Update README.md

README.md

@@ -20,4 +20,21 @@ print(tokenizer.decode(ids['input_ids'], skip_special_tokens=False))
 # <bos>Hello, this is a test input.<EOT>
 len(tokenizer)
 # 65004
-```
+```
+
+
+details relevant for model configs using this:
+```py
+>>> tokenizer
+GPT2TokenizerFast(name_or_path='pszemraj/claude-tokenizer-mlm', vocab_size=65000, model_max_length=200000, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<bos>', 'eos_token': '<EOT>', 'unk_token': '<EOT>', 'sep_token': '<EOT>', 'pad_token': '<pad>', 'cls_token': '<bos>', 'mask_token': '<mask>'}, clean_up_tokenization_spaces=True),  added_tokens_decoder={
+        0: AddedToken("<EOT>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        1: AddedToken("<META>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        2: AddedToken("<META_START>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        3: AddedToken("<META_END>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        4: AddedToken("<SOS>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        65000: AddedToken("<pad>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        65001: AddedToken("<CLS>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        65002: AddedToken("<bos>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        65003: AddedToken("<mask>", rstrip=False, lstrip=True, single_word=False, normalized=True, special=True),
+}
+```