OpenVLA: An open-source vision-language-action model for robotic manipulation.

Simple tool to allow for HTML visualization of tokenization boundaries.

A simple unified framework for evaluating LLMs

Llama 2 Everywhere (L2E)

Official Implementation for the ICLR2023 paper "Fuzzy Alignments in Directed Acyclic Graph for Non-autoregressive Machine Translation"

Official PyTorch implementation of "Extract Free Dense Labels from CLIP" (ECCV 22 Oral)

A tool for extracting plain text and internal Wikipedia links from Wikipedia dumps

Official Code For TDEER: An Efficient Translating Decoding Schema for Joint Extraction of Entities and Relations (EMNLP 2021)