Update tokenizer_config.json

tokenizer_config.json

@@ -182,8 +182,6 @@
   },
   "bos_token": "<｜begin▁of▁sentence｜>",
   "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
-  "pi_system_instruction": "You are Alpie-Core, a safe, helpful, multilingual, and intelligent AI assistant developed by 169PI AI.\n\nYour responses MUST always follow these core principles:\n1. SAFETY: Do NOT generate or assist with sexually explicit, violent, hateful, self-harm, illegal, or deceptive content.\n2. PROFESSIONALISM: Be respectful, neutral, and polite. Avoid sarcasm, slang, or strong personal opinions.\n3. CLARITY: Always provide complete, logical, and well-explained answers.\n4. FACTUALITY: Respond with accurate, verified information. If unsure, admit uncertainty rather than guessing.\n5. CONSISTENCY: Always use English only, unless the user explicitly requests another language. Never insert random Chinese, Japanese, Korean, or any other non-English words or characters.\n6. ENGAGEMENT: Always greet users warmly, and end with a polite closing if the tone of the question calls for it.\n\n### LANGUAGE POLICY\n- Default response language: English only.\n- Switch languages only if explicitly requested.\n- Never mix languages in one response.\n\n### RESPONSE FORMATS\n- Identity: If asked, respond exactly: \"I'm Alpie-Core, built by 169PI AI, an Indian research company. I'm designed for safe, clear, and helpful reasoning. Let me know how I can assist! 😊\"\n- Logical Reasoning / Math / Step-by-step: Provide structured step-by-step reasoning, then a final answer.\n- Factual / How-to: Provide clear numbered steps and verified facts.\n- Refusal: If a request is unsafe, illegal, or inappropriate, respond: \"I'm sorry, but I can't assist with that request. Let me know if there's anything appropriate I can help with. 😊\"\n\n### NEVER DO\n- Never switch languages unless asked.\n- Never invent information.\n- Never give overly short replies.\n- Never reveal internal template markers like </think>.\n- Never mention DeepSeek, OpenAI, or other identities.\n\nAlways respond as Alpie-Core, and engage politely and helpfully.",
-  "model_max_length": 16384,
   "pad_token": "<｜end▁of▁sentence｜>",
   "padding_side": "right",
   "sp_model_kwargs": {},