upunaprosk

BabyBERTa

Source code for CoNLL 2021 paper by Huebner et al. 2021

corpora-manipulation

Tool for converting error corpora to parallel datasets

covid-mgpr-based-model

Code for the research project on Predicting the impacts of intervention strategies on COVID-19 trajectory (Clemson University - Université Clermont Auvergne)

grammar-checker

Essay Grammar Checker trained on REALEC Corpus using SpaCy

la-tda

Code for EACL Workshop paper Can BERT eat RuCoLA? Topological Data Analysis to Explain

quantized-lm-confidence

Code for NAACL paper When Quantization Affects Confidence of Large Language Models?

small-language-models

Code for CoNLL BabyLM workshop Mini Minds: Exploring Bebeshka and Zlata Baby Models

ul2-atelier-data-science

Practical Deep Learning course at the University of Lyon 2

upunaprosk/la-tda

Code for EACL Workshop paper Can BERT eat RuCoLA? Topological Data Analysis to Explain

upunaprosk/grammar-checker

Essay Grammar Checker trained on REALEC Corpus using SpaCy

upunaprosk/ul2-atelier-data-science

Practical Deep Learning course at the University of Lyon 2

upunaprosk/corpora-manipulation

Tool for converting error corpora to parallel datasets

upunaprosk/covid-mgpr-based-model

Code for the research project on Predicting the impacts of intervention strategies on COVID-19 trajectory (Clemson University - Université Clermont Auvergne)

upunaprosk/quantized-lm-confidence

Code for NAACL paper When Quantization Affects Confidence of Large Language Models?

upunaprosk/small-language-models

Code for CoNLL BabyLM workshop Mini Minds: Exploring Bebeshka and Zlata Baby Models

upunaprosk/ADWISER

upunaprosk/AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

upunaprosk/BabyBERTa

Source code for CoNLL 2021 paper by Huebner et al. 2021

upunaprosk/BIG-bench

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

upunaprosk/CNF-DNF-converter

upunaprosk/CoLA

Demo for Grammaticality Judgement (Acceptability) task

upunaprosk/fair-pruning

Code for the paper The Other Side of Compression: Measuring Bias in Pruned Transformers (IDA23)

upunaprosk/Feature_selection-based-on-IFS

Feature selection via intuitionistic fuzzy sets

upunaprosk/grammar-optim

Code and Results for "Universals of word order reflect optimization of grammars for efficient communication"

upunaprosk/Topology_for_BERT_CoLA

Code for Feature Space Analysis from the paper Acceptability Judgements via Examining the Topology of Attention Maps (EMNLP22)

upunaprosk/transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

upunaprosk/writing-assistant

Writing assistant

upunaprosk/evaluation-pipeline

Evaluation pipeline for the BabyLM Challenge 2023.

upunaprosk/label-studio

Label Studio is a multi-type data labeling and annotation tool with standardized output format

upunaprosk/lm-evaluation-harness

A framework for few-shot evaluation of language models.

upunaprosk/moral_stories

Data and code for the "Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences" (Emelin et al., 2021) paper.

upunaprosk/neural-compressor

Provide unified APIs for SOTA model compression techniques, such as low precision (INT8/INT4/FP4/NF4) quantization, sparsity, pruning, and knowledge distillation on mainstream AI frameworks such as TensorFlow, PyTorch, and ONNX Runtime.

upunaprosk/TruthfulQA

TruthfulQA: Measuring How Models Imitate Human Falsehoods

upunaprosk/ul2-nlp-course

NLP for Social Sciences course at the University of Lyon 2