Upload tokenizer

special_tokens_map.json

@@ -13,7 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": "<unk>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -6,7 +6,7 @@
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -29,12 +29,14 @@
     }
   },
   "bos_token": "<s>",
+  "chat_template": "{% if 'role' in messages[0] %}{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] + '\n\n' }}{% set loop_messages = messages[1:] %}{% else %}{{ 'Below are some instructions that describe some tasks. Write responses that appropriately complete each request.' + '\n\n' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response:\n' + message['content'] + eos_token + '\n\n' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### Response:\n' }}{% endif %}{% else %}{{ bos_token }}{% if messages[0]['from'] == 'system' %}{{ messages[0]['value'] + '\n\n' }}{% set loop_messages = messages[1:] %}{% else %}{{ 'Below are some instructions that describe some tasks. Write responses that appropriately complete each request.' + '\n\n' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['from'] == 'human' %}{{ '### Instruction:\n' + message['value'] + '\n\n' }}{% elif message['from'] == 'gpt' %}{{ '### Response:\n' + message['value'] + eos_token + '\n\n' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### Response:\n' }}{% endif %}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},
-  "legacy": true,
+  "legacy": false,
   "model_max_length": 2048,
-  "pad_token": "</s>",
+  "pad_token": "<unk>",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",