blackfish021/apertus-lightpath-translator-v4

Apertus 8B lightpath translator, fourth format (standing policies)

A LoRA adapter that reads a standing policy for an optical transport network, in English, German, French or Italian, into one line of the policy language of the project Apertus Lightpath (Hack Apertus 2026, Track 2B), with two slots the third format lacks, a scope and a lifetime:

avoid=Zurich-Milan; via=none; hops=any; km=any; path=any; prefer=none; scope=rate:400; until=6h; rest=none

scope is any, a bit rate (rate:400), requests from a node (from:Zurich) or to a node (to:Milan); until is open (until withdrawn) or a number of hours. "For the next 6 hours, 400G services avoid the Zurich–Milan link" is the sentence above. A policy table (src/standing.py in the repository) holds such lines: which policies are active, which cover a request, the one line they combine to, the conflicts a new policy raises, and a report per policy.

Model details

• Base model: andreasmartin/apertus-v1.5-8b-text (text-only conversion of swiss-ai/Apertus-v1.5-8B).
• Method: QLoRA, 4-bit NF4 base, rank 32, alpha 32, 79.7 M trainable parameters, completion-only loss; one A100 80 GB, 65 minutes; grammar-constrained greedy decoding.
• Training data: 7,170 records: the third format's training material re-answered in the fourth format, plus 1,600 sentences that carry a scope or lifetime clause, in four languages, from templates filled with the topology. Scoped sentences of the held-out paraphrase pool were kept out of training.
• Files: adapter_model.safetensors and adapter_config.json at the root are the released adapter; adapter-epoch1/ and checkpoint/ are training artefacts.
• Developed by: Wadood Ranjha. License: Apache-2.0.

Results (from the project's results files)

• On 800 blind policy sentences (200 scope and lifetime phrases written by a separate AI instance, attached to the third round's blind sentences): right meaning, scope and lifetime included, 93.5 % (en 95.0, de 92.0, fr 95.0, it 92.0); by kind, a bit rate 90–97.5, requests from a node 72.5–90 (the weakest), to a node 92.5–100, a number of hours 90–100, until further notice 92.5–100.
• On the third format's test sets it is at least as good as reader 1: 96.7 / 93.2 / 96.0 / 94.6 % (en / de / fr / it); of instruction types shown to no component it silently applies 16.7 % (reader 1: 46.3 %).
• Closed loop on a stream of standing policies (three at the start, one every two simulated hours, at most four active; 240 and 390 Erlang, three seeds): the policy table built from its readings breaks 1.1 / 1.5 % of requests against the true table, where ignoring scope breaks 12.7 / 30.0 %, ignoring lifetime 11.9 / 6.4 %, first fit 42.0 / 38.1 %, and a reader of the third format (no scope, no lifetime) 21.4 / 36.9 %.
• In 4-bit GGUF form on a laptop GPU it reads 90.6 % of the policy sentences and its table stays within 2.4 points of the truth.
• On the third round's mixed stream of per-request instructions (390 Erlang, three seeds) it can replace reader 1: alone it breaks 10.7 % of requests (reader 1: 10.6 %), in front of the decider 9.1 % (9.5 %), passing 16.1 % of requests to the decider instead of 11.5 %.
• Template lines (by the author, partly with ChatGPT 6.1 Sol), at 16 bits: right on 34 of the owner set's 40 and on 36 of template set 1's 40 (English, German, Italian, Swedish; 15 standing policies), Swedish 9 of 10, although no training sentence is Swedish. In 4 bits on the laptop: 31, 35, and 33 and 34 of two more sets of 40 in English and German (English 46 of 50, German 21 of 30), 61 of 70 and 17 of 20 of sets 4 and 5 (English, Swiss German, French, Italian): 211 of all 250.
• The same 60 items in nine languages and scripts (written and translated by separate AI instances; 4 bits on the laptop; results/design/parallel.json): right on 55 in English, 52–53 in German, French and Italian, 43 in Urdu script, 45 in Hindi and in Arabic script, 32 in Urdu/Hindi in Latin letters, 14 in Arabic in Latin letters.
• Known error: "to Prague, avoid Berlin" is read as a scope (to:Prague) where an operator means the current request's destination; the language has no word yet for a request's own end points.

How to use

As reader 1 (blackfish021/apertus-lightpath-translator-v3, see its card), with this repository's name and the fourth format's prompt (src/translate.py, SYSTEM4). A GGUF of the adapter for llama.cpp is in blackfish021/apertus-lightpath-translator-v3-gguf (lightpath-translator-v4-lora-f16.gguf).

Intended use and limits

Research and prototyping on a simulator; synthetic sentences; one training run; no second reader of this format yet, so scope and lifetime are read once. Other models' role: Claude (Anthropic) wrote the project's code and documentation under the author's direction, the sentence templates of the training data and, as separate instances that never saw the repository, the test sentences; no other model is part of the system. The author wrote the template lines (a test set) partly with ChatGPT 6.1 Sol (OpenAI).

Repository: github.com/theBlackfish01/ApertusNetworkGym (track_2b/).