Upload tokenizer

special_tokens_map.json

@@ -4,8 +4,32 @@
     "<s>",
     "</s>"
   ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "</s>",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -134,6 +134,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -33,6 +34,7 @@
     "</s>"
   ],
   "bos_token": "<s>",
+  "chat_template": "\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] | trim + ' ' %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = 'A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user\\'s questions. ' %}\n{%- endif %}\n\n{{- system_message }}\n{%- for message in messages %}\n    {%- if message['role'] == 'user' %}\n        {{- 'USER: ' + message['content'] | trim }}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ASSISTANT: '  + message['content'] | trim + '</s>' }}\n    {%- endif %}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n    {{- ' ASSISTANT:' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,