# QA System Optimization

This model is fine-tuned based on EEVE-Korean-Instruct-10.8B-v1.0, designed to evaluate whether the retrieved context in RAG (Retrieval-Augmented Generation) is correct for a given question, answering with 'yes' or 'no'.

A bilingual reranking model based on Bloomz-560m for measuring semantic relevance between queries and contexts, supporting both French and English

A RoBERTa-based QA classification model for identifying categories of non-factual questions

A question-answering model trained on the adversarial_qa dataset, designed to answer adversarial questions.

A QA and NER model fine-tuned on the conll2003 dataset based on distilbert-base-uncased-squad2

This model is designed to distinguish between question queries and statement queries, specifically trained for neural search query classification via Haystack's classification functionality.

A multi-task model based on DistilBERT for question answering and named entity recognition, fine-tuned on the conll2003 dataset

A Chinese multimodal pretraining model built on the Oscar framework, initialized with Mengzi-Bert base version, trained on 3.7 million image-text pairs.