datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
corpus_embeddings_multilingual-e5-large-instructjusticio-BOE-A-1978-31229-constitucion-by-articles-qa-multilingual-e5-large-groq_llama3_70b-sas
Dataset summary
It is an end-to-end evaluation dataset (using SAS metric) for Justicio.
Domain: Legal, Law, Spanish Constitution
Language: Spanish
SAS summary
The concept of Semantic Answer Similarity refers to the evaluation of the semantic similarity between the generated answer and the ground truth. The score ranges from 0 to 1. A higher score indicates a better match between the generated answer and the ground truth.
Justicio summary
Justicio is a… See the full description on the dataset page: https://huggingface.co/datasets/dariolopez/justicio-BOE-A-1978-31229-constitucion-by-articles-qa-multilingual-e5-large-groq_llama3_70b-sas.justicio-BOE-A-1978-31229-constitucion-by-articles-qa-multilingual-e5-large-groq_llama3_70b_8192justicio-BOE-A-1978-31229-constitucion-by-articles-multilingual-e5-large-query-groq_llama3_70bindex-MIRACLRetrieval-th-intfloat_multilingual-e5-largedataset_teste_multilingual-e5-large
antonioanerao/dataset_teste_multilingual-e5-large
Dataset tabular com colunas planas para revisao no Argilla e uso posterior em fine-tuning de retrieval.
Uso
As colunas principais para revisao humana sao:
query
positive_passage
negative_passage
positive_reference
negative_reference
O dataset tem 36 registros.
Observacao
Este dataset foi formatado com colunas planas para facilitar a inferencia automatica de fields no Argilla ao importar do Hugging Face Hub.
As… See the full description on the dataset page: https://huggingface.co/datasets/antonioanerao/dataset_teste_multilingual-e5-large.multilingual-e5-large-instruct_2index-MIRACLRetrieval-de-intfloat_multilingual-e5-largeindex-MIRACLRetrieval-ru-intfloat_multilingual-e5-largeindex-MIRACLRetrieval-fr-intfloat_multilingual-e5-largeindex-MIRACLRetrieval-es-intfloat_multilingual-e5-largeindex-MIRACLRetrieval-ja-intfloat_multilingual-e5-large