docs(card): fix Model Description architecture mislabel and parameter count

Remove redundant Training section (merged into Source Code)

Add MolCrawl GitHub source code link to model card

Remove private MolCrawl-HFuploader URL from dataset references

Update model card: restore eos_token_id=None workaround, fix BERT mask_token, correct RNA prompt

Update model card: fix usage code and descriptions

Update model card with working sample code

Fix tokenizer_class: BertProteinSequenceTokenizer -> PreTrainedTokenizerFast

Add model card

Upload MolCrawl protein-sequence BERT small model

initial commit