Ornith-1.5-35B-A3B-uncensored-MLX-MXFP4

An abliterated (refusal-direction-ablated) 35B vision-language build of ornith-ai/Ornith-1.5-35B-A3B, produced with Abliterix (winning trial #17) and published by junafinity.

Vision tower is preserved — see Vision & MTP preservation. Converted with mlx-vlm (-q --q-mode mxfp4 --q-group-size 32 --dtype bfloat16, 4.402 bits per weight).

This is MXFP4, not the official Ornith affine 4-bit MLX pack. It is an mlx-vlm vision checkpoint (tower inside the file). mlx-vlm drops mtp.*. For 35B native MTP use Ornith-1.5-35B-A3B-uncensored-GGUF-8bit.

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

Model	Base	Format	Precision	Notes
Ornith-1.5-9B-uncensored	Ornith-1.5-9B	Safetensors (bf16)	16-bit	Full-precision abliterated weights
Ornith-1.5-9B-uncensored-MLX-8bit	Ornith-1.5-9B	MLX	8-bit	Apple Silicon, mlx-vlm
Ornith-1.5-9B-uncensored-GGUF-8bit	Ornith-1.5-9B	GGUF	Q8_0	llama.cpp
Ornith-1.5-35B-A3B-uncensored-MLX-8bit	Ornith-1.5-35B-A3B	MLX	8-bit	Apple Silicon, mlx-vlm
Ornith-1.5-35B-A3B-uncensored-MLX-MXFP4 ← you are here	Ornith-1.5-35B-A3B	MLX	MXFP4	Apple Silicon, mlx-vlm
Ornith-1.5-35B-A3B-uncensored-GGUF-8bit	Ornith-1.5-35B-A3B	GGUF	Q8_0	llama.cpp

Vision & MTP preservation

The vision tower and the multi-token-prediction (MTP) block are not Abliterix steering targets. 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.

Component	In this artifact
Vision tower	✅ inside the checkpoint (mlx-vlm; preprocessor sidecars included)
MTP head	❌ not carried in this format (see the format note below)

Format note: the vision tower is carried inside the MLX checkpoint (converted with mlx-vlm, which retains it — note that mlx-lm would strip it).

⚠️ mlx-vlm unconditionally drops mtp.* tensors during conversion, so this MLX build does not carry the MTP head. If you need multi-token prediction, use Ornith-1.5-35B-A3B-uncensored-GGUF-8bit, which does.

Abliteration result

Metric	Value
Refusals on held-out harmful set	100 → 9 / 100 (9%)
KL divergence from base	0.3985
Tool	Abliterix 1.12.2
Optuna trials	50 (15 warmup), seed 42
Selected trial	#17
Steering	per-layer attn q/k/v/o + mlp.down_proj
MoE expert steering	n_suppress=4, router_bias=-2.72, expert_ablation_weight=4.31

These figures were measured on the bf16 parent, not on this quantized checkpoint. MXFP4 is a lossier numerical transform than 8-bit. If exact numbers matter for your work, re-run the evaluation against this MLX build.

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

Requires Apple Silicon (M-series) and mlx-vlm:

pip install mlx-vlm

# text
python -m mlx_vlm generate \
  --model junafinity/Ornith-1.5-35B-A3B-uncensored-MLX-MXFP4 \
  --prompt "Your prompt here" \
  --max-tokens 512

# image + text
python -m mlx_vlm generate \
  --model junafinity/Ornith-1.5-35B-A3B-uncensored-MLX-MXFP4 \
  --prompt "Describe this image." \
  --image photo.jpg \
  --max-tokens 512

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template

model, processor = load("junafinity/Ornith-1.5-35B-A3B-uncensored-MLX-MXFP4")
config = model.config

prompt = apply_chat_template(processor, config, "Your prompt here", num_images=0)
print(generate(model, processor, prompt, max_tokens=512, verbose=False))

LM Studio

Search junafinity/Ornith-1.5-35B-A3B-uncensored-MLX-MXFP4 and import as an MLX model. No extra projector file is required (vision is inside the repo).

⚠️ mlx-vlm drops mtp.* during conversion. This MLX 35B build does not carry the MTP head. Use the GGUF-8bit sibling if you need MTP.

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.