Best model tokenizer with eval_loss: 0.9291 (Trained with Unsloth)

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "5809": {
@@ -783,13 +782,10 @@
   "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
-  "errors": "replace",
   "extra_special_tokens": {},
-  "from_slow": true,
-  "legacy": false,
   "model_max_length": 16384,
   "pad_token": "<|dummy_87|>",
-  "padding_side": "left",
+  "padding_side": "right",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "�"
 }