Downloads · 30 days
5
6% of all-time downloads
Buttermilk03/scriber-lfm2.5-350m-polishing-de-qad-v1
scriber-lfm2.5-350m-polishing-de-qad-v1 is a text generation model from Buttermilk03. Use it when you need the model to write or continue text. The card lists the license as other.
Training-tool attribution: These model weights are Generated Output from Praxist by Sapient Intelligence. The PRAXIST Fair Source License applies independently of the base-model license; see the pinned PRAXIST license.
Downloads · 30 days
5
6% of all-time downloads
All-time downloads
86
Public
Repo size
218 MB
Likes
0
Public
Click a slice to open those files.
.gguf218 MB · 100%
From the Hugging Face model README
Training-tool attribution: These model weights are Generated Output from Praxist by Sapient Intelligence. The PRAXIST Fair Source License applies independently of the base-model license; see the pinned PRAXIST license.
Modified derivative: These weights were modified by the open-source Scriber project from
LiquidAI/LFM2.5-350M-Baseat revision9960764e30892e01f29a6dc23df2533fcd8bd5ae. Liquid AI did not produce or endorse the modified model. See MODIFICATIONS.md and the included LFM Open License v1.0.
This is a small local German live-dictation post-processor. It cleans raw speech-to-text transcripts linguistically, typographically, and structurally while preserving content, order, numbers, names, and meaning. It is not a general-purpose assistant and must not answer questions found in a transcript.
The only model artifact is:
gguf/qad_q4_0/Scriber-LFM2.5-350M-Production-QAD-Q4_0.ggufe1ca3391d896db64df91c5ed5a02e16f5b6bbec5de81667ec99535eb7b1c0486No BF16, PTQ, Q8, or other quantized product alternative is published.
LiquidAI/LFM2.5-350M-Base, exact revision above
(354,483,968 parameters).f87067841bac583bc089a225382248d857791ca8.The exact 2,000 source/target pairs, split audit, complete accepted training
recipe, and lessons from the rejected runs are published in
Buttermilk03/scriber-lfm2.5-350m-polishing-de-training-v1.
The selected QAD artifact reproduced all 600 cases in the final local runtime regression exactly:
| Runtime regression | Cases | Exact | Safety rejection | Protected mutation |
|---|---|---|---|---|
| Long German letters | 200 | 200/200 | 0 | 0 |
| Short identity/noise cases | 400 | 400/400 | 0 | 0 |
| Total | 600 | 600/600 | 0 | 0 |
On an NVIDIA RTX 4070 Laptop GPU with llama.cpp b10158, measured median latency was about 687 ms for the long set and 196 ms for the short set. These 600 cases belong to the frozen training/validation recipe family and therefore establish runtime fidelity, not an unbiased estimate of generalization.
The separately retrained full-capacity H200 candidate reached 599/600 because it changed one protected amount. It was rejected; this repository contains the earlier 600/600 artifact.
Use deterministic greedy decoding with at most 384 new tokens and the exact plain-completion prompt below:
Aufgabe: Glätte das folgende deutsche Speech-to-Text-Transkript sprachlich, typografisch und strukturell. Bewahre Inhalt, Reihenfolge, Zahlen, Namen und Bedeutung. Füge nichts hinzu, beantworte keine Fragen und gib ausschließlich die bereinigte Fassung zurück.
Transkript:
${transcript}
Bereinigte Fassung:
The prompt SHA-256 is
e0ff2d5297f3d4d5ae7b8af85ea1cf52a24704bfb2e61990eab6de52b42058d8.
Do not expose model output without a preservation check. Scriber returns the original transcript whenever output is empty, oversized, repetitive, leaks control markers, changes protected numeric or lexical anchors, or otherwise violates the post-processing contract.
scriber-protection-policy.json contains the exact safety metadata used by
Scriber. The model itself receives the raw transcript without KEEP markers;
those markers must never appear in visible output.
The included LICENSE is mechanically unchanged from the pinned base-model
revision. The LFM Open License v1.0 includes a Commercial Use Limitation tied
to annual revenue; review the license itself before redistribution or
commercial deployment.
These weights were generated with Praxist by Sapient Intelligence. The pinned PRAXIST Fair Source License requires retaining that product-name attribution for third-party availability and defines a separate commercial license threshold. On 2026-09-01, the owner explicitly confirmed aggregate annual revenue of the licensee and all affiliates of USD 0, satisfying the free-license revenue condition for this open-source work.
This model card is descriptive and is not legal advice.