Fix bos/eos token IDs (config.json + tokenizer_config.json)

config.json

@@ -8,8 +8,8 @@
     "AutoModel": "modeling_ouro.OuroModel",
     "AutoModelForCausalLM": "modeling_ouro.OuroForCausalLM"
   },
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 2048,

tokenizer_config.json

@@ -157,10 +157,10 @@
     "<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,
   "tokenizer_class": "GPT2Tokenizer",