A data construction and evaluation framework to quantify privacy norm awareness of language models (LMs) and emerging privacy risk of LM agents. (NeurIPS 2024 D&B)

LLM training in simple, raw C/CUDA

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Code for Quiet-STaR

High-performance In-browser LLM Inference Engine

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

Resource, Evaluation and Detection Papers for ChatGPT

Large Language Model Text Generation Inference

Accessible large language models via k-bit quantization for PyTorch.

A Python module for getting the GPU status from NVIDA GPUs using nvidia-smi programmically in Python

S2ORC: The Semantic Scholar Open Research Corpus: https://www.aclweb.org/anthology/2020.acl-main.447/

A high-throughput and memory-efficient inference and serving engine for LLMs

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

Interact with your documents using the power of GPT, 100% privately, no data leaks

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

[ICLR 2024 & NeurIPS 2023 WS] An Evaluator LM that is open-source, offers reproducible evaluation, and inexpensive to use. Specifically designed for fine-grained evaluation on a customized score ru…

DSPy: The framework for programming—not prompting—foundation models

✌[ICLR 2024] Class Incremental Learning via Likelihood Ratio Based Task Prediction

[ACL 2023] Class-Incremental Learning based on Label Generation

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

A hyperparameter optimization framework

An Extensible Continual Learning Framework Focused on Language Models (LMs)

[EMNLP 2022] Adapting a Language Model While Preserving its General Knowledge

Data augmentation for NLP

[EMNLP 2022] Continual Training of Language Models for Few-Shot Learning

Code for ECML-PKDD 2022 Paper --- CMG: A Class-Mixed Generation Approach to Out-of-Distribution Detection

A Unified Library for Parameter-Efficient and Modular Transfer Learning