projecte-aina/FLOR-6.3B

Text Generation • Updated Sep 25 • 260 • 32

Note Bloom-based foundational model

projecte-aina/DEBERTA_CIEL

Token Classification • Updated May 28 • 2

Note deBERTA base model pretrained for NERC on Catalan Entity Identification and Linking (CEIL) dataset projecte-aina/ceil

projecte-aina/roberta-base-ca-v2

Fill-Mask • Updated Dec 23, 2022 • 827 • 4

Note Transformer-based masked language model for the Catalan language based on the RoBERTA base model

projecte-aina/longformer-base-4096-ca-v2

Fill-Mask • Updated Dec 15, 2022 • 18

Note Longformer version of the roberta-base-ca-v2 masked language model for the Catalan language

projecte-aina/aguila-7b

Text Generation • Updated Jan 31 • 6.18k • 57

Note Foundational model, based on Falcon 7b with continuous pretraining with further ES and CA tokens

projecte-aina/roberta-large-ca-v2

Fill-Mask • Updated Dec 23, 2022 • 4

Note Pretrained RoBERTA large model for Catalan

projecte-aina/multiner_ceil

Token Classification • Updated May 28 • 10

Note RoBerta large model pretrained for NERC on Catalan Entity Identification and Linking (CEIL) dataset projecte-aina/ceil

projecte-aina/roberta-base-ca-v2-cased-te

Text Classification • Updated Nov 30, 2022 • 32

Note Textual Entailment model for the Catalan language fine-tuned from the roberta-base-ca-v2 model

projecte-aina/roberta-base-ca-cased-pos

Token Classification • Updated Nov 16, 2022 • 16

Note Part-of-speech-tagging (POS) model for the Catalan language fine-tuned from the roberta-base-ca model

projecte-aina/roberta-base-ca-v2-cased-pos

Token Classification • Updated Nov 30, 2022 • 13 • 1

Note Part-of-speech-tagging (POS) model for the Catalan language fine-tuned from the roberta-base-ca-v2 model

projecte-aina/ST-NLI-ca_paraphrase-multilingual-mpnet-base

Sentence Similarity • Updated Nov 7, 2023 • 1.6k • 1

Note Sentence-transformers model: It maps sentences and paragraphs to a 768 dimensional dense vector space

projecte-aina/roberta-base-ca-cased-ner

Token Classification • Updated Apr 11 • 33 • 1

Note Named Entity Recognition (NER) model for the Catalan language fine-tuned from the BERTa model

projecte-aina/roberta-base-ca-v2-cased-ner

Token Classification • Updated Apr 11 • 14

Note Named Entity Recognition (NER) model for the Catalan language fine-tuned from the roberta-base-ca-v2 model

projecte-aina/roberta-base-ca-cased-sts

Text Classification • Updated Nov 16, 2022 • 156

Note Semantic Textual Similarity model for the Catalan language fine-tuned from the roberta-base-ca model

projecte-aina/roberta-large-ca-v2-massive

Text Classification • Updated Dec 30, 2022 • 58 • 1

Note Intent Classification model for the Catalan language fine-tuned from the roberta-large-ca-v2 model

projecte-aina/roberta-base-ca-cased-tc

Text Classification • Updated Nov 16, 2022 • 50 • 1

Note Text Classification model for the Catalan language fine-tuned from the roberta-base-ca model

projecte-aina/roberta-base-ca-v2-cased-qa

Question Answering • Updated Nov 16, 2022 • 44 • 1

Note Question Answering model for the Catalan language fine-tuned from the roberta-base-ca-v2 model

projecte-aina/roberta-base-ca-v2-cased-tc

Text Classification • Updated Nov 28, 2022 • 18 • 1

Note Text Classification model for the Catalan language fine-tuned from the roberta-base-ca-v2 model

projecte-aina/roberta-base-ca-v2-cased-sts

Text Classification • Updated Nov 16, 2022 • 30

Note Semantic Textual Similarity model for the Catalan language fine-tuned from the roberta-base-ca-v2 model

projecte-aina/roberta-large-ca-paraphrase

Text Classification • Updated Nov 18, 2022 • 18

Note Paraphrase Detection model for the Catalan language fine-tuned from the roberta-large-ca-v2 model

projecte-aina/distilroberta-base-ca-v2

Fill-Mask • Updated Jul 11, 2023 • 14

Note Distilled version of projecte-aina/roberta-base-ca-v2

projecte-aina/roberta-base-ca-cased-te

Text Classification • Updated Nov 17, 2022 • 16

Note Textual Entailment model for the Catalan language fine-tuned from the roberta-base-ca model

projecte-aina/roberta-base-ca-v2-cawikitc

Zero-Shot Classification • Updated Jun 19, 2023 • 23 • 1

Note Zero-Shot Text Classification model in Catalan created by fine-tuning RoBERTa-base-ca-v2 with a classification dataset, CaWikiTC, reformulated as entailment

projecte-aina/roberta-base-ca-cased-qa

Question Answering • Updated Nov 16, 2022 • 76

Note Question Answering model for the Catalan language fine-tuned from the roberta-base-ca model

projecte-aina/roberta-base-ca-v2-cased-wikicat-ca

Text Classification • Updated Nov 28, 2022 • 20

Note Text Classification model for the Catalan language fine-tuned from the roberta-base-ca-v2 model

projecte-aina/roberta-base-ca-v2-massive

Text Classification • Updated Jan 13, 2023 • 14 • 1

Note Intent Classification model for the Catalan language fine-tuned from the roberta-base-ca-v2 model

projecte-aina/FLOR-1.3B-Instructed

Text Generation • Updated Mar 19 • 54

Note Text generation