huu4ontocord

MDEL

Multi-Domain Expert Learning

rio

Text pre-processing for NLP datasets

aurora

Multilingual, Multimodal, Multidomain model based on Starcoderplus and Bakllava

muliwai

experimental PII framework

KeyedVectorsANN

Genism word2vec + Pysparnn ANN + Trimmed GoogleNewsVec = Fast and lightweight NLP tool

sungai

Sample multilingual data and tools for creating the data - used for NLP multilingual NLP research

aurora-m

Adapting Starcoderplus for Multimodal Experts

M3rlin

Multilingual, Multimodal, Multidomain (M3) Model

M3rlin-fmengine

M3 Training Using FMengine

create_pii_dataset

data_tool_experiments

data_tooling

How should we store and serve the dataset?

hpj.py

Simple Python to Javascript translator with an emphasis on readability of generated code.

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

neox_alpaca_generate

oftf

One File Text Filter

pii_processing

PII Processing code to clean up BigScience datasets. Reference implementation for the PII Hackathon

summarize

Summarize. is a Streamlit application that performs automatic text summarization using both extractive and abstractive models.

tevatron

Tevatron - A flexible toolkit for dense retrieval research and development.

Viet-Mistral

Vietnamese Mistral