🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies

Multiple paper open-source codes of the Microsoft Research Asia DKI group

distributed trainer for LLMs

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Streamlit Component, for a Chatbot UI

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

This is a demo of a dataframe with editable cells, powered by `streamlit-aggrid` from Pablo Fonseca. You can edit the cells by clicking on them and then export your selection to a csv file! 🎈

Entity Linker solution

PICARD - Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models

Autoregressive Entity Retrieval

Source code for Grounded Adaptation for Zero-shot Executable Semantic Parsing

Semantic parsers based on encoder-decoder framework

Neural Machine Translation on the Nepali-English language pair

novel deep learning research works with PaddlePaddle

This repository contains source code for the TaBERT model, a pre-trained language model for learning joint representations of natural language utterances and (semi-)structured tables for semantic p…

A relation-aware semantic parsing model from English to SQL

Python library for computing edit distance between arbitrary Python sequences.