Upload tokenizer

special_tokens_map.json

@@ -1,80 +1,50 @@
 {
-  "additional_special_tokens": [
-    {
-      "content": "<ent>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<ent2>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<ent>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<ent2>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "cls_token": {
-    "content": "<s>",
+    "content": "<cls>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "mask_token": {
     "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
+    "lstrip": false,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
     "content": "<pad>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "</s>",
+    "content": "<sep>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab06a40b6fb706ccde8547f0f2fca96968d9af24f49a214da6693d954f3ee4fa
-size 8656721
+oid sha256:9640c4cc0aba69ddb3b0d70601a75cb9fc55688868539ce240c5031d6ce6acec
+size 6724970

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
+size 1831879

tokenizer_config.json

@@ -1,18 +1,21 @@
 {
+  "add_bos_token": true,
+  "add_dummy_prefix_space": false,
+  "add_eos_token": true,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,69 +23,149 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": true,
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50265": {
-      "content": "<ent>",
+    "5": {
+      "content": "<mask>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50266": {
-      "content": "<ent2>",
+    "6": {
+      "content": "<cls>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "7": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<|available_tools|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<|tool_calls|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<|tool_results|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<|code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<|file|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102397": {
+      "content": "<|prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102398": {
+      "content": "<|suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102399": {
+      "content": "<|middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
-  "additional_special_tokens": [
-    "<ent>",
-    "<ent2>",
-    "<ent>",
-    "<ent2>"
-  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
-  "entity_mask2_token": "[MASK2]",
-  "entity_mask_token": "[MASK]",
-  "entity_pad_token": "[PAD]",
-  "entity_token_1": "<ent>",
-  "entity_token_2": "<ent2>",
-  "entity_unk_token": "[UNK]",
+  "cls_token": "<cls>",
+  "do_lower_case": false,
   "eos_token": "</s>",
-  "errors": "replace",
+  "extra_ids": 0,
   "extra_special_tokens": {},
+  "keep_accents": true,
+  "legacy": false,
   "mask_token": "<mask>",
-  "max_entity_length": 32,
-  "max_mention_length": 30,
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "task": null,
-  "tokenizer_class": "LukeTokenizer",
-  "unk_token": "<unk>"
+  "padding_side": "right",
+  "sep_token": "<sep>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }