# XNLI fine-tuning

A zero-shot classification model fine-tuned based on the Turkish BERT model, trained on the XNLI Turkish dataset, suitable for Turkish text classification tasks.

A multilingual text embedding model fine-tuned on the XNLI dataset based on intfloat/multilingual-e5-large-instruct, supporting zero-shot classification tasks in 15 languages

m-ST5 is a multilingual sentence embedding model based on the mT5 encoder, specifically optimized for cross-lingual semantic textual similarity and sentence retrieval tasks.

This model is a fine-tuned version of multilingual-e5-base on the XNLI dataset, supporting multilingual zero-shot classification tasks.

Based on the XLM-Roberta-base model, continuously pre-trained on Arabic Twitter corpus and fine-tuned on the XNLI Arabic dataset for zero-shot text classification.

Based on the XLM-Roberta-base model, it underwent continuous pre-training on a large multilingual Twitter corpus and was fine-tuned on the Chinese XNLI dataset, focusing on zero-shot text classification in Chinese.

Based on the XLM-Roberta-base model, continuously pretrained on a multilingual Twitter corpus and fine-tuned on the French XNLI dataset for zero-shot text classification

Representation-based Russian sentence encoder that obtains sentence representations by averaging token embedding vectors

Zero-shot classification model fine-tuned on XNLI Spanish dataset based on Spanish BERT base model

A 101-language sentence representation model based on multilingual BERT, generating sentence representations through mean-pooling of word embeddings