LLM training in simple, raw C/CUDA

ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution

The best ChatGPT that $100 can buy.

A collection of benchmarks and datasets for evaluating LLM.

Align Anything: Training All-modality Model with Feedback

The most recent documentation of OpenReview

Embodied Agent Interface (EAI): Benchmarking LLMs for Embodied Decision Making (NeurIPS D&B 2024 Oral)

SSRL: Self-Search Reinforcement Learning

Heuristic Analysis for NLI Systems

A library for mechanistic interpretability of GPT-style language models

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

Train transformers on synthetic graph search problems to measure their scaling behavior and to do mechanistic analysis.

SemEval-2023 - Visual-WSD: Visual Word Sense Disambiguation (Visual-WSD)

A recipe for online RLHF and online iterative DPO.

The main repo for NLWeb, implemented in Python.

Revisiting Natural Language Understanding with Large Language Models

Arena-Hard-Auto: An automatic LLM benchmark.

A Semantic Parsing Toolkit for English utterances to ULKB

Natural language understanding by probabilistic abduction of a symbolic theory from sentences and logical forms.

Decision making under uncertainty using the POMDPs.jl ecosystem taught by Robert Moss

A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".

Educational resources

Non-finished examples

Kullback-Leibler projections for Bayesian model selection in Python

BAyesian Model-Building Interface (Bambi) in Python.

Formulas for mixed-effects models in Python