github.com
Serve Llama 2 and other large language models locally from command line or through a browser interface.
Directory
Search results
Published directory entries matching your search.
numind.ai
NuExtract 2.0 is a document information extraction model developed by NuMind. NuMind builds frontier multimodal large language models that convert documents into structured JSON and clean Markdown, available via SaaS or private enterprise deployment. The models are specialized for document extraction and deployed in industries including insurance, banking, and healthcare; for example, AXA increased its extraction accuracy from 30% to 97% after switching to NuExtract.
github.com
Notebooks is a Docker-based starter kit for machine learning through Jupyter notebooks, intended for users who want a ready runtime environment. Its images cover combinations of Keras, TensorFlow and PyTorch with CUDA v8 through v11, and include JupyterLab, scikit-learn, pandas and visualization, vision and NLP libraries. Python 3 only, as Python 2 is end-of-life.
github.com
nn_builder is a tool for building neural networks with less boilerplate code; the user specifies the network type and it builds it. It supports NN, CNN and RNN networks for PyTorch and TensorFlow 2.0, taking arguments such as layers_info, hidden_activations and dropout.
neuroph.sourceforge.net
Neuroph is a lightweight, open source Java neural network framework released under the Apache 2.0 license. It provides a Java library and a GUI editor, Neuroph Studio, based on the NetBeans Platform, for creating, training and saving neural networks. It supports architectures including Perceptron, Multi Layer Perceptron, Hopfield, Kohonen and RBF networks, and both supervised and unsupervised learning rules.
github.com
NALP is a Python library covering Natural Adversarial Language Processing. It combines natural language processing and adversarial learning, from embeddings to neural networks. The package offers corpus loading for raw text and audio, encoders, and pre-loaded neural network models. Version 3.0.2 requires Python 3.11+.
huggingface.co
Mixtral-8x7B-v0.1 is a pretrained generative Sparse Mixture of Experts large language model developed by Mistral AI, hosted on the Hugging Face platform under the mistralai/Mixtral-8x7B-v0.1 repository, and released under the Apache 2.0 license.
github.com
Mamba-Chat is a chat language model built on a state-space model architecture rather than a transformer. The repository provides training and fine-tuning code based on a modified Huggingface Trainer class. The model is based on Mamba-2.8B and was fine-tuned on 16,000 samples of the HuggingFaceH4/ultrachat_200k dataset. Code is provided for testing and fine-tuning, including a command-line chatbot and a Gradio app.
github.com
LMFlow is a toolkit for finetuning and inference of large foundation models, presented as extensible, convenient and efficient. It offers support for custom optimizer training, conversation templates, speculative decoding, long context inference with position interpolation for LLaMA models, and Flash Attention-2. The project is released under the Apache-2.0 license and was made available on PyPI.
github.com
LLMKube is a Kubernetes operator for self-hosted large language model inference across heterogeneous GPU fleets supporting NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. It supports runtimes including llama.cpp, vLLM, TGI, and mlx-server, offers multi-GPU sharding, model caching, and OpenAI-compatible endpoints. It is licensed under Apache-2.0 and designed for homelab and on-prem fleet deployment, and is actively developed.
github.com
KerasTuner is a hyperparameter optimization framework for Keras. It provides a define-by-run syntax for configuring search spaces and includes Bayesian Optimization, Hyperband and Random Search algorithms. It requires Python 3.8+ and TensorFlow 2.0+.
github.com
GPyTorch is a Gaussian process library implemented using PyTorch, designed for creating scalable, flexible, and modular Gaussian process models. It performs most inference operations using numerical linear algebra techniques such as preconditioned conjugate gradients, and provides GPU acceleration through matrix-vector-multiplication-based inference. Installation requires Python 3.10 or later, PyTorch 2.4.1 or later, and NumPy 2.0 or later.
github.com
GPT-NeoX is EleutherAI's library for training large-scale language models on GPUs. It builds on NVIDIA's Megatron and adds DeepSpeed techniques plus optimizations. It supports launching via Slurm, MPI and the IBM Job Step Manager, and offers predefined configurations for architectures including Pythia, PaLM, Falcon and LLaMA 1 & 2. The repository states it is likely the wrong library for those not training models with billions of parameters from scratch.
huggingface.co
Tool that estimate is a given text is real or generated by GPT.
magenta.tensorflow.org
Magenta is an open source research project exploring the role of machine learning as a tool in the creative process, focused on art and music. It includes Magenta Studio, a collection of music plugins for Ableton Live, and Magenta RealTime 2, an open model and real-time neural synthesis engine.
github.com
FastEdit is a repository intended to help developers inject fresh and customized knowledge into large language models using one command. It supports models including GPT-J, LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, and InternLM. The implemented algorithm is Rank-One Model Editing (ROME). It requires Python 3.8+ and PyTorch 1.13.1+.
ernie.baidu.com
ERNIE is Baidu's blog covering its model releases. Posts describe ERNIE 5.1, a model trained with disaggregated fully-asynchronous reinforcement learning and scaled agentic post-training, and ERNIE 5.0, a 2.4 trillion-parameter unified multimodal model trained from scratch that integrates text, image, video and audio in a single autoregressive framework. ERNIE-Image is a text-to-image generation model built on a single-stream Diffusion Transformer.
distill.pub
Distill publishes articles about machine learning, including peer-reviewed explanations of neural network topics such as graph neural networks, feature visualization and feature-wise transformations. In a July 2, 2021 editorial, the team announced that after five years Distill would be taking a break.
github.com
Datumbox is an open-source machine learning framework written in Java for rapid development of machine learning and statistical applications. It focuses on including many machine learning algorithms and statistical methods and on handling large datasets. The code is licensed under the Apache License, Version 2.0, and releases are available on Maven Central, including version 0.8.2.
theconversation.com
This is an academic analysis article published on The Conversation titled 'ChatGPT, DALL-E 2 and the collapse of the creative process'. It argues that the focus of these AI tools on the framing of artistic tasks fetishizes the creative moment and devalues the work required to develop an idea into a finished creative work.
github.com
Caffe is a deep learning framework developed by Berkeley AI Research and community contributors, designed with expression, speed, and modularity in mind. It is released under the BSD 2-Clause license and includes associated reference models.
github.com
Bloop is a fast code search engine written in Rust, distributed through GitHub releases. The repository was archived by its owner on Jan 2, 2025, and is now read-only. Release notes for versions v0.6.0 to v0.6.5 list changes such as explaining files in a user-set language, adding multiple files to code studio, code coloring for COBOL, and alternative input types for Chinese users.
github.com
AutoKeras is an AutoML library for deep learning built on Keras, developed by DATA Lab at Texas A&M University. The project describes its goal as making machine learning accessible to everyone. It can be installed with pip, and the documentation states it is currently only compatible with Python 3.7 or later and TensorFlow 2.8.0 or later.
The AI Safety Summit 2023 is a global event held on 1 and 2 November at Bletchley Park, Buckinghamshire. It brings together international governments, AI companies, civil society groups and researchers to consider AI risks, especially at the frontier of development, and discuss mitigation through internationally coordinated action.