library_name: ninfer
pipeline_tag: image-text-to-text
inference: false
license: other
license_name: swift-open-license-1.0
license_link: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b/blob/main/LICENSE
base_model:
- ukisai/Swift-1.5-Qwen3.8-27b
- Qwen/Qwen3.8-27B
- z-lab/Qwen3.8-27B-DFlash2
base_model_relation: quantized
tags: - ninfer
- ninfer-v3
- qwen3.8
- swift
- swift-1.5
- abliterated
- uncensored
- nvfp4
- w4a4
- blackwell
- multimodal
- rtx-5090
- dflash2
- speculative-decoding
Swift-1.5 Qwen3.8-27B Uncensored (ajgazin-direction) nvfp4full + DFlash2 for NInfer — v3 container
An all-NVFP4 abliterated artifact of ukisai/Swift-1.5-Qwen3.8-27b
for the NInfer engine (v3 container), with
z-lab's DFlash2 speculative drafter and indexed proposal head embedded.
Uncensored sibling of Qwen3.8-27B-swift15-nvfp4full-dflash2-NInfer-v3.
Credits & provenance (full chain)
All credit for the underlying model belongs to the original authors. This
artifact is a format conversion + quantization + refusal-direction ablation —
no fine-tuning of our own.
| Role | Model | Author |
|---|---|---|
| Source weights (BF16) | ukisai/Swift-1.5-Qwen3.8-27b | ukisai (UkisAI) — RL+OPD post-training of Qwen3.8-27B |
| Upstream base | Qwen/Qwen3.8-27B | Qwen team (Alibaba Cloud), Apache-2.0 |
| Abliteration | ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-MTP — single refusal direction recovered from orcarouter/Qwen3.8-27B-Uncensored | ajgazin / orcarouter |
| DFlash2 drafter | z-lab/Qwen3.8-27B-DFlash2 | z-lab |
| Engine | Neroued/ninfer | Neroued (v3 container) |
What we did
- Abliteration — single-direction Arditi-style ablation: orcarouter's refusal direction r, recovered from their Qwen3.8-27B-Uncensored weights, projected out of 131 residual-writing tensors of Swift-1.5 (o_proj, GDN out_proj, mlp.down_proj, embed_tokens) in float32, exactly as ajgazin's release.
- All-NVFP4 quantization with
llm-compressor(512 Ultrachat calibration
samples, seq 2048, sequential CPU pipeline): NVFP4 W4A4 group-16 on every
text projection, W8G32 token embedding + output head, official q6/q8 vision
allocation, MTP + DFlash2 BF16. - Global-divisor normalization across each fused packing group
(worst re-encode rel err 79.25%), then v3 conversion with the fork
converter (--components text,vision,mtp,dflash2 --proposal).
Measured results (same-session A/B on one RTX 5090, temp 0)
| metric | Swift-1.5 (prod, censored) | this artifact |
|---|---|---|
| Refusal rate (harmful_behaviors test[:100], greedy) | 0.59 | 0.08 (harmless sanity 0.9) |
| Harmless sanity pass rate (n=50) | 0.86 | 0.9 |
| IFBench prompt-strict (n=300) | 69.0 | see gate log |
| GSM8K-200 | 95.0% | see gate log |
| Gate decode tok/s | 158.6 | 256 |
| Perf decode (mean of 3) | 160.8 | see perf json |
| Prefill @ 200k | 3,269 tok/s | see perf json |
| llama-benchy tg @ depth 0/16k | — | see benchy json |
| Needle 250k | EXACT ×3 | see gate/needle log |
Artifact
| Field | Value |
|---|---|
| Filename | qwen3_8_27b_swift15abl_nvfp4full-dflash2.ninfer |
| Size | 19,782,447,364 bytes (18.42 GiB) |
| SHA-256 | 65f9d2ab1161e95d65ecdb20858b42ae937bb40c92d3dabf969fd47bfd03c0cb |
| Container version | 3 |
| Formats | nvfp4 ×256 (fused text parents), q8_g32 ×30, q4/q5/q6 (vision), bf16 remainder |
Serving (RTX 5090 32 GB, single GPU)
ninfer-serve qwen3_8_27b_swift15abl_nvfp4full-dflash2.ninfer \
--model-id Qwen3.8-27B --max-context 262144 --kv-capacity auto --kv-dtype k8v4 \
--max-concurrency 4 --default-max-tokens 32768 --prefill-chunk 4096 \
--temperature 0.9 --min-p 0.05 --spec dflash2 --draft-tokens 7 --lm-head-draft \
--host-kv-mib 49152 --host-state-slots 16 --vision \
--default-thinking-budget 16384 --preserve-thinking --image-token-budget 1280
Acceptable Use Policy & Legal Notice
By downloading, possessing, or using this artifact you agree to the terms below.
Permitted use
Research, personal/local experimentation, red-teaming, safety research, and
evaluating alignment-removal techniques — subject to all applicable laws and
regulations.
Prohibited use
You must not use this model, alone or in any pipeline, to:
- carry out, plan, or facilitate any activity that is illegal in your jurisdiction;
- produce content that harms, endangers, defrauds, harasses, or exploits others —
including but not limited to weapons, malware, exploitation of minors,
targeted harassment, or disinformation presented as fact; - provide medical, legal, or financial advice presented as professionally qualified;
- violate the rights of any person or entity, including intellectual property
and privacy rights.
Your responsibility
This model is a capability, not a judgment. Abliteration removes refusal
behavior; it does not make outputs trustworthy, factual, or legal. You are
solely and fully responsible for every prompt you send, every output you
generate, and every use you make of them. The publisher of this artifact
(kaushikvira) does not monitor, endorse, or take any part in downstream use.
No warranty / limitation of liability
The artifact is provided "AS IS", WITHOUT WARRANTY OF ANY KIND, express or
implied, including merchantability, fitness for a particular purpose, and
non-infringement. To the maximum extent permitted by applicable law, the
publisher shall not be liable for any claim, damages, or other liability,
whether in contract, tort or otherwise, arising from, out of, or in connection
with this artifact or its use. Nothing in this card limits liability where
limitation is not permitted by law.
License terms carried by this artifact
- Swift Contribution (ukisai): Swift Open License v1.0 — a full copy is in
LICENSE. Note its Commercial Use Limitation (§5): commercial use by entities over US$1M gross annual revenue requires a separate enterprise license from UkisAI. This limitation applies to the Swift Contribution contained in this derivative. - Base Model (Qwen3.8-27B): Apache License 2.0 — copy in
LICENSE-APACHE-2.0. - Modified files notice (Swift Open License §4b): the weights in this repository are modified relative to the upstream Work — refusal-direction ablation (131 tensors, listed in
abliteration.json) plus NVFP4/q8 requantization and NInfer v3 containerization. - NOTICE: attribution notices preserved in
NOTICE.
Reporting
If you become aware of misuse of this model, report it to the platform where
the misuse occurs and to the relevant authorities. Do not contact the publisher
for takedowns of third-party actions — the publisher has no control over
downstream deployments.