Chat Template - Liquid AI Docs

<|startoftext|><|im_start|>system
You are a helpful assistant trained by Liquid AI.<|im_end|>
<|im_start|>user
Explain how a heat pump works.<|im_end|>
<|im_start|>assistant
<think>

Conversations are formatted using special tokens:

<|startoftext|> — Start of the conversation.
<|im_start|> — Start of the message. Always followed by the role name (system, user, assistant, or tool) and a line break.
<|im_end|> — End of the message.
<think> / </think> — Start and end of the model’s reasoning, at the beginning of an assistant turn.

LFM3 supports four conversation roles:

system — (Optional) Defines who the assistant is and how it should respond.
user — Messages from the user containing questions and instructions.
assistant — Responses from the model.
tool — Results from tool/function execution. Used for tool use workflows.

The complete chat template definition can be found in the chat_template.jinja file in each model’s Hugging Face repository.

Using LFM2 or LFM2.5? See LFM2 and LFM2.5 for their chat template.

Text Models

We recommend storing your conversation as a list of dictionaries as follows:

messages = [
    {"role": "system", "content": "You are a helpful assistant trained by Liquid AI."},
    {"role": "user", "content": "Explain how a heat pump works."}
]

You can then apply LFM3’s chat template using the .apply_chat_template() method from Transformers:

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM3-1.7B", trust_remote_code=True)

# Apply chat template
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
print(prompt)

Output:

<|startoftext|><|im_start|>system
You are a helpful assistant trained by Liquid AI.<|im_end|>
<|im_start|>user
Explain how a heat pump works.<|im_end|>
<|im_start|>assistant
<think>

Reasoning

Reasoning is enabled by default, so the template opens every assistant turn with <think>. Set enable_thinking=False in apply_chat_template() for direct answers. Reasoning from turns before the latest user message is removed unless preserve_thinking=True.

Vision Models

from transformers import AutoProcessor

processor = AutoProcessor.from_pretrained("LiquidAI/LFM3-VL-2B", trust_remote_code=True)

messages = [
    {"role": "system", "content": "You are a helpful assistant trained by Liquid AI."},
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
            {"type": "text", "text": "What species is in this picture?"},
        ],
    },
]

# Apply chat template
prompt = processor.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
print(prompt)

Output:

<|startoftext|><|im_start|>system
You are a helpful assistant trained by Liquid AI.<|im_end|>
<|im_start|>user
<|vision_start|><|image|><|vision_end|>What species is in this picture?<|im_end|>
<|im_start|>assistant
<think>

Audio and Omni Models

<|startoftext|><|im_start|>system
Perform ASR in English.<|im_end|>
<|im_start|>user
<|vision_start|><|audio|><|vision_end|><|im_end|>
<|im_start|>assistant

In the answer, <|audio_start|> opens speech and <|mixed_start|> opens interleaved text and speech. LFM3-Omni-2B is a non-reasoning model: its template opens every assistant turn with an empty <think></think> block. See LFM3-Audio-2B and LFM3-Omni-2B for the recommended system prompts.

LFM2 and LFM2.5

LFM2 and LFM2.5 use a ChatML-like chat template without the <think> prefill:

<|startoftext|><|im_start|>system
You are a helpful assistant trained by Liquid AI.<|im_end|>
<|im_start|>user
What is C. elegans?<|im_end|>
<|im_start|>assistant
It's a tiny nematode that lives in temperate soil environments.<|im_end|>

LFM2 Text Models

We recommend storing your conversation as a list of dictionaries as follows:

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is machine learning?"}
]

You can then apply LFM2’s chat template using the .apply_chat_template() method from Transformers:

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2.5-1.2B-Instruct")

# Apply chat template
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
print(prompt)

Output:

<|startoftext|><|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
What is machine learning?<|im_end|>
<|im_start|>assistant

LFM2 Vision Models

LFM2-VL models follow the same chat template with additional support for images. When formatted, images are represented with a sentinel token (<image>), which is automatically replaced with image tokens by the processor. When creating conversations for vision models, use a structured format with content as a list containing image and text entries:

image = load_image("path/to/image.jpg")  # or use PIL Image

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image},  # PIL Image or loaded image
            {"type": "text", "text": "What is in this image?"},
        ],
    },
]

You can then apply the chat template using the processor’s .apply_chat_template() method:

from transformers import AutoProcessor
from transformers.image_utils import load_image

processor = AutoProcessor.from_pretrained("LiquidAI/LFM2.5-VL-1.6B")

# Apply chat template
prompt = processor.apply_chat_template(
    conversation,
    tokenize=False,
    add_generation_prompt=True
)
print(prompt)

Output:

<|startoftext|><|im_start|>system
You are a helpful multimodal assistant by Liquid AI.<|im_end|>
<|im_start|>user
<image>What is in this image?<|im_end|>
<|im_start|>assistant

​Text Models

​Reasoning

​Vision Models

​Audio and Omni Models

​LFM2 and LFM2.5

​LFM2 Text Models

​LFM2 Vision Models

Text Models

Reasoning

Vision Models

Audio and Omni Models

LFM2 and LFM2.5

LFM2 Text Models

LFM2 Vision Models