feyzaakyurek

seq_icl

ERASE

Code and Data for "Language Modeling with Editable External Knowledge"

MOSS-RLHF

MOSS-RLHF

Megatron-LM

Ongoing research training transformer models at scale

memit

Mass-editing thousands of facts into a transformer memory (ICLR 2023)

ViLMA

ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models (ICLR 2024, Official Implementation)

GRACE

[NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

knowledge_distillation

Repository for "Propagating Knowledge Updates to LMs Through Distillation" (NeurIPS 2023).

al-folio

A beautiful, simple, clean, and responsive Jekyll theme for academics

faiss

A library for efficient similarity search and clustering of dense vectors.

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

MQuAKE

[EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

Platypus

Code for fine-tuning Platypus fam LLMs using LoRA

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

ecbd

serac

Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

deprem_openai_apis

Extract addresses and intents from tweet texts

ThoughtSource

A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

google-research

Google Research

RL4LMs

A modular RL library to fine-tune language models to human preferences

rank_bm25

A Collection of BM25 Algorithms in Python

GEM-metrics

Automatic metrics for GEM tasks

CodeT

t5x

interscript

The InterScript dataset contains interactive user feedback on scripts generated by a T5-XXL model.

bandit-qa

Code for Simulating Bandit Learning from User Feedback for Extractive Question Answering.

influence

Influence Experiments

lexical

Paper: Lexicon Learning for Few-Shot Neural Sequence Modeling