Upload tokenizer

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<BRG>": 50257,
+  "<|keywordtext|>": 50258,
+  "<|padtext|>": 50260,
+  "<|septext|>": 50261,
+  "<|startoftext|>": 50259
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    "<BRG>",
+    "<|keywordtext|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|padtext|>",
+  "sep_token": "<|septext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<BRG>",
+    "<|keywordtext|>"
+  ],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}