Upload tokenizer

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<</SYS>>": 38366,
+  "<<SYS>>": 38365,
+  "[/INST]": 38368,
+  "[INST]": 38367
+}

special_tokens_map.json

@@ -1,4 +1,9 @@
 {
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:e792a804bbfc19a96b61b87109b8f2b0b7c92830025f285b402ba27c0c309c6f
+size 596883

tokenizer_config.json

@@ -25,18 +25,56 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "38365": {
+      "content": "<<SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38366": {
+      "content": "<</SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38367": {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38368": {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
   "bos_token": "<s>",
   "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": false,
+  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
-  "padding_side": "right",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": false,
+  "use_fast": true
 }