Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "<cls>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenization_proprime.py

@@ -0,0 +1,139 @@
+import os
+from typing import List, Optional
+from pathlib import Path
+from transformers.tokenization_utils import PreTrainedTokenizer
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"}
+
+
+def load_vocab_file(vocab_file):
+    with open(vocab_file, "r") as f:
+        lines = f.read().splitlines()
+        return [l.strip() for l in lines]
+
+
+class ProPrimeTokenizer(PreTrainedTokenizer):
+    vocab_files_names = VOCAB_FILES_NAMES
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(
+        self,
+        vocab_file=None,
+        unk_token="<unk>",
+        cls_token="<cls>",
+        pad_token="<pad>",
+        mask_token="<mask>",
+        eos_token="<eos>",
+        **kwargs,
+    ):
+        if vocab_file is None:
+            vocab_file = Path(__file__).parent / "vocab.txt"
+        self.all_tokens = load_vocab_file(vocab_file)
+        self._id_to_token = dict(enumerate(self.all_tokens))
+        self._token_to_id = {tok: ind for ind, tok in enumerate(self.all_tokens)}
+        super().__init__(
+            unk_token=unk_token,
+            cls_token=cls_token,
+            pad_token=pad_token,
+            mask_token=mask_token,
+            eos_token=eos_token,
+            **kwargs,
+        )
+
+        # TODO, all the tokens are added? But they are also part of the vocab... bit strange.
+        # none of them are special, but they all need special splitting.
+
+        self.unique_no_split_tokens = self.all_tokens
+        self._update_trie(self.unique_no_split_tokens)
+
+    def _convert_id_to_token(self, index: int) -> str:
+        return self._id_to_token.get(index, self.unk_token)
+
+    def _convert_token_to_id(self, token: str) -> int:
+        return self._token_to_id.get(token, self._token_to_id.get(self.unk_token))
+
+    def _tokenize(self, text, **kwargs):
+        return text.split()
+
+    def get_vocab(self):
+        base_vocab = self._token_to_id.copy()
+        base_vocab.update(self.added_tokens_encoder)
+        return base_vocab
+
+    def token_to_id(self, token: str) -> int:
+        return self._token_to_id.get(token, self._token_to_id.get(self.unk_token))
+
+    def id_to_token(self, index: int) -> str:
+        return self._id_to_token.get(index, self.unk_token)
+
+    def build_inputs_with_special_tokens(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        cls = [self.cls_token_id]
+        sep = [self.eos_token_id]
+        if token_ids_1 is None:
+            if self.eos_token_id is None:
+                return cls + token_ids_0
+            else:
+                return cls + token_ids_0 + sep
+        elif self.eos_token_id is None:
+            raise ValueError(
+                "Cannot tokenize multiple sequences when EOS token is not set!"
+            )
+        return (
+            cls + token_ids_0 + sep + token_ids_1 + sep
+        )  # Multiple inputs always have an EOS token
+
+    def get_special_tokens_mask(
+        self,
+        token_ids_0: List,
+        token_ids_1: Optional[List] = None,
+        already_has_special_tokens: bool = False,
+    ) -> List[int]:
+        """
+        Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` or `encode_plus` methods.
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of ids of the first sequence.
+            token_ids_1 (`List[int]`, *optional*):
+                List of ids of the second sequence.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+
+        Returns:
+            A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+        if already_has_special_tokens:
+            if token_ids_1 is not None:
+                raise ValueError(
+                    "You should not supply a second sequence if the provided sequence of "
+                    "ids is already formatted with special tokens for the model."
+                )
+
+            return [1 if token in self.all_special_ids else 0 for token in token_ids_0]
+        mask = [1] + ([0] * len(token_ids_0)) + [1]
+        if token_ids_1 is not None:
+            mask += [0] * len(token_ids_1) + [1]
+        return mask
+
+    def save_vocabulary(self, save_directory, filename_prefix):
+        vocab_file = os.path.join(
+            save_directory,
+            (filename_prefix + "-" if filename_prefix else "") + "vocab.txt",
+        )
+        with open(vocab_file, "w") as f:
+            f.write("\n".join(self.all_tokens))
+        return (vocab_file,)
+
+    @property
+    def vocab_size(self) -> int:
+        return len(self.all_tokens)
+
+
+ProPrimeTokenizer.register_for_auto_class("AutoTokenizer")

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_proprime.ProPrimeTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "ProPrimeTokenizer",
+  "unk_token": "<unk>"
+}

vocab.txt

@@ -0,0 +1,33 @@
+<cls>
+<pad>
+<eos>
+<unk>
+L
+A
+G
+V
+S
+E
+R
+T
+I
+D
+P
+K
+Q
+N
+F
+Y
+M
+H
+W
+C
+X
+B
+U
+Z
+O
+.
+-
+<null_1>
+<mask>