Try LFM • Docs • LEAP • Discord

LFM2.5-Encoder-350-Prompt-Router

A full fine-tune of LFM2.5-Encoder-350M with a zero-shot routing head that scores a prompt against user-defined routing lanes in a single encoder pass.

Find more details about our encoders in our blog post.

[!NOTE] 💻 Demos: Try this fine-tuned model running in a CPU-only Hugging Face space: Zero-shot prompt routing — define your own routing lanes as free text. The model scores the whole prompt against every lane in one pass.

Usage

⚠️ Loads custom code via trust_remote_code=True (the model wraps a trust_remote_code encoder).

Install the required packages:

pip install torch transformers

Run zero-shot prompt routing:

from transformers import AutoModel, AutoTokenizer

model_id = "LiquidAI/LFM2.5-Encoder-350-Prompt-Router"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModel.from_pretrained(model_id, trust_remote_code=True).eval()

routes = ["Coding", "Sales", "Creative writing", "General knowledge"]
prompt = "Can you help me debug a failing Python unit test?"

print(model.route(prompt, routes, tokenizer=tokenizer))

📬 Contact

• Got questions or want to connect? Join our Discord community
• If you are interested in custom solutions with edge deployment, please contact our sales team.

Citation

@article{liquidAI2026Encoders,
  author = {Liquid AI},
  title = {LFM2.5-Encoders: Fast at Long Context, Even on CPU},
  journal = {Liquid AI Blog},
  year = {2026},
  note = {www.liquid.ai/blog/lfm2-5-encoders},
}