learning .☆18Jun 14, 2026Updated last month
- EvaByte: Efficient Byte-level Language Models at Scale☆119Apr 22, 2025Updated last year
- Long context evaluation for large language models☆18Jan 23, 2026Updated 6 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- An experimental desktop client for using Claude Desktop's MCP with Novelcrafter codices.☆11Dec 3, 2024Updated last year
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆32May 1, 2025Updated last year
- Historical Language Model for London - A specialized LLM trained on 1500-1850 historical English text☆35Nov 1, 2025Updated 9 months ago
- Genetics for Language Models☆18Jul 1, 2024Updated 2 years ago
- Multi-Modal Language Modeling with Image, Audio and Text Integration, included multi-images and multi-audio in a single multiturn.☆18Feb 20, 2024Updated 2 years ago
- AI tool for auto-research, TTS, and Graphical assembly into a completed Podcast☆81Feb 8, 2026Updated 6 months ago
- A ground-up LLM engineering project: tokenizer → architecture → training → scaling laws → inference. Starts at 80M, engineered to scale i…☆75Jan 29, 2026Updated 6 months ago