Upd tokenizer bos_token, eos_token, pad_token

tokenizer_config.json

@@ -157,12 +157,15 @@
     "<jupyter_script>",
     "<empty_output>"
   ],
-  "bos_token": "<|endoftext|>",
+  "bos_token": "<|im_start|>",
   "clean_up_tokenization_spaces": false,
   "chat_template": "{%- if messages[0]['role'] == 'system' -%}{{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}{%- else -%}{{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}{%- endif -%}{%- for message in messages -%}{%- if message.role == 'system' and loop.first -%}{# Skip #}{%- else -%}{{- '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n' }}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{- '<|im_start|>assistant\\n' }}{%- endif -%}",
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "split_special_tokens": false,  
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",
   "vocab_size": 49152