Upload tokenizer

glm_tokenizer.py

@@ -0,0 +1,48 @@
+from tokenizers import Tokenizer
+from tokenizers.models import BPE
+from transformers import PreTrainedTokenizerFast
+
+
+class gLM2Tokenizer(PreTrainedTokenizerFast):
+
+    VOCAB = [
+        "<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", "a", "t", "c", "g", "<+>", "<->", "<mask>", "<sep>",
+    ]
+
+    def __init__(
+        self,
+        unk_token="<unk>",
+        cls_token="<cls>",
+        pad_token="<pad>",
+        mask_token="<mask>",
+        eos_token="<eos>",
+        sep_token="<sep>",
+        pos_token="<+>",
+        neg_token="<->",
+        **kwargs,
+    ):
+        all_tokens = self.VOCAB
+        token_to_id = {tok: ind for ind, tok in enumerate(all_tokens)}
+
+        bpe = BPE(token_to_id, merges=[], unk_token=str(unk_token))
+        tokenizer = Tokenizer(bpe)
+        special_tokens = [cls_token, pad_token,
+                          mask_token, eos_token, sep_token, pos_token, neg_token]
+
+        tokenizer.add_special_tokens(
+            special_tokens,
+        )
+
+        super().__init__(
+            tokenizer_object=tokenizer,
+            unk_token=unk_token,
+            cls_token=cls_token,
+            pad_token=pad_token,
+            mask_token=mask_token,
+            eos_token=eos_token,
+            sep_token=sep_token,
+            **kwargs,
+        )

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,133 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<cls>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 33,
+      "content": "<+>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 34,
+      "content": "<->",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 35,
+      "content": "<mask>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 36,
+      "content": "<sep>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": null,
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "<unk>",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<cls>": 0,
+      "<pad>": 1,
+      "<eos>": 2,
+      "<unk>": 3,
+      "L": 4,
+      "A": 5,
+      "G": 6,
+      "V": 7,
+      "S": 8,
+      "E": 9,
+      "R": 10,
+      "T": 11,
+      "I": 12,
+      "D": 13,
+      "P": 14,
+      "K": 15,
+      "Q": 16,
+      "N": 17,
+      "F": 18,
+      "Y": 19,
+      "M": 20,
+      "H": 21,
+      "W": 22,
+      "C": 23,
+      "X": 24,
+      "B": 25,
+      "U": 26,
+      "Z": 27,
+      "O": 28,
+      "a": 29,
+      "t": 30,
+      "c": 31,
+      "g": 32,
+      "<+>": 33,
+      "<->": 34,
+      "<mask>": 35,
+      "<sep>": 36
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "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
+    },
+    "33": {
+      "content": "<+>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<->",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "glm_tokenizer.gLM2Tokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "gLM2Tokenizer",
+  "unk_token": "<unk>"
+}