medium.datadriveninvestor.com
Post by Travis Tang from DataDrivenInvestor.
Directory
Search results
Published directory entries matching your search.
anyword.com
Anyword is a generative AI content platform and performance API for go-to-market teams. It adds A/B-tested data and brand context to prompts and works with any AI model or application. The platform includes a data-driven editor, content intelligence, brand voice features, and integrations with marketing channels such as Google Ads, Meta, and LinkedIn.
github.com
BayesO is a Python framework for Bayesian optimization, described as a simple but essential Bayesian optimization package. It is installed via pip and is tested on Python 3.8 through 3.12. The repository includes documentation, examples and tests, and is released under the MIT License.
featuredgpts.com
Featured GPTs is a curated directory of custom GPTs for use with ChatGPT. It lists the top 1% of hand-picked, tested custom GPTs from the official GPT store, with content updated daily. Example listed GPTs include Video Summarizer and Midjourney Prompt Generator.
microsoft.com
Microsoft Research publication proposing 18 generally applicable design guidelines for human-AI interaction. The guidelines were validated through evaluation rounds, including a user study with 49 design practitioners who tested them against 20 AI-infused products. The authors state the guidelines can serve as a resource for practitioners designing AI applications and for researchers developing interaction design guidelines.
github.com
A Clojure wrapper for deeplearning4j with added syntactic sugar, aiming to provide a declarative API for machine learning on the JVM. It translates Clojure keywords into Java method calls, making many deeplearning4j configuration options accessible. The project is a work in progress, and configurations have been tested on basic feedforward nets, RNNs and CNNs.
github.com
pyhsmm is a Python library for approximate unsupervised inference in Bayesian Hidden Markov Models and explicit-duration Hidden semi-Markov Models, focusing on the HDP-HMM and HDP-HSMM with weak-limit approximations. Extensions include autoregressive models, switching linear dynamical systems and factorial models. The package is stated as no longer maintained and was last tested with Python 3.7.
sciruby.com
SciRuby is a project providing tools for scientific computing and data visualization in Ruby. Its releases include NMatrix, a linear algebra library with dense and sparse matrix storage and tensor support, alongside visualization and statistics gems. The project describes itself as currently alpha, and it notes its gems are tested but not battle-hardened. SciRuby and NMatrix are available under the BSD three-clause license.
github.com
A pure Rust tokenizer library that reads tokenizers directly from GGUF model files, requiring no Python, C++ or separate tokenizer files. It supports SPM, BPE, WPM, RWKV and UGM tokenizers tested token-for-token against llama.cpp, and offers batch encoding with optional Rayon parallelism. MIT licensed.
github.com
Stemmer is an English Porter2 stemming implementation in Elixir. It reduces inflected or derived words to their stem, base or root form. The Stemmer.stem/1 function accepts a single word, a sentence, or a list of words. It is tested against the official diffs.txt file containing more than 29000 words.