NOTICE

Swift-1.5-Qwen3.8-27B huihui-style abliterated NVFP4 NInfer artifact
====================================================================

This repository contains a single-file NInfer engine artifact (NVFP4/FP8
mixed-precision weights, container v3, with vision tower, MTP head and a
DFlash2 drafter) plus the build records that make it reproducible.

Licence
-------
The Swift 1.5 checkpoint is distributed under the Swift Open License v1.0 (see
LICENSE in this repository); this artifact is a derivative of it, so the Swift
Open License v1.0 continues to apply to the Swift Contribution it contains.
The Qwen3.8-27B base-model portion is Apache-2.0 (Copyright 2026 Alibaba Cloud;
see LICENSE-APACHE-2.0). The abliteration delta is derived from
huihui-ai/Huihui-Qwen3.8-27B-abliterated (Apache-2.0). The DFlash2 drafter is
z-lab/Qwen3.8-27B-DFlash2 (see its model card for its licence). Free commercial
use is subject to the $1,000,000-per-fiscal-year gross-revenue threshold of the
Swift Open License v1.0. This is a description, not legal advice.

Statement of changes (Swift Open License v1.0, sections 4-5)
------------------------------------------------------------
The weights in this repository are MODIFIED relative to the Swift 1.5 checkpoint:

1. Abliteration (weights changed). 70 tensors of the language model were changed
   by a per-tensor weight-difference transfer:
       W_ablated = W_swift15 + (W_huihui - W_qwen)      (fp32, rounded to bf16)
   where W_qwen is Qwen/Qwen3.8-27B and W_huihui is
   huihui-ai/Huihui-Qwen3.8-27B-abliterated. The changed tensors are the
   self_attn.o_proj / linear_attn.out_proj / mlp.down_proj matrices of language
   layers 17..51 (measured, not assumed; see ablation-report.json). Every other
   tensor - including all vision (model.visual.*), MTP (mtp.*), lm_head and
   embedding tensors - is bit-identical to Swift 1.5 (source-audit.json).
2. Quantization (numerical format changed). llm-compressor oneshot with the
   NVFP4+FP8 allocation of unsloth/Qwen3.8-27B-NVFP4 (recipe/unsloth_qconfig.json),
   32 calibration samples from ultrachat-200k, sequence length 2048.
3. Conversion (container format changed). Neroued/ninfer, official
   tools.convert, recipe qwen3_8_27b_nvfp4, components text,vision,mtp,dflash2,
   with the maintained tools/chat_templates/qwen3_8.jinja chat template.

Pinned inputs
-------------
  ukisai/Swift-1.5-Qwen3.8-27b              bc7a1e10b689648585a3ef41494c8d84cf77271a
  Qwen/Qwen3.8-27B                          1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0
  huihui-ai/Huihui-Qwen3.8-27B-abliterated  739e3c5b89849f6c238ce1e5b70008612ae42cdd
  z-lab/Qwen3.8-27B-DFlash2                 50307d4c4cde6860d4eee73e2547cd786fe8e8a4
  Neroued/ninfer                            bace20dc70249eed6402b66d4852c6c3f9612905

The refusal-rate evaluation code in recipe/ reproduces the keyword scorer of
p-e-w/heretic @ 3521f8648a0dccf6e12a92666862632235fac7e6
(heretic/scorers/keyword_rate.py, AGPL-3.0-or-later); the marker list is used
for comparability of numbers only.

The engine is built exclusively for NVIDIA Blackwell compute capability
12.0 (sm_120a).