lfm2-350m-modular-loom

LFM2-350M (modular export)

Liquid AI's LFM2-350M hybrid conv/attention LM, exported as per-layer topologies.

This is a loom.cpp export: a single self-describing GGUF that carries its own graph topologies, tokenizer (if any) and driver script, produced by loom-exporter.

Original model

Exported from LiquidAI/LFM2-350M. Weights are unmodified; this repo packages the same parameters into loom.cpp's GGUF format.

License

LFM Open License v1.0 -- inherited from the base model above.

Language(s)

en, ar, zh, fr, de, ja, ko, es

Usage

Run it with loom-py -- loom-py-rt on PyPI:

pip install -U "loom-py-rt[hub]"

import loom

model = loom.Model.from_pretrained("loom-ai-org/lfm2-350m-modular-loom")
print(model.text2text.chat("Who discovered Brazil?", max_new_tokens=256))

# The same model, one turn at a time, and with the decode rule named rather than inherited:
print(model.chat([("user", "Name one river in Brazil.")], temperature=0.0))

The layer underneath

The call above is the high-level door: one per task, named for the modality pair it maps between, with the windowing, sampling and assembly this model needs already applied. Under it, model.infer(...) passes your arguments straight to the driver this GGUF embeds -- which is where you go for a knob the door does not name.

model.driver_source prints that driver, including a header comment documenting every argument it accepts for this model, and is the authority on it. See loom-py for the API and loom.cpp for what the engine does between the two.

Files

• lfm2-350m-modular.gguf -- the model, exported with loom-exporter.