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
.
💻
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))
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},
}
Runs of LiquidAI LFM2.5-Encoder-350M-Prompt-Router on huggingface.co
5.4K
Total runs
0
24-hour runs
-9
3-day runs
41
7-day runs
324
30-day runs
More Information About LFM2.5-Encoder-350M-Prompt-Router huggingface.co Model
More LFM2.5-Encoder-350M-Prompt-Router license Visit here:
LFM2.5-Encoder-350M-Prompt-Router huggingface.co is an AI model on huggingface.co that provides LFM2.5-Encoder-350M-Prompt-Router's model effect (), which can be used instantly with this LiquidAI LFM2.5-Encoder-350M-Prompt-Router model. huggingface.co supports a free trial of the LFM2.5-Encoder-350M-Prompt-Router model, and also provides paid use of the LFM2.5-Encoder-350M-Prompt-Router. Support call LFM2.5-Encoder-350M-Prompt-Router model through api, including Node.js, Python, http.
LFM2.5-Encoder-350M-Prompt-Router huggingface.co is an online trial and call api platform, which integrates LFM2.5-Encoder-350M-Prompt-Router's modeling effects, including api services, and provides a free online trial of LFM2.5-Encoder-350M-Prompt-Router, you can try LFM2.5-Encoder-350M-Prompt-Router online for free by clicking the link below.
LiquidAI LFM2.5-Encoder-350M-Prompt-Router online free url in huggingface.co:
LFM2.5-Encoder-350M-Prompt-Router is an open source model from GitHub that offers a free installation service, and any user can find LFM2.5-Encoder-350M-Prompt-Router on GitHub to install. At the same time, huggingface.co provides the effect of LFM2.5-Encoder-350M-Prompt-Router install, users can directly use LFM2.5-Encoder-350M-Prompt-Router installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
LFM2.5-Encoder-350M-Prompt-Router install url in huggingface.co: