gsarti / it5Links
Materials for "IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation" ๐ฎ๐น
โ30Updated 11 months ago
Alternatives and similar repositories for it5
Users that are interested in it5 are comparing it to the libraries listed below
Sorting:
- A monolingual and cross-lingual meta-embedding generation and evaluation frameworkโ80Updated 3 years ago
- Explainable Zero-Shot Topic Extractionโ62Updated 9 months ago
- A Python library aimed at dissecting and augmenting NER training data.โ58Updated 2 years ago
- A library to synthesize text datasets using Large Language Models (LLM)โ151Updated 2 years ago
- A spaCy custom component that extracts and normalizes temporal expressionsโ54Updated 2 years ago
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.โ93Updated 2 years ago
- Load What You Need: Smaller Multilingual Transformers for Pytorch and TensorFlow 2.0.โ102Updated 3 years ago
- classy is a simple-to-use library for building high-performance Machine Learning models in NLP.โ87Updated last month
- ๐ฎ๐น Italian BERT and ELECTRA models (incl. evaluation)โ18Updated 2 years ago
- A python package to run inference with HuggingFace language and vision-language checkpoints wrapping many convenient features.โ27Updated 8 months ago
- Bi-encoder entity linking architectureโ46Updated 8 months ago
- Alternate Implementation for Zero Shot Text Classification: Instead of reframing NLI/XNLI, this reframes the text backbone of CLIP modelsโฆโ36Updated 3 years ago
- Examples for aligning, padding and batching sequence labeling data (NER) for use with pre-trained transformer modelsโ65Updated 2 years ago
- โ22Updated 3 years ago
- Augmenty is an augmentation library based on spaCy for augmenting texts.โ155Updated last year
- Repository for the paper "MultiNERD: A Multilingual, Multi-Genre and Fine-Grained Dataset for Named Entity Recognition (and Disambiguatioโฆโ44Updated last year
- Tutorial to pretrain & fine-tune a ๐ค Flax T5 model on a TPUv3-8 with GCPโ58Updated 2 years ago
- โ35Updated 3 years ago
- German small and large versions of GPT2.โ20Updated 3 years ago
- ๐ ๏ธ Tools for Transformers compression using PyTorch Lightning โกโ83Updated 6 months ago
- Source code and data for Like a Good Nearest Neighborโ29Updated 4 months ago
- A python package for benchmarking interpretability techniques on Transformers.โ212Updated 8 months ago
- Recon NER, Debug and correct annotated Named Entity Recognition (NER) data for inconsistencies and get insights on improving the quality โฆโ106Updated last year
- โ43Updated 2 years ago
- KIND: an Italian Multi-Domain Dataset for Named Entity Recognitionโ15Updated last year
- ๐ค Disaggregators: Curated data labelers for in-depth analysis.โ66Updated 2 years ago
- ๐ซ SpaCy wrapper for ConceptNet ๐ซโ93Updated last year
- Using short models to classify long textsโ21Updated 2 years ago
- negate_sentence(A Python module that doesn't negate sentences.)โ31Updated 7 months ago
- โ13Updated 2 years ago