Alignment Lab AI's repositories
KnowledgeBase
never forget anything again! combine AI and intelligent tooling for a local knowledge base to track catalogue, annotate, and plan for you!
Dataset-Conversion-Toolkit
a set of scripts to easily convert all training data from huggingface into alpaca instruct or sharegpt format, which should allow for ease of use with any trainer
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.
PythonProgrammingPuzzles
A Dataset of Python Challenges for AI Research
aphrodite-engine
PygmalionAI's large-scale inference engine
axolotl
Go ahead and axolotl questions
openchat
OpenChat: Advancing Open-source Language Models with Imperfect Data
autolabel
Label, clean and enrich text datasets with LLMs.
Bend
A massively parallel, high-level programming language
EETQ
Easy and Efficient Quantization for Transformers
ELLA
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
function-sampler
Logit Sampler for Function calling LM's. Making it probabilistically impossible to generate incorrect function calls!
GraphScope
🔨 🍇 💻 🚀 GraphScope: A One-Stop Large-Scale Graph Computing System from Alibaba | 一站式图计算系统
JARVIS
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
knowledge-graph-generator
Knowledge Graph Generator app
llm-transparency-tool
LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo
morphic
An AI-powered search engine with a generative UI
parler-tts
Inference and training library for high-quality TTS models.
Preft-data-claude
a short script to create preference data with claude
prompt2model
prompt2model - Generate Deployable Models from Natural Language Instructions
pyreason
An explainable inference software supporting annotated, real valued, graph based and temporal logic
pyreft
ReFT: Representation Finetuning for Language Models
revideo
Create Videos with Code
rho
Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.
stackexchanger
stackexchange data from datadumps made easy
WizardLM
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath