Alignment Lab AI's Projects
Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
Natural Language Processing Best Practices & Examples
notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references under the /Resources folder.
Stampy's copy of Alignment Research Dataset scraper
A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.
AICI: Prompts as (Wasm) Programs
AIOS: LLM Agent Operating System
PygmalionAI's large-scale inference engine
Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
Convert Compute And Books Into Instruct-Tuning Datasets
We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.
This repository provides a comprehensive set of tools for audio diarization, transcription, and dataset management. It leverages state-of-the-art models like Whisper, NeMo, and wav2vec2 to achieve accurate results.
Label, clean and enrich text datasets with LLMs.
automated ljspeech dataset generation for tts models
A Python program that tries to prove a statement given a set of propositions in first order logic.
AutoNL - Natural Language Automation tool
👩💻👨💻 Awesome cheatsheets for popular programming languages, frameworks and development tools. They include everything you should know in one single file.
Go ahead and axolotl questions
An implementation of base85 encoding, which is more space-efficient than base64
Mapping spatiotemporal patterns in an online and continuous fashion
A massively parallel, high-level programming language
Beyond Language Models: Byte Models are Digital World Simulators
Domains Blacklist for Squid-Cache