alignment-lab-ai Goto Github PK

ai-easy

Natural Language Processing Best Practices & Examples

ai-notes

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.

aici

AICI: Prompts as (Wasm) Programs

aios

AIOS: LLM Agent Operating System

alignmentlab.ai

aphrodite-engine

PygmalionAI's large-scale inference engine

audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

augmentation-station

augmentoolkit

Convert Compute And Books Into Instruct-Tuning Datasets

autodiarize

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.

autoljspeech

automated ljspeech dataset generation for tts models

automated-interpretability

autometicassistant

autonl

AutoNL - Natural Language Automation tool

axolotl

Go ahead and axolotl questions

babelcode

bgpt

Beyond Language Models: Byte Models are Digital World Simulators

bigcode-dataset

blog

brain_autorl

causal-agents

causaltransfer

Repository containing code for Counterfactual Augmentation/Causal Transfer Learning.

chat-llamaindex

codemixed-text-generator

This tool helps automatic generation of grammatically valid synthetic Code-mixed data by utilizing linguistic theories such as Equivalence Constant Theory and Matrix Language Theory.

coderanker

Fault-aware neural code rankers

coderec_programming_states

Code and Data for: Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming

codexglue

CodeXGLUE

coml

Interactive coding assistant for data scientists and machine learning developers, empowered by large language models.

ctgcn-code

Code for the scalable generation of causal graph neural network representations

dads

Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.