Sampo Pyysalo (spyysalo)

spyysalo

Geek Repo

Company:University of Turku

Github PK Tool:Github PK Tool


Organizations
nlplab
restful-open-annotation
TsujiiLaboratory
UniversalDependencies

Sampo Pyysalo's repositories

lumi-llm-scaling

Scripts and documentation on scaling large language model training on the LUMI supercomputer

Language:ShellLicense:MITStargazers:10Issues:1Issues:0

dl-binf-summer-school-2023

Material for 2023 Summer School on Applied Deep Learning in Bioinformatics

Language:Jupyter NotebookLicense:MITStargazers:8Issues:2Issues:0

keras-bert-ner

Named entity recognition built on top of BERT and keras-bert.

Language:PythonLicense:MITStargazers:4Issues:2Issues:4

warc-tools

Tools for working with Web ARChive files.

Language:PythonLicense:MITStargazers:2Issues:2Issues:0

consensus-pipeline

Annotation consensus processing pipeline

Language:Jupyter NotebookLicense:MITStargazers:1Issues:2Issues:0

finnish-natural-instructions

Tools and data for a Finnish machine translation of Natural Instructions (https://github.com/allenai/natural-instructions)

Language:PythonLicense:MITStargazers:1Issues:1Issues:0

generative-lm-server

Simple generative language model service

Language:CSSLicense:MITStargazers:1Issues:1Issues:0

instruction-finetune

Finetune language model on instruction data

Language:PythonLicense:MITStargazers:1Issues:1Issues:0

lm-text-correction

Text correction using a language model

Language:PythonLicense:MITStargazers:1Issues:2Issues:0

pdftools

Tools for working with PDF documents

Language:PythonLicense:MITStargazers:1Issues:2Issues:0

string-db-tools

Tools for working with STRING database text mining data

Language:PythonLicense:MITStargazers:1Issues:3Issues:0

torch-transformers-text-classifier

Simple text classifier using Transformers with the Torch backend.

Language:PythonLicense:MITStargazers:1Issues:0Issues:0

bert-span-classifier

Text span classifier using BERT

Language:PythonLicense:MITStargazers:0Issues:0Issues:0
Language:Jupyter NotebookStargazers:0Issues:2Issues:0

databricks-dolly-translation

Translation of Databricks Dolly instruction dataset

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

gendemo

Minimal text generation demo using transformers

Language:CSSLicense:MITStargazers:0Issues:0Issues:0

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

gutenberg-tools

Tools for working with Project Gutenberg texts (https://www.gutenberg.org/)

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

instruction-generation

Tools for generating instruction data

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

lumi-causal-lm-finetune

Tools for finetuning large causal language models on LUMI

License:MITStargazers:0Issues:0Issues:0

Megatron-DeepSpeed

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

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

Megatron-LM

Ongoing research training transformer models at scale

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

mt-quality-assessment

Tools and resources for learning to predict machine translation quality

License:MITStargazers:0Issues:0Issues:0

nanotron

Minimalistic large language model 3D-parallelism training

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

ni-to-chatml

Generate ChatML from Natural Instructions data

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

onion-tools

Tools for text deduplication using the onion (ONe Instance ONly) tool

Language:PythonLicense:MITStargazers:0Issues:2Issues:0

paraphrase-generation

Tools and resources for training causal language model for paraphrase generation

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

suomi24-corpus

Tools for working with the Suomi24 corpus

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

taggedpdf

Tools for working with tagged PDF documents

Language:PythonLicense:MITStargazers:0Issues:2Issues:0

xling-instructions

Generate instruction-formatted data from translation pairs

Language:PythonLicense:MITStargazers:0Issues:0Issues:0