docs: add Python/optimum usage example, list source.spm and vocab.json in files table

Upload tokenizer_config.json with huggingface_hub

Upload vocab.json with huggingface_hub

Upload source.spm with huggingface_hub

Update model card for int8 quantized models

Add int8 quantized models (EnableSubgraph: True)

Update model card for float32 (reverted from float16)

Revert to float32 — ONNX Runtime Web WASM does not support float16 tensors

Rename ONNX files with _fp16 suffix for Transformers.js auto-detection

Update model card for float16

Quantize to float16 for smaller downloads

Add model card

Initial ONNX model export from HiTZ/cap-punct-eu

initial commit