alignment-lab-ai Goto Github PK

r_u_sure

Code accompanying the paper "R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents"

reagent

A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)

rome

Locating and editing factual associations in GPT (NeurIPS 2022)

rulesengine

A Json based Rules Engine with extensive Dynamic expression support

self-organising-systems

semanticflowgraph

Semantic flow graphs for data science

sgpt

SGPT: GPT Sentence Embeddings for Semantic Search

smore

sonar

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

sparse_autoencoder

swiftrank

Compact, ultra-fast SoTA reranker enhancing retrieval pipelines and terminal applications.

synthetic-data-generators

various scripts im using to generate data for a few puposes. example uses and functionality should be commented at the bottom of each. would not mind prs with similar scripts to add to the pile

t5x

task-oriented-dialogue

taskweaver

A code-first agent framework for seamlessly planning and executing data analytics tasks.

temporian

Temporian is an open-source Python library for preprocessing ⚡ and feature engineering 🛠 temporal data 📈 for machine learning applications 🤖

tensorrt

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

text-to-logicform

Text-to-LogicForm is a simple code for leveraging a syntactic graph for semantic parsing using a nov

textbook

distill chatGPT coding ability into small model (1b)

tracecodegen

translation-starter

triton

Development repository for the Triton language and compiler

ulkb

A HOL-based framework for reasoning over knowledge graphs

unisim

UniSim is a package for efficient similarity computation, fuzzy matching, and clustering of data.

vaem

Sample code for VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data

visualblocks

Visual Blocks for ML is a Google visual programming framework that lets you create ML pipelines in a no-code graph editor. You – and your users – can quickly prototype workflows by connecting drag-and-drop ML components, including models, user inputs, processors, and visualizations.

vmf_embeddings

weak-to-strong

wikicausal

WikiCausal: Corpus and Task for Evaluation of Causal Knowledge Graph Construction

world_models