Minimalistic large language model 3D-parallelism training

Github implementation of https://reports.chatclimate.ai/

This repository contains the code for the paper "Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering".

Code for DSTC9 Track 1 - Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access.

distributed trainer for LLMs

Lightweight Variant of RETURNN

DSTC11 Track 5 - Task-oriented Conversational Modeling with Subjective Knowledge

Official code for 3ML (EMNLP 2022)

Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.

Code for the paper "Does Joint Training Really Help Cascaded Speech Translation?" (EMNLP 2022)

Bundle Python executable with preloaded modules

Switchboard Named Entity Corpus

Open, modular controller platform for portafilter espresso machines

An elaborate and exhaustive paper list for Named Entity Recognition (NER)

SeqScore: Scoring for named entity recognition and other sequence labeling tasks

Self-Supervised Speech Pre-training and Representation Learning Toolkit

Sisyphus recipies for ASR

DSTC10 Track 2 - Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

experiments with RETURNN

LUKE -- Language Understanding with Knowledge-based Embeddings

Papers & presentation materials from Hugging Face's internal science day

The RWTH extensible training framework for universal recurrent neural networks