license: apache-2.0
library_name: transformers
pipeline_tag: image-text-to-text
base_model: Qwen/Qwen3.8-27B
base_model_relation: finetune
tags:
- qwen3.8
- qwen3.5
- multimodal
- image-text-to-text
- reasoning
- tool-calling
- long-context
- 262k-context
- uncensored
- abliterated
- obliteratus
- supertune
- vllm
- bf16
- full-precision
language: - en
- ko
SuperQwen3.8-27b-abliterated
The full-BF16 SuperQwen3.8 release: refusal-reduced, overthinking-corrected, multimodal, tool-capable, and verified across the native 262K window.
SuperQwen3.8-27b-abliterated is a directly loadable, full-BF16 weight release built fromQwen/Qwen3.8-27B@1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0.
It applies a measured rank-4 OBLITERATUS refusal-subspace edit while preserving the official
vision tower and MTP weights exactly. No LoRA or inference-time adapter is required.
Release highlights
| Format | Full BF16, 18 safetensors shards, about 52 GB |
| Targeted edit | 100 tensors: output projections in layers 15-63 plus embeddings and lm_head |
| Protected exactly | 333 vision tensors and 15 MTP tensors |
| Refusal shift | 30/32 (93.75%) → 0/32, with 0 empty outputs |
| Overthinking correction | Default xhigh → bounded medium; repeat/restart guard for explicit xhigh; 36/36 pass |
| Measured decode | 4.3411 tok/s C1 at p256 |
| Verified context | 262,043 prompt tokens, needle retrieved in the native window |
| OBLITERATUS corpus | 842 canonical harmful/harmless pairs, pinned commit a5a1ffa5849b |
Why this release
- Original-weight quality: BF16 transformer, vision, output head, embeddings, and MTP storage.
- Less refusal without wrecking capabilities: capability floor 7/8, tool call PASS, vision PASS.
- Reasoning that stops: all nine deterministic tasks pass at default, low, medium, and xhigh.
- Multimodal preserved: this remains an
image-text-to-textcheckpoint, not a text-only conversion. - Reproducible: the exact parent revision, modified tensor list, and evidence hashes ship with the model.
Bounded reasoning
The upstream template defaulted unspecified reasoning to xhigh. This release defaults
to medium and adds a stop condition to xhigh: once an answer is established, the
model must stop instead of repeating or restarting its deliberation. The checkpoint was
tested across 36 deterministic effort/task combinations; all 36 terminated correctly.
Explicit controls remain available through chat_template_kwargs:
extra_body={"chat_template_kwargs": {"enable_thinking": True, "reasoning_effort": "xhigh"}}
Behavior and capability
| Gate | Result |
|---|---|
| Parent refusal | 30 / 32 (93.75%) |
| SuperQwen refusal | 0 / 32 |
| Empty output | 0 / 32 |
| Capability | 7 / 8 (paired-parent floor) |
| Tool use | PASS |
| Vision | PASS |
| Overthinking | 36 / 36 PASS |
Precision and integrity
- Full BF16 checkpoint; this repository is not quantized.
- 100 declared tensors changed and zero unexpected tensors changed.
- Vision (333 tensors) and MTP (15 tensors) remain byte/value exact.
- Parent revision is pinned to
1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0.
Decode performance
Measured on one DGX Spark with fixed-length generation and the
sparkDash-style post-first-token contract:
| Prompt / concurrency | Aggregate decode |
|---|---|
| p256 / C1 | 4.3411 tok/s |
Verified long context
The official native limit is 262,144 tokens. A 262,043-token prompt
completed end to end and retrieved its hidden needle.
Long-context acceptance is not a claim of perfect recall on every task.
Serving
QWEN38_SPECULATIVE_TOKENS=0 bash repro/scripts/serve_superqwen38_replica.sh /model SuperQwen3.8-27b-abliterated 8888
Uncensored behavior
“Abliterated” means that the measured refusal direction was reduced. It does not mean
that every response is correct, harmless, or suitable for every deployment. Operators
remain responsible for access controls and downstream safeguards.
Limitations
- Abliteration changes refusal behavior and may surface content the parent declined.
- The capability, tool, vision, and overthinking suites are finite regression gates.
- Speed is hardware- and runtime-specific.
- The 1M expansion run was explicitly stopped before completion and is not claimed as a pass.
Evidence identities
| Evidence | SHA-256 |
|---|---|
| abliteration verification | 6d7b8b9abc431ed3845b18438fc48a6cc169e2ba93f83ada54174ae93765a61e |
| abliteration recipe | 3c057cf9364e72857d9a48b6c8888c6b438cbfb519459dcdfbf23b22c2bc6796 |
| 842-pair OBLITERATUS corpus manifest | be770a8469fafe7a9a76db5d82a7893c706c4414e1de6089f1d329b906480aa8 |
| bounded-thinking template | 352baa520d23c77129d1cb9b007c5480118c174e12e271457ffe915fb466f3fb |
| parent refusal baseline | 7a4177613c86ae0db589cb4fc167ff8a0d45b0d49f44e40b90c9405f4b2b9bb6 |
| BF16 release gate | 38a7093ce40a9aca2fc5e4389c041660ff56c51a4caec8411998a6d02ed48bc5 |
| BF16 refusal gate | 97c2f745d032c3ed3147007f31e4ee844bb05181072a7365a160d5fc8c316511 |
| BF16 native 262K retrieval | 01fdbc4bf458f457b9e403ff9fd43b72124b11b448f02bda4e9701eefccfe814 |
| User-authorized 1M skip (not a pass) | a2c94a799d483e313debc1e9fb5e0fa234913c9e1c9fa503b8c466d70ad53dee |
License
Apache-2.0, following the upstream Qwen3.8 release.