mikii17/question-answering

Update model name to use finetuned version v1 for consistency

Update model name to use finetuned version v2 for improved performance

Remove debug print statements and correct function call in process_request

Fix typo in variable name from 'contexts' to 'context' in process_request function

Add import for concurrent.futures to enable threading support

Refactor inference logic to use ThreadPoolExecutor for optimized question answering

Fix offset mapping handling in infer_single_question function

Fix offset mapping handling in inference function and update return value format

Add debug print statements for sequence_ids and offset_mapping in inference function

Add debug print statements for input and output variables in inference function

Add numpy import for numerical operations in main.py

Refactor input ID and attention mask handling in inference function to add batch dimension

Convert input IDs and attention mask to tensors in inference function

Remove unnecessary return_tensors argument in inference function

Fix sequence ID reference in offset mapping adjustment

Refactor offset mapping adjustment to utilize sequence IDs for context tokens

Add imports for AutoTokenizer and AutoModelForQuestionAnswering

Implement question inference function using fine-tuned model

Add logs

Considering multiple contexts

Fix model identifier in question-answering pipeline

Merge branch 'main' of https://huggingface.co/spaces/mikii17/question-answering

Update model

Add application file

Fix model identifier in question-answering pipeline

Add application file

initial commit