Thinking

<think>15% of 80: 10% is 8 and 5% is 4, so 15% is 12.</think>The answer is 12.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "LiquidAI/LFM3-1.7B"
model = AutoModelForCausalLM.from_pretrained(model_id, dtype="bfloat16", device_map="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

messages = [{"role": "user", "content": "A shop sells pens at $3 each or 4 for $10. What is the lowest cost for 11 pens?"}]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    enable_thinking=True,  # the default
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

output_ids = model.generate(
    **inputs,
    do_sample=True,
    temperature=0.1,
    top_k=50,
    repetition_penalty=1.1,
    max_new_tokens=16384,
)
text = tokenizer.decode(output_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)

import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "LiquidAI/LFM3-VL-2B"
model = AutoModelForImageTextToText.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
            {"type": "text", "text": "How many cats are in this image?"},
        ],
    }
]

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    enable_thinking=True,  # the default
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

with torch.inference_mode():
    output_ids = model.generate(
        **inputs,
        do_sample=True,
        temperature=0.1,
        top_k=50,
        repetition_penalty=1.1,
        max_new_tokens=16384,
    )
text = processor.decode(output_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)

message = response.choices[0].message
reasoning = getattr(message, "reasoning_content", None) or getattr(message, "reasoning", None)
print("Reasoning:", reasoning)
print("Answer:", message.content)

stream = client.chat.completions.create(
    model="LiquidAI/LFM3-1.7B",
    messages=[{"role": "user", "content": "What is 17 * 23 - 45?"}],
    stream=True,
)
for chunk in stream:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    reasoning = getattr(delta, "reasoning_content", None) or getattr(delta, "reasoning", None)
    if reasoning:
        print(reasoning, end="", flush=True)  # show it greyed out or hide it in your UI
    if delta.content:
        print(delta.content, end="", flush=True)

def split_reasoning(text):
    reasoning, separator, answer = text.partition("</think>")
    if not separator:
        # No closing tag: generation stopped mid-thought. Raise the token limit.
        return reasoning.replace("<think>", "").strip(), ""
    return reasoning.replace("<think>", "").strip(), answer.strip()

reasoning, answer = split_reasoning(text)