Directory
Published directory entries matching your search.
Mochi is an open-source video generation model by Genmo, released under an Apache 2.0 license. The repository provides installation, weight downloads, a Gradio UI, CLI, and API, plus LoRA fine-tuning support and an inference harness.
GALACTICA is a general-purpose scientific language model trained on scientific text and data. This repository provides a Model API for GALACTICA, installable from pip or the repository, with five model sizes. The models can be used with the transformers library. It is a stand-alone model that is not instruction tuned, so correct prompts are needed for good results.
Moon Phase Radio broadcasts worldwide via FM, AM and the Web, offering commercial-free Ambient and Downtempo music on two separate channels 24 hours a day. It commenced broadcasting on 1st January 2010 and is privately funded and listener supported, without on-air advertising or air-play charges. Listeners can tune in via internet platforms or the station's own radio player.
Muse is a text-to-image Transformer model that generates images from text prompts and supports image editing, including inpainting, outpainting and mask-free editing, without fine-tuning or inverting the model. It is trained on a masked modeling task in discrete token space using text embeddings from a pre-trained language model.
Self-hosted downloader and player for YouTube, Bilibili, Twitch, MissAV, and yt-dlp sites. Features channel subscriptions, auto-downloads, and local storage for media. Organize your library into collections with a sleek UI. Includes built-in Cloudflare Tunnel support for secure remote access without port forwarding. Docker-ready deployment.
Netmaker is a zero trust networking platform. It connects devices, clouds and sites using WireGuard tunnels with granular access controls. Access Control Lists let users configure which devices in a network can communicate, with options to block access to a device or make a whole network default-blocked. Policies can restrict traffic by directionality, ports, destination and hostnames.
Neuraxle is an AutoML library that supports hyperparameter tuning via pipeline abstractions to build clean deep learning production pipelines. Pipeline steps can have associated hyperparameter spaces, and the library is compatible with Scikit-Learn, TensorFlow, and most other libraries, frameworks, and MLOps environments.
Nexdata is a data service and annotation platform offering services including annotation, fine-tuning, RLHF, red teaming, in-cabin sensing datasets, LiDAR data labeling, and LLM annotation. It provides a human-computer interaction semi-automatic annotation platform with flexible deployment options for public cloud or privatized deployment, and multi-level quality inspections.
NextPVR is a free whole-home digital video recorder for Windows, Linux, Mac and Docker. It records, watches and streams live TV across devices, with live TV, a TV guide, recordings, search and a web scheduler. Supported tuners include DVB, ATSC, QAM, DMB-T, analog, SAT>IP and HDPVR.
NNI is an open source AutoML toolkit developed by Microsoft. It automates tasks across the machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning for machine learning workflows.
NYCU Dataverse is a research data repository for National Yang Ming Chiao Tung University, established in 2022. It accepts deposits of finalized research data from the university's faculty, research staff and students, provided the content does not violate copyright or intellectual property rights and contains no identifiable information. The repository aims to make the university's research data publicly accessible to support citation and academic visibility.
OnionHop is a desktop client that routes traffic through Tor, offering proxy and system-wide VPN modes, bridges for restrictive networks, split tunneling, a kill switch, and a command-line client. It is available for Windows, Linux and macOS.
Online Sequencer is a browser-based music sequencer for making tunes and sharing them with friends. It offers instrument selection, note and marker selection, grid and time-signature settings, and export to MP3, WAV and MIDI, along with MIDI and sequence import and sheet music opening.
Public data portal for browsing datasets from Tunesia.
OpenTunnel is a free tunneling service offering SSH, V2Ray, XRay, OpenVPN, WireGuard and other accounts. The site states that accounts are free, servers offer unlimited bandwidth and are online 24 hours, and no logs are used to monitor activity. It lists total server counts per protocol.
OrcaSlicer is a free, open-source 3D printing slicer for FDM 3D printers, created by SoftFever. It runs on Windows, macOS, and Linux and is licensed under AGPL-3.0. The slicer includes a built-in calibration suite and per-feature control over print settings, with tuned profiles for printers from Bambu Lab, Prusa, Creality, Voron, and others. Network printing supports Klipper, PrusaLink, and OctoPrint.
oumi-ai/oumi is a publicly available GitHub repository that provides tools and workflows for fine-tuning, evaluating, and deploying open-weight large language models, with support for models such as Qwen and Gemma.
Paper Digest - ChatGPT is a curated resource page from Paper Digest that collects recent ChatGPT-related academic papers. The Paper Digest team extracts relevant papers, generates associated features for each entry, and sorts the results by relevance and date. The static page is updated bi-weekly, and a more frequently updated online version is also available. The page includes a brief overview of ChatGPT as OpenAI's November 2022 launched generative chatbot built on the GPT-3 family of large language models, fine-tuned with supervised and reinforcement learning techniques.
If you want to find out more about how these models were trained and even fine-tune them yourself, check-out the Parler-TTS repository on GitHub.
A write-up on practical patterns for integrating large language models into systems and products, drawing on academic research, industry resources and practitioner know-how. It covers seven key patterns, including evals, RAG, fine-tuning, caching, guardrails, defensive UX and collecting user feedback.
Petals is a project for running large language models at home, BitTorrent-style. Users load part of a model and join a network of people serving its other parts. It supports generating text with Llama 3.1, Mixtral, Falcon and BLOOM and fine-tuning them on a consumer-grade GPU or Google Colab.
Pipeline Conversations is a podcast from ZenML featuring interviews with platform engineers, ML practitioners and technical leaders building production AI systems. Episodes cover MLOps and LLMOps topics including Kubernetes workflows, model fine-tuning and evaluation, LLM security, cost optimization, prompt engineering and agents in production.
A project to create a Cairo backend for abcm2ps, enabling it to generate output in formats supported by the Cairo library: PNG, SVG and PDF. It adds flags to select those output formats and produces one file per tune.
Polyaxon is a platform for building, training, and monitoring large-scale deep learning applications. It deploys into any data center or cloud provider and supports major deep learning frameworks such as Tensorflow, MXNet, Caffe, and Torch. It manages workloads with container and node management and offers hyperparameter tuning through experiment groups defining a search algorithm and search space.
