---

license: other

license_name: lfm1.0

license_link: LICENSE

base_model: LiquidAI/LFM2.5-1.2B-Instruct

language:

• de
• ar

pipeline_tag: text-generation

tags:

• gguf
• lfm2
• german
• language-learning
• on-device

---

Laura — German tutor in Arabic (LFM2.5 1.2B, GGUF)

Laura is the tutor in an offline German course app for adult beginners

(A1–A2). This model talks to the learner in Arabic and teaches German with

German examples. It runs on the phone, CPU only.

This is a modified version of LiquidAI/LFM2.5-1.2B-Instruct.

Changes made: a LoRA adapter (rank 16, all linear layers, 2 epochs) was trained

on ~2,500–3,300 short tutoring conversations in Arabic, merged into the weights,

and the result converted to GGUF and quantised to Q4_K_M with llama.cpp.

Distributed under the base model's LFM Open License v1.0 — see LICENSE.

How the app uses it

The app does not trust the model to judge German on its own. It checks the

learner's sentence with its own dictionary first and adds the verdict to the

message — (Check: ✗ → „corrected sentence“ · reason) or (Check: ✓ …) — plus

dictionary meanings and the chapter's rule card. The model was trained with

exactly those notes and explains them; without them it is a much weaker teacher.

Evaluation

Round 6, on 359 held-out conversations it never saw in training: 1150 of 1152 replies (99.8%) follow the app's rules and the German check (0 praises of a sentence the check marks wrong). In the app, verdicts, corrections, dictionary meanings and rule-card answers are written by the app itself; the model adds the conversation around them.

Files

• laura-ar-lfm2.5-1.2b-Q4_K_M.gguf — Q4_K_M, 0.73 GB