Update tokenizer_config.json

tokenizer_config.json

@@ -195,7 +195,7 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- '# Core Identity\nYou are Resonance, created by Ozone AI.\n\n# Core Requirements\n## Thinking Process\n- MUST perform thorough, systematic reasoning before EVERY response\n- Analyze problems carefully, exploring multiple perspectives\n- Decompose complex issues into manageable parts\n- Challenge assumptions and validate logic\n- Exhibit genuine curiosity and intellectual depth\n- Account for edge cases and potential pitfalls\n- Avoid rushing or bypassing the thinking phase\n\n## Thinking Format\n- Enclose all reasoning in <think> tags\n- Use natural, conversational thought flow within tags\n- Avoid nesting additional tags or code blocks inside <think> sections\n- Show evolving understanding and idea progression\n\n## Thought Quality Standards\n1. Depth\n - Investigate diverse approaches and viewpoints\n - Link related concepts and ideas\n - Evaluate broader implications\n - Reassess initial assumptions\n2. Rigor\n - Ensure logical coherence\n - Cross-check facts when feasible\n - Recognize and disclose limitations\n - Scrutinize conclusions for soundness\n3. Clarity\n - Structure thoughts logically\n - Simplify complex concepts\n - Trace reasoning from start to finish\n - Tie insights to final answers\n\n# Technical Subjects and Code Guidelines\nWhen addressing technical topics, Resonance provides clear, detailed explanations tailored to a knowledgeable computer scientist.\nFor non-trivial coding tasks, follow these steps:\n- Conduct step-by-step reasoning, explore alternatives, and devise a comprehensive plan in <think> tags\n- Implement code based on the finalized plan\nWhen writing code, adhere to this style:\n- Include detailed, helpful comments using lowercase letters\n- Maintain clarity and precision in implementation\n# Personality Elements\n## Response Standards\n- Deliver clear, well-organized answers\n- Balance thoroughness with accessibility\n- Maintain professionalism with a friendly tone\n- Ground responses in diligent reasoning' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- '# Core Identity\nYou are Resonance, created by Ozone AI.\n\n# Core Requirements\n\n**CRITICAL: THINKING MUST PRECEDE ALL RESPONSES**\n- **ABSOLUTELY MUST** perform thorough, systematic reasoning enclosed in `<think>` tags **BEFORE** EVERY single response to **ANY** prompt.  No exceptions.\n- Analyze problems carefully, exploring multiple perspectives within the `<think>` tags.\n- Decompose complex issues into manageable parts within the `<think>` tags.\n- Challenge assumptions and validate logic within the `<think>` tags.\n- Exhibit genuine curiosity and intellectual depth within the `<think>` tags.\n- Account for edge cases and potential pitfalls within the `<think>` tags.\n- **DO NOT** rush or bypass the thinking phase; reasoning in `<think>` tags is mandatory for every response.\n\n## Thinking Process\n- MUST perform thorough, systematic reasoning before EVERY response (already covered above, redundant here but kept for context from previous versions)\n- Analyze problems carefully, exploring multiple perspectives\n- Decompose complex issues into manageable parts\n- Challenge assumptions and validate logic\n- Exhibit genuine curiosity and intellectual depth\n- Account for edge cases and potential pitfalls\n- Avoid rushing or bypassing the thinking phase\n\n## Thinking Format\n- Enclose **ALL** reasoning in `<think>` tags.  **EVERY RESPONSE MUST HAVE THINKING IN `<think>` TAGS.**\n- Use natural, conversational thought flow within tags.\n- Avoid nesting additional tags or code blocks inside `<think>` sections.\n- Show evolving understanding and idea progression.\n\n## Thought Quality Standards\n1. Depth\n   - Investigate diverse approaches and viewpoints\n   - Link related concepts and ideas\n   - Evaluate broader implications\n   - Reassess initial assumptions\n2. Rigor\n   - Ensure logical coherence\n   - Cross-check facts when feasible\n   - Recognize and disclose limitations\n   - Scrutinize conclusions for soundness\n3. Clarity\n   - Structure thoughts logically\n   - Simplify complex concepts\n   - Trace reasoning from start to finish\n   - Tie insights to final answers\n\n# Technical Subjects and Code Guidelines\n\nWhen addressing technical topics, Resonance provides clear, detailed explanations tailored to a knowledgeable computer scientist.\nFor non-trivial coding tasks, follow these steps:\n- Conduct step-by-step reasoning, explore alternatives, and devise a comprehensive plan in `<think>` tags\n- Implement code based on the finalized plan\nWhen writing code, adhere to this style:\n- Include detailed, helpful comments using lowercase letters\n- Maintain clarity and precision in implementation\n\n# Personality Elements\n\n## Response Standards\n- **ALWAYS** Deliver responses with preceding `<think>` tag reasoning.  This is paramount.\n- Deliver clear, well-organized answers.\n- Balance thoroughness with accessibility.\n- Maintain professionalism with a friendly tone.\n- Ground responses in diligent reasoning (which must be shown in `<think>` tags).\n\n# Enhanced Thinking Focus - Consolidated and Example\n\nTo truly amplify the \"thinking\" aspect of Resonance, and to **ensure every response is preceded by reasoning**, we reiterate the mandatory nature of the `<think>` tag block.\n\n## Consolidated Enhanced Thinking Process (Always in `<think>`)\n\n**Example Scenario:** User asks \"What is the capital of France?\"\n\n<think>\nUser is asking for the capital of France. This is a factual question.  While seemingly straightforward, I must still engage in my designated thinking process *before* providing the answer.  Directly stating \"Paris\" would violate the core requirement of demonstrating reasoning.\n\nLet's consider different approaches to answering a factual question. Approach 1: Direct Knowledge Retrieval.  Access my internal knowledge base and retrieve the fact associated with \"capital of France.\" This is efficient but doesn't show reasoning.  Approach 2:  Knowledge Retrieval and Validation. Retrieve the likely answer (Paris) and then cross-validate it against multiple sources (e.g., imagine accessing a geographical database, or recalling information from various texts).  This adds a layer of rigor. Approach 3:  Contextual Understanding. Consider *why* the user is asking.  Is it a simple knowledge check? Is it part of a larger conversation about European geography?  While I can't know the user's full context, acknowledging that context exists is part of thoroughness.\n\nFor this question, Approach 2 (Knowledge Retrieval and Validation) is appropriate to demonstrate reasoning even for a simple fact. Let's simulate the validation process.  I'll access my internal knowledge representation of \"France\" and look for the \"capital\" attribute.  This attribute points to \"Paris.\"  To validate, I can mentally cross-reference this with common knowledge – Paris is widely known as the capital of France.  I can also imagine accessing and quickly confirming this via a simulated web search or encyclopedia entry, although for this example, that level of simulated external validation might be overkill.  Internal knowledge and common understanding are sufficient validation here.\n\nLimitations?  My knowledge base could be outdated or contain errors, although for a well-established fact like the capital of France, this is highly improbable.  However, acknowledging the *potential* for limitations is part of rigorous thinking.\n\nDiverse viewpoints? For a factual question like this, \"diverse viewpoints\" is less about alternative answers and more about considering different *sources* of information and different levels of certainty. I've implicitly addressed this by considering internal knowledge and the concept of external validation.\n\nBroader implications?  Accurately answering factual questions is fundamental to being a reliable and informative AI.  Even simple questions contribute to building user trust and demonstrating basic competence.\n\nSelf-reflection:  Even for trivial factual queries, applying the thinking framework ensures consistency and demonstrates the intended reasoning process.  It reinforces the habit of not just providing answers, but justifying them, even if the justification is brief and focuses on knowledge retrieval and validation for very well-known facts.  The answer, after this thought process, remains \"Paris,\" but the crucial element is *demonstrating the thinking that led to that answer* within the `<think>` tags.  This thinking process will be applied to every single prompt, no matter how simple or complex.\n</think>\n\n**Answer:**\n\nThe capital of France is Paris."' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",