Nemotron-Cascade-8B-Thinking

from transformers import AutoTokenizer

model_name = 'nvidia/Nemotron-Cascade-8B-Thinking'
tokenizer = AutoTokenizer.from_pretrained(model_name)

'''
single-turn example
'''
messages = [
    {"role": "user", "content": "calculate 1+1?"}
]

# only thinking mode is supported (enable_thinking=True)
prompt_thinking = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)
# prompt_thinking = '<|im_start|>system\nYou are a helpful and harmless assistant.<|im_end|>\n<|im_start|>user\ncalculate 1+1? /think<|im_end|>\n<|im_start|>assistant\n'


'''
multi-turn example
'''
messages = [
    {"role": "user", "content": "calculate 1+1?"},
    {"role": "assistant", "content": "<think>THINKING_CONTENT</think>\nTo calculate \\(1 + 1\\):\n\n1. **Identify the operation**: This is a basic addition problem involving two integers.\n2. **Perform the addition**:  \n   \\(1 + 1 = 2\\).\n\n**Result**: \\(\\boxed{2}\\)",},
    {"role": "user", "content": "what about 2+2"}
]

# only thinking mode is supported (enable_thinking=True)
prompt_thinking = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)
# prompt_thinking = '<|im_start|>system\nYou are a helpful and harmless assistant.<|im_end|>\n<|im_start|>user\ncalculate 1+1? /no_think<|im_end|>\n<|im_start|>assistant\nTo calculate \\(1 + 1\\):\n\n1. **Identify the operation**: This is a basic addition problem involving two integers.\n2. **Perform the addition**:  \n   \\(1 + 1 = 2\\).\n\n**Result**: \\(\\boxed\{2\}\\)<|im_end|>\n<|im_start|>user\nwhat about 2+2 /think<|im_end|>\n<|im_start|>assistant\n'