craigpfeifer

streamlit

Streamlit — A faster way to build and share data apps.

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

pytorch-lightning

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

haystack

:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

pygwalker

PyGWalker: Turn your pandas dataframe into an interactive UI for visual analysis

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

kedro

Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.

dbt-core

dbt enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

aim

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

simpletransformers

Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

phoenix

AI Observability & Evaluation

kenlm

KenLM: Faster and Smaller Language Model Queries

jackson

🔥 Streamline your web application's authentication with Jackson, an SSO service supporting SAML and OpenID Connect protocols. Beyond enterprise-grade Single Sign-On, it also supports Directory Sync via the SCIM 2.0 protocol for automatic user and group provisioning/de-provisioning. 🤩

detext

DeText: A Deep Neural Text Understanding Framework for Ranking and Classification Tasks

pynndescent

A Python nearest neighbor descent for approximate nearest neighbors

docassemble

A free, open-source expert system for guided interviews and document assembly, based on Python, YAML, and Markdown.

bleurt

BLEURT is a metric for Natural Language Generation based on transfer learning.

vectorhub

Vector Hub - Library for easy discovery, and consumption of State-of-the-art models to turn data into vectors. (text2vec, image2vec, video2vec, graph2vec, bert, inception, etc)

ETM

Topic Modeling in Embedding Spaces

acl-anthology

Data and software for building the ACL Anthology.

litdata

Transform datasets at scale. Optimize datasets for fast AI model training.

awesome-tool-llm

annotation-tools

Topic_Modelling_Beyond_Tokens

Investigating into how to extract meaningful topic names from textual data

PAL-A-tool-for-Pre-annotation-and-Active-Learning

PAL: A tool for Pre-annotation and Active Learning

rhapsode

Advanced desktop search/corpus exploration prototype