TAPAS large model fine tuned on Sequential Question Answering (SQA) This model has 2 versions which can be used. The default version corresponds to the tapas sqa inter masklm large reset checkpoint of the original Github repository. This model was pre trained on MLM and an additional step which the authors call intermediate pre training, and then fine tuned on SQA. It uses relative position embeddings (i.e. resetting the position index at every cell of the table). The other (non default) version which can be used is: no reset , which corresponds to tapas sqa inter masklm large (intermediate pre training, absolute position embeddings). Disclaimer: The team releasing TAPAS did not write a model card for this model so this model card has been written by the Hugging Face team and contributors. Results on SQA Dev Accuracy Size Reset Dev Accuracy Link LARGE noreset 0.7223 tapas large finetuned sqa (absolute pos embeddings) LARGE reset 0.7289 tapas large finetuned sqa BASE noreset 0.6737 tapas base finetuned sqa (absolute pos embeddings) BASE reset 0.874 tapas base finetuned sqa MEDIUM noreset 0.6464 tapas medium finetuned sqa (absolute pos embeddings) MEDIUM reset 0.6561 tapas medium fin…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy