CodeV is a 7-billion-parameter vision-language model fine-tuned based on Qwen2.5-VL-7B-Instruct. Through two-stage training of supervised fine-tuning (SFT) and reinforcement learning (RL) based on tool-aware policy optimization (TAPO), it aims to achieve reliable and interpretable visual reasoning. It represents visual tools as executable Python code and ensures the consistency between tool usage and question evidence through a reward mechanism, solving the problem of irrelevant tool invocation under high accuracy.

MultimodalTransformersMultiple Languages

A table summarization model based on the BART architecture, optimized for query-focused table summarization tasks.

Natural Language ProcessingTransformersEnglish

A chat model based on the Llama2 architecture, fine-tuned on over 40,000 long chat conversations, with good conversation ability.

Natural Language ProcessingTransformers

This is an Italian paraphrasing generation model based on the MT5-base architecture, fine-tuned on the TaPaCo and STS Benchmark datasets.

Natural Language ProcessingTransformersOther

A model fine-tuned based on microsoft/deberta-v3-base, achieving an accuracy of 75.76% on the evaluation set

Natural Language ProcessingTransformers

TAPEX is a table pre-training model that learns through neural SQL executors, specifically designed for table question answering tasks.

Natural Language ProcessingTransformersEnglish

TAPEX is a model that achieves table pretraining by learning neural SQL executors, based on the BART architecture, specifically designed for table reasoning tasks.

Natural Language ProcessingTransformersEnglish

TAPEX is a table pre-training model that learns via neural SQL executor, based on the BART architecture, specifically designed for table reasoning tasks.

Natural Language ProcessingTransformersEnglish

TAPEX is a model designed for table reasoning tasks, learning through neural SQL executors for table pretraining, based on the BART architecture.

Natural Language ProcessingTransformersEnglish

TAPEX is a table pre-training model learned through neural SQL executors, based on the BART architecture, specifically designed for table reasoning tasks.

Natural Language ProcessingTransformersEnglish

TAPAS (Table Parser) is a table-based pre-trained language model developed by Google Research, specifically designed for processing tabular data and natural language queries.

Natural Language ProcessingTransformers

TAPAS is a table-based question answering model that handles conversational QA tasks on tabular data through pre-training and fine-tuning.

Natural Language ProcessingTransformersEnglish

TAPAS is a table question answering model based on the BERT architecture, pre-trained in a self-supervised manner on Wikipedia table data, supporting natural language question answering on table content

Natural Language ProcessingTransformersEnglish

TAPAS is a BERT-like model based on the Transformer architecture, specifically designed for processing tabular data and related text, pretrained in a self-supervised manner on Wikipedia table data.

Natural Language ProcessingTransformersEnglish

TAPAS is a Transformer-based table question answering model pre-trained in a self-supervised manner on Wikipedia tables and associated text, supporting table understanding and question answering tasks.

Natural Language ProcessingTransformersEnglish

TAPEX is a model designed for table question answering tasks, learning table pre-training through neural SQL executors and based on the BART architecture.

Natural Language ProcessingTransformersEnglish

TAPEX-large is a large-scale language model pre-trained on tabular data, specifically fine-tuned for table question answering tasks. It achieves table understanding through a neural SQL executor and can answer natural language questions about table content.

Natural Language ProcessingTransformersEnglish

This model is a small version of TAPAS, which has undergone intermediate pre-training and fine-tuning on the SQA dataset. It is suitable for table question answering tasks in dialogue scenarios.

Natural Language ProcessingTransformersEnglish

TAPAS is a pre-trained language model based on tabular data, specifically designed for natural language tasks related to tables.

Natural Language ProcessingTransformers

TAPAS is a Transformer-based table question answering model pre-trained in a self-supervised manner on English Wikipedia table data, supporting table QA and entailment tasks.

Natural Language ProcessingTransformersEnglish