3D LEGO models and mosaics from images using R and #tidyverse

AI Logging for Interpretability and Explainability🔬

LLM training code for Databricks foundation models

A Survey on Data Selection for Language Models

vietnews dataset for vietnamese summarization benchmark

Probabilistic programming with HuggingFace language models

[ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.

Apéro is a Hugo theme for personal websites. A Hugo theme you'll want to hang out with 🌌 . This is the source for the theme files to install.

Mamba SSM architecture

Fine-tune mistral-7B on 3090s, a100s, h100s

Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from easy questions to hard

OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.

[ASE 2023] Software Entity Recognition with Noise-Robust Learning

Gram2Vec is a document embedding algorithm that embeds documents into a higher dimensional space based off grammatical style.

[ACL 2023] Explanation-based Finetuning Makes Models More Robust to Spurious Correlation

Syntax Regex Matcher is a package for applying regular expressions to parse trees to look for syntactic constructions in English sentences

Multilingual syllable annotation pipeline component for spacy

The original Backpack Language Model implementation, a fork of FlashAttention

In-context Example Selection with Influences

Learning to Compress Prompts with Gist Tokens - https://arxiv.org/abs/2304.08467

Fast & Simple repository for pre-training and fine-tuning T5-style models

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

A PyTorch implementation of Multimodal Few-Shot Learning with Frozen Language Models with OPT.

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Few-shot Learning of GPT-3

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

Source code for paper "Learning from Noisy Labels for Entity-Centric Information Extraction", EMNLP 2021

Code for paper "CrossFit 🏋️: A Few-shot Learning Challenge for Cross-task Generalization in NLP" (https://arxiv.org/abs/2104.08835)