Irina Proskurina's repositories
grammar-checker
Essay Grammar Checker trained on REALEC Corpus using SpaCy
ul2-atelier-data-science
Practical Deep Learning course at the University of Lyon 2
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)
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
AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
BIG-bench
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
CoLA
Demo for Grammaticality Judgement (Acceptability) task
fair-pruning
Code for the paper The Other Side of Compression: Measuring Bias in Pruned Transformers (IDA23)
Feature_selection-based-on-IFS
Feature selection via intuitionistic fuzzy sets
grammar-optim
Code and Results for "Universals of word order reflect optimization of grammars for efficient communication"
Topology_for_BERT_CoLA
Code for Feature Space Analysis from the paper Acceptability Judgements via Examining the Topology of Attention Maps (EMNLP22)
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
writing-assistant
Writing assistant
evaluation-pipeline
Evaluation pipeline for the BabyLM Challenge 2023.
label-studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
moral_stories
Data and code for the "Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences" (Emelin et al., 2021) paper.
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.
TruthfulQA
TruthfulQA: Measuring How Models Imitate Human Falsehoods
ul2-nlp-course
NLP for Social Sciences course at the University of Lyon 2