Upload tokenizer

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 16384,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {
@@ -56,12 +51,6 @@
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
@@ -70,24 +59,12 @@
       }
     ],
     "pair": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 1
-        }
-      },
       {
         "Sequence": {
           "id": "B",
@@ -95,17 +72,7 @@
         }
       }
     ],
-    "special_tokens": {
-      "<s>": {
-        "id": "<s>",
-        "ids": [
-          1
-        ],
-        "tokens": [
-          "<s>"
-        ]
-      }
-    }
+    "special_tokens": {}
   },
   "decoder": {
     "type": "Sequence",

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": false,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -26,19 +28,15 @@
     }
   },
   "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 %}",
+  "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 %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
-  "max_length": 16384,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<unk>",
   "padding_side": "right",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }