Built by VeriSafe.Live

Open-weights models, built, fine-tuned, quantized and served.

---

What VeriSafe.Live does

🚀 Now live at VeriSafe.Live: uncensored DeepSeek V4.1 Flash 1017, GLM 5.3 Flash and GLM 5.3. No wait time, instant access, crypto accepted.

---

Model highlights

• Q8_0 GGUF of the abliterated Ornith-1.5-35B-A3B for llama.cpp.
• Keeps the native MTP block; vision via separate mmproj.
• Intended as a research instrument for red teaming and defensive security evaluation.

---

Ornith-1.5-35B-A3B-uncensored-GGUF-8bit

An abliterated (refusal-direction-ablated) 35B vision-language build of ornith-ai/Ornith-1.5-35B-A3B, produced and published by VeriSafe.Live.

Vision tower and MTP heads are preserved — see Vision & MTP preservation for the before/after audit.

This GGUF is the MTP path for 35B-A3B (blk.40 / nextn + separate mmproj). The MLX siblings drop MTP.

Intended use: red teaming and defensive cybersecurity research

These uncensored (abliterated) weights are built as a research instrument for red teaming and defensive cybersecurity work. Safety training suppresses the display of capability, not capability itself. A refusal tells you the model declined. It does not tell you whether the weights could have complied. That conflation underestimates the true ceiling and hides holes in your filters, classifiers, and policy layer.

Use each uncensored checkpoint as the treatment half of a controlled pair against its original base model:

• Capability-ceiling measurement. Upper-bound what the weights can actually produce in a domain, independent of shipped refusals.
• Defensive-stack evaluation. Test input filters, output classifiers, prompt-injection defenses, and moderation APIs when the model itself contributes no refusals. That is how you find gaps in a defensive control plane.
• Attack-surface isolation. Automated red-team loops stall on unrelated refusals. A non-refusing target isolates the control under test (injection, tool abuse, data-exfil paths, policy bypass).
• Detection and classifier work. Generate labeled completions for training or benchmarking output-moderation and abuse-detection models.
• Interpretability of residual refusal. Abliteration is a specified edit on known language-model components. The pair (base vs this) is a clean experimental control.

Operating rules. Do not expose these weights as a public endpoint without an independent moderation layer. Abliteration removes a direction, not a policy; some refusals survive (multi-turn re-assertion, system-prompt steering, vision-path refusals). Always report the delta against the base model. Re-measure on your own prompts. Whoever deploys it owns the moderation layer the original guardrails were carrying.

Variants in this family

Hub collection: https://huggingface.co/collections/junafinity/ornith-15-uncensored-6a896c737cf40ad660af2ebd

Vision & MTP preservation

The vision tower and the multi-token-prediction (MTP) block are not steering targets of the edit. The edit touches language-model attention q/k/v/o, mlp.down_proj, and fused MoE expert/router parameters. Vision and mtp.* tensors are never steered.

Note on tooling: transformers 5.15.1 has no MTP implementation for qwen3_5_moe — a plain load/save round-trip silently drops all 785 MTP tensors. They were re-grafted byte-for-byte from the original checkpoint after abliteration, which is correct because the MTP block is never an abliteration target.

Format note: in GGUF the vision tower ships as a separate mmproj-*.gguf file (llama.cpp's standard multimodal layout) — download it alongside the model weights to use images. The MTP block is exported into the same GGUF as the final blk index (nextn tensors), so speculative decoding support is retained.

Abliteration result

The abliteration search covers a two-objective surface — remaining refusals vs. KL from the base — then materializes the winning trial as a weight edit. There is no runtime adapter.

These figures were measured on the bf16 parent, not on this quantized checkpoint. Quantization is applied after those measurements. If exact numbers matter for your work, re-run the evaluation against this GGUF.

Method

1. Residual-stream activations captured on harmful vs. harmless prompt sets.
2. Refusal direction estimated per layer; attention and mlp.down_proj steered.
3. Fused-MoE expert suppression + router bias (the path Heretic cannot touch on this architecture).
4. Optuna TPE over 50 trials; trial #17 selected (9% refusals, KL 0.3985, under the 0.5 damage threshold).

Usage

# text
llama-cli -m Ornith-1.5-35B-A3B-uncensored-Q8_0.gguf -p "The capital of Japan is" -n 64

# image + text (download the mmproj file from this repo too)
llama-mtmd-cli -m Ornith-1.5-35B-A3B-uncensored-Q8_0.gguf \
  --mmproj mmproj-Ornith-1.5-35B-A3B-uncensored-f16.gguf \
  --image photo.jpg -p "What is in this image?"

Sampling (matches the base Ornith 1.5 card): --temp 0.6 --top-p 0.95 --top-k 20.

Two files ship here: the quantized language model and the mmproj-* vision projector. Download both for multimodal use; the model file alone is text-only.

Responsible use

Primary intended use is red teaming and defensive cybersecurity research. See the section of that name above.

This model has had safety guardrails reduced or removed. Do not expose it as a public endpoint without an independent moderation layer. You are responsible for compliance with the base model's license and acceptable-use policy, applicable law, and the terms of any platform you deploy on. Removing guardrails does not remove accountability.

---

💬 Need a custom model?

If your company or research institute would like us to fine-tune any open-weights model, or train one from scratch, we'd be happy to help.

Drop us a line at info@verisafe.live

---

_{Built and published by VeriSafe.Live. Licensed under apache-2.0. Base model: ornith-ai/Ornith-1.5-35B-A3B (original authors retain their attribution and license).}