Upload tokenizer

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<END_A>": 32003,
+  "<END_Q>": 32001,
+  "<START_A>": 32002,
+  "<START_Q>": 32000
+}

special_tokens_map.json

@@ -1,4 +1,10 @@
 {
+  "additional_special_tokens": [
+    "<START_Q>",
+    "<END_Q>",
+    "<START_A>",
+    "<END_A>"
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -13,6 +19,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 4096,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -29,6 +34,42 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32000,
+      "content": "<START_Q>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32001,
+      "content": "<END_Q>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32002,
+      "content": "<START_A>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32003,
+      "content": "<END_A>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {