Prompt format and sampling

Use the embedded chat template

Every repository ships the model's chat template: chat_template.jinja beside the Transformers and MLX weights, and embedded in each GGUF file. Let your runtime apply it instead of writing prompt markup by hand: apply_chat_template in Transformers, --jinja in llama.cpp, and the chat endpoints of llama.cpp and vLLM.

• End-of-sequence token: <|im_end|>. Padding token: <|endoftext|>.
• Text in, text out. The base model's vision encoder is not included.

Thinking and non-thinking

Noema 1.5 4B thinks by default and switches through the chat template. Noema 1.5 2B is recommended without thinking for instructions, structured output and code. Noema 2B was trained and evaluated without thinking.

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    enable_thinking=False,
    return_dict=True,
    return_tensors="pt",
)

Read the answer

With thinking on, the reasoning trace comes first and ends at </think>; the answer follows. Split on the last </think>, or let vLLM's qwen3 reasoning parser return the two separately.

reasoning, _, answer = text.rpartition("</think>")
print(answer.strip())

In multi-turn use, keep only the final answers in the conversation history. The Noema 1.5 4B chat template already drops earlier reasoning traces. In the Noema app, Reasoning history controls this for supported GGUF models.

Sampling for Noema 1.5 4B

Thinking is on by default; pass enable_thinking=False to the chat template to answer directly. Avoid greedy decoding with thinking on, which makes repetition more likely in any reasoning model. In multi-turn use, keep only final answers in the history.

Sampling for Noema 1.5 2B

The packaged defaults are greedy and stop at <|im_end|>. Deployments should enforce output limits and detect repeated spans, especially with thinking on.

Sampling for Noema 2B

Do not use greedy decoding: this model family can enter repetition loops under greedy sampling. The presence penalty applies on engines that support it, such as vLLM and llama.cpp.