Bryan-Romas-Bose

void

NeMo-Curator

Scalable data pre processing and curation toolkit for LLMs

ai-review-ingestion

brickflow

Pythonic Programming Framework to orchestrate jobs in Databricks Workflow

guidance

A guidance language for controlling large language models.

sglang

SGLang is a fast serving framework for large language models and vision language models.

autolabel

Label, clean and enrich text datasets with LLMs.

dspy

DSPy: The framework for programming—not prompting—foundation models

vllm

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

outlines

Structured Text Generation

ollama

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

litellm

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

opentelemetry-python-contrib

OpenTelemetry instrumentation for Python modules

phoenix

AI Observability & Evaluation

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

human-learn

Natural Intelligence is still a pretty good idea.

bulk

A Simple Bulk Labelling Tool

tpot

A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.

bricks

Open-source natural language enrichments at your fingertips.

ludwig

Low-code framework for building custom LLMs, neural networks, and other AI models

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

scrubadub_spacy

Clean personally identifiable information from dirty dirty text using spaCy.

project-menu

See the issue board for the current status of active and prospective projects!

statcheck

A spellchecker for statistics

Data-Whisperer

An NLP text to vizualization builder for Tableau.

ecco

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).

Palmetto

Palmetto is a quality measuring tool for topics

dejavu

Audio fingerprinting and recognition in Python

BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.