Open-Weight Models

Model · Zero-shot classification

malkuth-4b

Sae Chan O

A small multilingual decision model for classification, with a focus on Korean. Given a text, a question, and a set of criteria, Malkuth returns probabilities over the possible choices instead of generating text. Malkuth-4B is a LoRA adapter trained on Kev and built on a frozen Qwen/Qwen3.5-4B-Base. It has 33.8M trainable parameters and a 124 MB adapter. - choice: select one of up to 255 options - noul: yes or no - score: select an ordered level Multiple questions can be evaluated against the same input. Questions are evaluated independently, so they cannot see each other's answers. Probabilities are temperature-calibrated on a held-out validation split. Malkuth is served through Kev and…

ONNX models used by the mangadict browser extension to find and read Japanese text in manga pages. They are repackaged from the models below for in-browser inference with onnxruntime-web; see those repos for training details and their licenses (all Apache-2.0). Use tagged revisions (e.g. v1); main may change.

Attention manifold checkpoint for LLaMA 3.2 1B Instruct. This model extends the standard transformer attention mechanism with learned manifold structures on the value path. The checkpoint contains the manifold parameters only — the base model weights are loaded from meta-llama/Llama-3.2-1B-Instruct. See the LLM Inspector for the full visualization and editing toolkit. Paper forthcoming.

Model · Text generation

mario-html-4B-GGUF

Wesjos Max

A visual-UI language model fine-tuned from Qwen3.5-4B, quantized to GGUF for llama.cpp. It answers in a small semantic HTML component system — bento grids, metric cards, steppers, callouts — wrapped in one root, instead of plain Markdown. Reasoning-native, and no system prompt required. One root element; everything else is an optional child: ai-view-header is not in the source repo's theme.css — it renders with default header styling. Fine, but define your own if you want tighter control. Apache License 2.0.

Action Chunking with Transformers (ACT) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot act guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning…

Model · Image to 3d

matchanu-1.5

PYGRASSREAL

Matchanu 1.5 is PyGrassReal's generative 3D asset engine capable of synthesizing production-ready watertight 3D meshes (STL, OBJ, PLY) and real-time 3D Gaussian Splats from text descriptions or single 2D concept images. Designed for Industrial Prototyping (3D Printing), Game & AR/VR Assets, and Architectural Elements, Matchanu 1.5 generates clean topology, UV unwrappings, and volume-accurate meshes without the point cloud artifacts common to open-source prototypes. 1. Prompt & Image-to-3D Mesh: - Converts single-view product photos or text prompts into clean, manifold 3D meshes ready for Blender, Rhino, Maya, or Unreal Engine. 2. 3D Printing Ready (Watertight Topology): - Automatically…

Model

matching

Allen E. Li

This repository is a compact, custom PyTorch implementation of Dino for Matching. The base configuration is intended for code review, smoke tests, and small controlled experiments rather than as a production-ready pretrained release. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses novograd with a linear warmup schedule. These are…