Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

special_tokens_map.json

@@ -1,24 +1,24 @@
 {
   "bos_token": {
     "content": "<s>",
-    "lstrip": false,
+    "lstrip": true,
     "normalized": false,
-    "rstrip": false,
+    "rstrip": true,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": "<|im_end|>",
   "unk_token": {
     "content": "<unk>",
-    "lstrip": false,
+    "lstrip": true,
     "normalized": false,
-    "rstrip": false,
+    "rstrip": true,
     "single_word": false
   }
 }

tokenizer.json

@@ -12,8 +12,8 @@
       "id": 0,
       "content": "<unk>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -21,8 +21,8 @@
       "id": 1,
       "content": "<s>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -34,6 +34,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32000,
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32001,
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": true,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {
@@ -70,7 +88,7 @@
       },
       {
         "SpecialToken": {
-          "id": "</s>",
+          "id": "<|im_end|>",
           "type_id": 0
         }
       }
@@ -90,7 +108,7 @@
       },
       {
         "SpecialToken": {
-          "id": "</s>",
+          "id": "<|im_end|>",
           "type_id": 0
         }
       },
@@ -108,28 +126,28 @@
       },
       {
         "SpecialToken": {
-          "id": "</s>",
+          "id": "<|im_end|>",
           "type_id": 1
         }
       }
     ],
     "special_tokens": {
-      "</s>": {
-        "id": "</s>",
+      "<s>": {
+        "id": "<s>",
         "ids": [
-          2
+          1
         ],
         "tokens": [
-          "</s>"
+          "<s>"
         ]
       },
-      "<s>": {
-        "id": "<s>",
+      "<|im_end|>": {
+        "id": "<|im_end|>",
         "ids": [
-          1
+          32000
         ],
         "tokens": [
-          "<s>"
+          "<|im_end|>"
         ]
       }
     }

tokenizer_config.json

@@ -4,17 +4,17 @@
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
     "1": {
       "content": "<s>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -25,17 +25,33 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": "<|im_end|>",
   "legacy": true,
   "max_length": 1024,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": "<|im_end|>",
   "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
@@ -43,6 +59,8 @@
   "tokenizer_class": "LlamaTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
+  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": true,
+  "use_fast": true
 }