Stars
[NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models
BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
A library for advanced large language model reasoning
Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models
Anthropic's educational courses
Official Code Repository for the paper "Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes" (ICML 2024).
Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"
[EMNLP 2024] Official implementation of "Investigating How Large Language Models Leverage Internal Knowledge to Perform Complex Reasoning"
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
User-friendly WebUI for AI (Formerly Ollama WebUI)
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.
Code for the paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
Benchmarking LLMs with Challenging Tasks from Real Users
Online Adaptation of Language Models with a Memory of Amortized Contexts (NeurIPS 2024)
Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions
OpenAI Triton Implementation of Streaming LLM
Confidence interval computation for evaluation in machine learning using the bootstrapping approach
A guidance language for controlling large language models.
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.
A library for generative social simulation
Democratizing Internet-scale financial data.
[NeurIPS'23 Spotlight] Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance (LPS), in PyTorch
XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech (INTERSPEECH 2023)
Multilingual G2P in 100 languages
Customizable implementation of the self-instruct paper.