Upload tokenizer

special_tokens_map.json

@@ -1,5 +1,6 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
   "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -10,11 +10,13 @@
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nAIko laguntzaile lagungarria zara, GPT-Bi izenekoa, AuriLab-ek hezia.<|im_end|>\n' }}{% endif %}{{'<|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": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "model_max_length": 1024,
+  "pad_token": "<|im_end|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }