Update tokenizr

tokenizer_config.json

@@ -8,7 +8,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "1": {
       "content": "<s>",
@@ -16,7 +16,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "2": {
       "content": "</s>",
@@ -24,11 +24,12 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif true == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'Vous êtes Vigogne, un assistant IA créé par Zaion Lab. Vous suivez extrêmement bien les instructions. Aidez autant que vous le pouvez.' %}{% 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' %}{{ '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
@@ -38,7 +39,7 @@
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "tokenizer_file": "/projects/bhuang/.cache/huggingface/transformers/models--meta-llama--Llama-2-70b-hf/snapshots/cc8aa03a000ff08b4d5c5b39673321a2a396c396/tokenizer.json",
+  "tokenizer_file": null,
   "unk_token": "<unk>",
   "use_default_system_prompt": true
 }