Architecture Modification / Research · Python

open-i3

A novel hybrid language model combining RWKV time-mixing and standard Multi-Head Attention for efficient training on consumer hardware.

FlameF0X@FlameF0X · Atlas 61.2 · #14= builder

View on GitHub4 Open FlameF0X's Atlas

What it is

The repository provides implementations of hybrid RWKV-Transformer models for BERT-style masked language modeling, language generation, and CLIP-style zero-shot image classification, including training and inference scripts.

Scored at4d7d8068 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Where it counts

Machine Learning92%
NLP & LLMs85%
Computer Vision35%
MLOps15%
Data Science10%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the Machine Learning board

Whole board

RankProjectBuilderFieldMerit

65, shared rankViralCutterML Application · PythonViralCutter is an open-source desktop application that automates the creation of short-form videos from long sources using AI-powered transcription, face tracking, and LLM-driven scene selection. It provides a Gradio/FastAPI+React web interface and CLI for end-to-end video…52.9/100ImplementationYudhis PratamaMachine Learning
71AgroADASML Application · PythonThe AgroADAS repository provides an end-to-end system for agricultural machinery guidance, including data collection, training of a multi-task segmentation and waypoint prediction model, and C++ inference for real-time deployment.52.6/100ImplementationSuceveanu Mircea Dan SanduMachine Learning
72open-i3Architecture Modification / Research · Python52.5/100ImplementationFlameF0XMachine Learning
73ml-from-scratchEducational Implementation · Jupyter NotebookThis repository contains from-scratch NumPy implementations of K-Nearest Neighbors, linear regression, and logistic regression, each with a README explaining the algorithm and usage, and a notebook demonstrating training and evaluation for linear regression.51.9/100ImplementationPop AlexandruMachine Learning
74, shared rankgenerative-lbracketML Application · Jupyter NotebookThe repository provides an end-to-end workflow for parametric L-bracket design, using C#/PicoGK to generate a dataset, training surrogate regression models (Random Forest, MLP) in Python, and applying Optuna to minimize predicted mass via generative design.50.9/100ImplementationkarimsMachine Learning

What it is

Where it counts

Around it on the Machine Learning board

More from FlameF0X