249M-param MoE transformer built from scratch in PyTorch. GQA, RoPE, SwiGLU, sparse MoE with 3 aux losses, AMP training loop no Trainer abstractions. Architecture mirrors LLaMA/Mistral/Mixtral decisions, fully inspectable.
☆19May 22, 2026Updated 5 months ago
Alternatives and similar repositories for H64LM
Users that are interested in H64LM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆14Dec 16, 2022Updated 3 years ago
- Privacy-first iOS app with on-device LLM inference via llama.cpp. Chat with local models, get AI health insights from HealthKit, and trac…☆32Aug 3, 2026Updated 2 months ago
- Experimental Chrome side-panel browser agent with LangGraph.js, MCP/WebMCP, local models, and semantic browser automation.☆20May 18, 2026Updated 5 months ago
- Implementation of a fast semantic chunker in C++, installable in python 3.7+ projects.☆22Sep 20, 2025Updated last year
- Abliterates models quickly and efficently, Qwen2.5-7B: 95%→2% refusal at 0.095 KL☆35Oct 2, 2026Updated 3 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- YAML Fundamentals for DevOps, Cloud and IaC Engineers, published by Packt☆12Jan 30, 2023Updated 3 years ago
- Implementation of "Scaling Latent Reasoning via Looped Language Models" aka LoopLM☆31Apr 28, 2026Updated 5 months ago
- This repo is a alternative solution for standard self-attention. It uses tree routing with learnable functions for cheaper self-attention…☆41Oct 11, 2026Updated last week
- Making MoE fine-tuning accessible to anyone with consumer hardware.☆18Oct 4, 2026Updated 2 weeks ago
- [COLM '24] Source-Aware Training Enables Knowledge Attribution in Language Models☆23Apr 1, 2025Updated last year
- Minimal training code of a nano text-to-image model☆37May 28, 2026Updated 4 months ago
- A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the…☆49Jul 10, 2026Updated 3 months ago
- A lightweight transformer language model built from scratch in PyTorch, trained on a single consumer GPU with a full pipeline for data pr…☆42Sep 30, 2026Updated 3 weeks ago
- Glow-TTS with Stochastic Duration Predictor and Stochastic Pitch Predictor☆20Jun 5, 2023Updated 3 years 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.
- Chain two LLMs — local or cloud: a Prompter that refines your idea, and a Coder that writes the code.☆34Jul 18, 2026Updated 3 months ago
- Code for boomerang distillation enables zero-shot model size interpolation.☆23Oct 14, 2026Updated last week
- Pretraining codebase for Apertus models, based on Megatron-LM☆23Oct 2, 2026Updated 3 weeks ago
- clustering method for single-cell transcriptomics data☆11Oct 11, 2026Updated last week
- Examples for the Activate conference☆11Sep 11, 2019Updated 7 years ago
- Backprop with Low-Precision Activations☆11Oct 28, 2019Updated 6 years ago
- A machine learning library focused on deep learning☆11Jun 2, 2015Updated 11 years ago
- Architected a distributed notebook execution environment simulating Kaggle Kernels. Utilized the Kubernetes K8s API for dynamic pod orche…☆20May 3, 2026Updated 5 months ago
- A very simple progress bar for python with accurate time prediction (linear).☆11Dec 30, 2021Updated 4 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Chew is a Go library for processing various content types into markdown/plaintext.☆42Feb 16, 2025Updated last year
- Demo of fine-tuning QA models for answering FAQ of cloud providers documentation☆11Jun 20, 2026Updated 4 months ago
- Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fu…☆29Updated this week
- ☆18Mar 20, 2017Updated 9 years ago
- A database-agnostic Agentic GraphRAG framework using swappable System One models (local Laya / cloud Jev). A plug-and-play intelligence l…☆51Sep 29, 2026Updated 3 weeks ago
- SwiftLet is a lightweight Python framework for running open-source Large Language Models (LLMs) locally using safetensors☆29Aug 6, 2025Updated last year
- CIFAR10 ResNets implemented in JAX+Flax☆12Apr 6, 2022Updated 4 years ago
- LLM Context Manager for inference optimization☆25Jul 28, 2025Updated last year
- Lightweight OpenAI wrapper using FastAPI. Add rate limits to OpenAI usage, optionally log and store all API calls, and share regulated Op…☆15Feb 15, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆20Updated this week
- 🏝️ Code for our paper: "Privasis: Synthesizing the Largest 'Public' Private Dataset from Scratch"☆16Jul 10, 2026Updated 3 months ago
- ☆11Jul 23, 2021Updated 5 years ago
- Answer-aware memory for Markdown notes: hybrid search + pluggable passage reranker, as a Claude Code plugin☆12Oct 15, 2026Updated last week
- Groq-powered MAD: The first work to explore Multi-Agent Debate with Large Language Models :D☆12Jul 5, 2024Updated 2 years ago
- A Rust binding for LibHailoRS☆11Jan 18, 2025Updated last year
- Fork of github.com/UCSBarchlab/OpenTPU for the TGPTPU project☆14Jun 1, 2025Updated last year