Upload tokenizer

special_tokens_map.json

@@ -6,8 +6,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "eos_token": "будь",
-  "pad_token": "будь",
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -29,11 +29,12 @@
     }
   },
   "bos_token": "<s>",
+  "chat_template": "{% set loop_messages = messages %}\n{% for message in loop_messages %}\n{% set content = message['role']+'\n'+ message['content'] + '\n' %}\n{% if message['role'] == 'System' %}\n{% set content = '<extra_id_0>' + content %}\n{% else %}\n{% set content = '<extra_id_1>' + content %}\n{% endif %}\n{{ content }}\n{% endfor %}\n{% if add_generation_prompt %}\n{{ '<extra_id_1>Assistant' }}\n\n{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "будь",
+  "eos_token": "</s>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "будь",
+  "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",