`tokenizer_config.json` Fixes (#2)

- `tokenizer_config.json` Fixes (a56c230bff16ef7ce3a10012858b692ad99c67a9)
- more tokenizer_config fixes (be52112a7484741ab83a995e224c8a6209a25774)

tokenizer_config.json

@@ -2050,13 +2050,16 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
+  "chat_template": "{%- for message in messages %}\n    {%- if loop.index0 == 0 %}\n        {{- bos_token }}\n    {%- endif %}\n    {%- if message['role'] == 'system' %}\n        {{- '<|start_header_id|>Metadata<|end_header_id|>\n\n' + message['content'] + eos_token }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {{- '<|start_header_id|>Japanese<|end_header_id|>\n\n' + message['content'] + eos_token }}\n    {%- endif %}\n    {%- if message['role'] == 'assistant' %}\n        {{- '<|start_header_id|>English<|end_header_id|>\n\n' + message['content'] + eos_token }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>English<|end_header_id|>\n\n' }}\n{%- endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
+  "eos_token": "<|eot_id|>",
   "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 8192,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }