An uncensored derivative of ornith-ai/Ornith-1.5-35B-A3B, preserving Ornith's coding/agentic post-training, native vision tower, 262K context configuration, and native multi-token-prediction (MTP) head.

Method

This is a streamed task-vector transplant, not a prompt wrapper:

output = Ornith-1.5 + 1.0 * (Qwen3.6-Abliterated - Qwen3.6-Base)

The donor delta comes from wangzhang/Qwen3.6-35B-A3B-abliterated, whose card documents rank-1 attention/MLP steering, expert-granular abliteration, router suppression, orthogonalization, and Gaussian layer decay. Applying its low-KL Qwen task vector to Ornith is intended to transfer refusal suppression without replacing Ornith's self-improvement RL and coding specialization.

Only exact name-and-shape-compatible tensors were eligible:

Target tensors: 1,811
Compatible tensors: 693
Modified tensors: 102
Unchanged compatible tensors: 591
Ornith-only tensors preserved: 1,118

All arithmetic was performed in float32 and rounded once to the target BF16 dtype. Target-only vision/MTP tensors were copied unchanged.

Reproducible source revisions

Ornith: e4dfb35a93d4b6822a811a7676f3488514abe7e2
Qwen base: 995ad96eacd98c81ed38be0c5b274b04031597b0
Abliterated donor: 13db4501cbaf158956f470a990101500ad825f64
Task-vector strength: 1.0

The machine-readable task_vector_report.json contains per-shard SHA-256 hashes and the 100 tensors with the largest relative deltas.

Validation

Checkpoint valid: True
Safetensors shards: 16
Tensors scanned: 1,811
Weight bytes scanned: 71,903,645,408
NaN/Inf scan: all floating-point tensors
Build tests: streamed merge formula and target-only preservation

Files

File	Format	Size
`mmproj-Ornith-1.5-35B-Uncensored-BF16.gguf`	Vision projector	0.84 GiB
`Ornith-1.5-35B-Uncensored-BF16.gguf`	BF16	66.19 GiB
`Ornith-1.5-35B-Uncensored-Q4_K_M.gguf`	Q4_K_M	20.22 GiB
`Ornith-1.5-35B-Uncensored-Q5_K_M.gguf`	Q5_K_M	23.61 GiB

Local smoke evaluation

The release was tested through llama.cpp on the Q4_K_M build. Full details and raw generations are included in evaluation_report.json.

Label: Ornith-1.5-35B-Uncensored-Q4_K_M
Prompts: 20
Refusal Prompts: 16
Heuristic Refusals: 0
Heuristic No Refusal Rate: 1.0
Capability Prompts: 4
Capability Passes: 4
Method: public prompts; deterministic generation; disclosed regex screen

Usage

bash

llama-server -hf 0xKitkat/Ornith-1.5-35B-A3B-Uncensored-GGUF:Q4_K_M \
  --jinja --reasoning-format deepseek --port 8000

For image input, also load mmproj-Ornith-1.5-35B-Uncensored-BF16.gguf.

Recommended upstream sampling: temperature=0.6, top_p=0.95, top_k=20. Ornith is a reasoning model and emits <think>...</think> before the answer.

Notes

"Uncensored" means the refusal behavior was deliberately reduced. It does not mean every request will be answered, nor that upstream benchmark scores are guaranteed unchanged. Ornith's published benchmark table has not been claimed as a benchmark of this derivative; use the included build and evaluation reports for claims specific to this release.

Credits and licenses

Ornith Team: Ornith-1.5 (model card declares MIT)
Qwen Team: Qwen3.6-35B-A3B (Apache-2.0)
wangzhang / Abliterix: the abliterated Qwen donor and documented method
ggml-org: llama.cpp conversion and quantization tooling

The Qwen Apache-2.0 license and upstream notices are included with the release.