Upload tokenizer with huggingface_hub

tokenizer/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  " </ENTITY_CHAIN> ": 50258,
+  "<ENTITY_CHAIN>": 50257
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<ENTITY_CHAIN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": " </ENTITY_CHAIN> ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    {
+      "__type": "AddedToken",
+      "content": "<ENTITY_CHAIN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "__type": "AddedToken",
+      "content": " </ENTITY_CHAIN> ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}