marcopoli / LLaMAntino-3-ANITALinks
The ๐ANITA project๐ *(Advanced Natural-based interaction for the ITAlian language)* wants to provide Italian NLP researchers with an improved model the for Italian Language ๐ฎ๐น use cases.
โ22Updated 11 months ago
Alternatives and similar repositories for LLaMAntino-3-ANITA
Users that are interested in LLaMAntino-3-ANITA are comparing it to the libraries listed below
Sorting:
- A multi-lingual approach to AllenNLP CoReference Resolution along with a wrapper for spaCy.โ107Updated last year
- A collection of Italian benchmarks for LLM evaluationโ30Updated 3 months ago
- Annotated corpus + evaluation metrics for text anonymisationโ61Updated last month
- Attribute statements generated by LLMs to preceding tokens using attention weights.โ17Updated 4 months ago
- Camoscio: An Italian instruction-tuned language model based on LLaMAโ127Updated last year
- A large scale dataset for Question Answering in Italianโ27Updated 6 years ago
- A collection of datasets for language model pretraining including scripts for downloading, preprocesssing, and sampling.โ60Updated last year
- A python package for benchmarking interpretability techniques on Transformers.โ214Updated 11 months ago
- A software for transferring pre-trained English models to foreign languagesโ18Updated 2 years ago
- A Python library aimed at dissecting and augmenting NER training data.โ58Updated 2 years ago
- Word Sense Linking model is designed to identify and disambiguate spans of text to their most suitable senses from a reference inventory.โ13Updated last year
- Sentiment analysis and emotion classification for Italian using BERT (fine-tuning). Published at the WASSA workshop (EACL2021).โ27Updated last year
- Efficiently find the best-suited language model (LM) for your NLP taskโ127Updated last month
- Dataset from the paper "Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering" (COLING 2022)โ114Updated 2 years ago
- โ39Updated last year
- ๐ซ SpaCy wrapper for ConceptNet ๐ซโ93Updated 2 years ago
- KIND: an Italian Multi-Domain Dataset for Named Entity Recognitionโ15Updated 2 years ago
- Fact checking baseline combining dense retrieval and textual entailmentโ30Updated 3 weeks ago
- A Python package to compute HONEST, a score to measure hurtful sentence completions in language models. Published at NAACL 2021.โ20Updated 4 months ago
- UmBERTo: an Italian Language Model trained with Whole Word Masking.โ106Updated 2 years ago
- This repository provides scripts for evaluating NLP models on the LEXTREME benchmark, a set of diverse multilingual tasks in legal NLPโ22Updated last year
- Public repository for SemEval 2023 - Task 10 - Explainable Detection of Online Sexism (EDOS)โ23Updated 2 years ago
- Repository collecting resources and best practices to improve experimental rigour in deep learning research.โ27Updated 2 years ago
- Full named-entity (i.e., not tag/token) evaluation metrics based on SemEvalโ13โ186Updated this week
- The robust European language model benchmark.โ120Updated this week
- โ53Updated last year
- โ169Updated last year
- SciRepEval benchmark training and evaluation scriptsโ75Updated last year
- โ57Updated 2 months ago
- This repository provides the source code used to automatically generate the book summarization datasets described in the paper titled "Ecโฆโ11Updated 4 months ago