LongCat-Flash-Thinking-2601-FP8

text = tokenizer.apply_chat_template(
    messages,
    tools=tools,
    tokenize=False,
    enable_thinking=True,
    add_generation_prompt=True,
    save_history_reasoning_content=False
)

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "meituan-longcat/LongCat-Flash-Thinking-2601-FP8"

# Load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Please tell me what is $$1 + 1$$ and $$2 \times 2$$?"},
    {"role": "assistant", "reasoning_content": "This question is straightforward: $$1 + 1 = 2$$ and $$2 \times 2 = 4$$.", "content": "The answers are 2 and 4."},
    {"role": "user", "content": "Check again?"}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    enable_thinking=True,
    add_generation_prompt=True,
    save_history_reasoning_content=False # Discard reasoning history to save tokens
)

# Template Output Structure:
# <longcat_system>You are a helpful assistant.<longcat_user>Please tell me what is $$1 + 1$$ and $$2 \times 2$$?<longcat_assistant>The answers are 2 and 4</longcat_s><longcat_user>Check again? /think_on <longcat_assistant><longcat_think>\n

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

print(tokenizer.decode(output_ids, skip_special_tokens=True).strip("\n"))

# Example Output:
# The user wants a double-check. Since $$1 + 1 = 2$$ and $$2 \times 2 = 4$$ are basic arithmetic truths, the previous answer is correct.\n</longcat_think>\nI have verified the calculations: $$1 + 1 = 2$$ and $$2 \times 2 = 4$$. The initial answer remains correct.</longcat_s>

tools = [
    {
        "type": "function",
        "function": {
            "name": "func_add",
            "description": "Calculate the sum of two numbers",
            "parameters": {
                "type": "object",
                "properties": {
                    "x1": {"type": "number", "description": "The first addend"},
                    "x2": {"type": "number", "description": "The second addend"}
                },
                "required": ["x1", "x2"]
            }
        }
    }
]

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Please tell me what is $$125679 + 234519$$?"},
    {
        "role": "assistant", 
        "reasoning_content": "This calculation requires precision; I will use the func_add tool.", 
        "tool_calls": [{"type": "function", "function": {"name": "func_add", "arguments": {"x1": 125679, "x2": 234519}}}]
    },
    {"role": "tool", "name": "func_add", "content": '{"ans": 360198}'}
]

text = tokenizer.apply_chat_template(
    messages,
    tools=tools,
    tokenize=False,
    enable_thinking=True,
    add_generation_prompt=True,
    save_history_reasoning_content=False
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate response based on tool result
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

print(tokenizer.decode(output_ids, skip_special_tokens=True).strip("\n"))