Laguna-XS-2.1-DFlash-GGUF

Laguna XS 2.1 DFlash GGUF

This repository contains a Q8_0 GGUF conversion of Poolside's DFlash drafter for Laguna XS 2.1. It is an auxiliary draft model. It is not a standalone language model and does not include the Laguna XS 2.1 target weights.

Artifact

The GGUF has five DFlash layers and target taps [2, 14, 26, 34, 40]. Its 41 matrix tensors use Q8_0. Its 23 normalization and bias tensors remain F32.

Download

hf download dev7a/Laguna-XS-2.1-DFlash-GGUF Laguna-XS-2.1-DFlash-Q8_0.gguf

Use this drafter only with a compatible Laguna XS 2.1 target and a runtime that supports the standardized llama.cpp dflash GGUF schema. In NS4, use catalog coordinate dev7a/laguna-xs:dflash.

Provenance and reproduction

The source weights are Poolside's SafeTensors at revision 5c36361aab23c8ed3afbd079c10c426b677bc607. The target tokenizer comes from Laguna XS 2.1 revision e9df9a59996d790b94b70f3fef343fe1d9e34bdf. Conversion uses Poolside's llama.cpp revision 06f8cebd7fe728687be3d19f8bdedb70d75883af.

The source manifest records every downloaded file, byte size, and SHA-256. The dependency locks contain hashes and use binary packages only. The released file and a clean repeated conversion were byte-identical.

Reproduce on Linux AArch64 with Python 3.12:

python3.12 scripts/download_sources.py --destination sources
python3.12 scripts/reproduce.py --sources sources --repeat-check

Verify the release without third-party Python packages:

python3.12 scripts/verify.py Laguna-XS-2.1-DFlash-Q8_0.gguf

This is a community conversion, not an official Poolside release. The weights remain under OpenMDW-1.1. The unmodified upstream license is in LICENSE. The conversion-code license and third-party notices are in LICENSE.code and THIRD_PARTY_NOTICES.md.