adding tokenizer

README.md

@@ -1,19 +1,18 @@
 ---
+language:
+- it
+license: cc-by-nc-4.0
 tags:
 - sft
 - it
 - mistral
 - chatml
 - axolotl
+prompt_template: <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|>
+  <|im_start|>assistant
 model-index:
 - name: maestrale-chat-v0.3-beta
   results: []
-license: cc-by-nc-4.0
-language:
-- it
-prompt_template: >-
-  <|im_start|>system {system_message}<|im_end|> <|im_start|>user
-  {prompt}<|im_end|> <|im_start|>assistant
 ---
 
 <div style="width: auto; margin-left: auto; margin-right: auto">

tokenizer_config.json

@@ -32,7 +32,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "32001": {
       "content": "<|im_start|>",
@@ -45,6 +45,7 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "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": "<|im_end|>",
   "legacy": true,