Create table question answering with Gen AI LLMs @HuggingFace #llm #generativeai #machinelearning

Use @HuggingFace opensource models @Microsoft Tapex and @Google Tapas to question a tabular database made with Pandas dataframe. TAPEX is based on the BART architecture, the transformer encoder-decoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. TAPAS is a BERT-like transformers model pretrained on a large corpus of English data from Wikipedia in a self-supervised fashion 0:00 Introduction 0:47 How to search for Table question answering model 2:00 Analyzing Microsoft tapex-base model 7:19 Analyzing Google tapas model 10:05 Testing model accuracy with Transformers api 14:08 Conclusion 15:16 Like Share and Subscribe Google Colab - https://colab.research.google.com/drive/1Iz_aoskOMYqdFWfpwk5YJWuBPfJkGxao?usp=sharing Google Tapas SQA - https://huggingface.co/google/tapas-base-finetuned-sqa Microsoft Tapex - https://huggingface.co/microsoft/tapex-base My hugging face profile - https://huggingface.co/superlazycoder