llm_think_toggle.py

chat_template="{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- '' }}\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  {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" and not message.tool_calls %}\n        {%- set content = message.content %}\n        {%- if not loop.last %}\n            {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n        {%- endif %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- if not loop.last %}\n            {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n        {%- endif %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + 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<think>\\n' }}\n{%- endif %}\n"

import openai
model = "/kaggle/input/qwq-32b/transformers/qwq-32b/1" 
base_url = 'https://....ngrok-free.app/v1/'
openai.api_key = "dummy"
openai.base_url = base_url
msg = "print hello world in python."
msg = 'just say hi'
msg = '9.9 vs 9.11 - which number is greater? Just tell me the answer.'
messages=[ 
            {"role": "user", "content": msg}, 
        ]
thinking = 0
fast_thinking = 1
if thinking:
    if fast_thinking:
        messages.insert(0, {"role": "system", "content": "Don't overthink. Think in one line only."})
    messages.append({"role": "assistant", "content": r"<think>\\n"} )
else:
    messages.insert(0, {"role": "system", "content": "Don't think. Just answer."})
    messages.append({"role": "assistant", "content": "<think>\n\n</think>\n\n"})
response =  openai.chat.completions.create( 
    model=model,
    messages=messages,
    seed=42,
    temperature=0,
    stream=True, 
    extra_body={
        "add_generation_prompt": 0,
        "continue_final_message": 1,
        "chat_template": chat_template
    }
) 
if thinking:
    print("<think>")
for chunk in response:
    msg = chunk.choices[0].delta.content 
    if msg:
        print(msg, end="", flush=True)