Update model card: add ONNX runtime guide and application use cases

Add quantized INT8 ONNX model export (58 MB)

Add FP16 ONNX model export (95 MB)

Fix dynamic import of configuration_bashkir_roberta

Improve model card and add citation

Remove misplaced metadata copy

Remove misplaced metadata copy

Fix tokenizer metadata

Fix model config metadata

Fix tokenizer auto-map metadata

Fix model config metadata

Add BashkirRoBERTa model files

Initial BashkirRoBERTa release

initial commit