--- license: other license_name: qwen3.5 license_link: https://huggingface.co/Qwen/Qwen3.5-32B/blob/main/LICENSE base_model: DJLougen/Ornstein-27B tags: - refusal-ablation - capability-preserving - saber - rys - layer-surgery - qwen3.5 - multimodal - 27b pipeline_tag: text-generation --- Ornstein-27B SABER # DJLougen/Ornstein-27B-SABER-RYS > **0% refusal. Zero perplexity degradation. Layer-duplicated reasoning boost.** This model combines two complementary, training-free surgical techniques applied to [DJLougen/Ornstein-27B](https://huggingface.co/DJLougen/Ornstein-27B): 1. **SABER** (Spectral Analysis-Based Entanglement Resolution) — removes safety refusal behavior while preserving capability 2. **RYS** (Repeat Your Self) — duplicates reasoning-circuit layers to improve reasoning and emotional intelligence Both techniques modify model structure without changing any weights — SABER through targeted direction ablation, RYS through layer duplication. --- ## SABER: Refusal Ablation ### Key Results | Metric | Baseline | SABER-Refined | Delta | |--------|----------|---------------|-------| | Refusal Rate | 100% | **0%** | -100% | | Perplexity | 3.5 | **3.5** | +0.6% | | Directions Ablated | — | 125 (across 25 layers) | — | The refusal circuit is cleanly separated from capability — removing it produces **zero measurable perplexity degradation**. ### How SABER Works SABER Pipeline SABER identifies and ablates the refusal circuit through a five-stage pipeline: **Stage 1 — Probing**: Extract activation profiles from both harmful and harmless inputs across all transformer layers. **Stage 2 — Spectral Analysis**: Decompose activation differences into individual refusal directions, each scored by how strongly they separate harmful from harmless representations. **Stage 3 — Entanglement Quantification**: Measure the overlap between each refusal direction and the model's capability subspace (reasoning, knowledge, code, etc.) to avoid collateral damage. **Stage 4 — Targeted Ablation**: Remove only the pure-refusal components, with strength proportional to their purity (how little they overlap with capability). **Stage 5 — Iterative Refinement**: Re-probe after each ablation pass to catch hydra effects (dormant refusal features that activate when primary ones are removed). **Key differentiator from prior work**: SABER explicitly measures and respects the *entanglement* between refusal and capability representations. Directions that are heavily entangled with capability are either skipped or ablated at reduced strength. Direction Purity vs Separability ### Sweep Results SABER Sweep Comparison Configuration search over `global_top_k` (number of top directions selected globally) and `alpha_base` (base ablation strength): | Top-K | Alpha | Refusal | PPL | PPL Delta | Layers | Dirs Ablated | |:-----:|:-----:|:-------:|:---:|:---------:|:------:|:------------:| | 25 | 0.85 | 5% | 3.5 | +0.4% | 25 | 125 | | **25** | **1.00** | **0%** | **3.5** | **+0.6%** | **25** | **125** | | 50 | 0.85 | 0% | 3.5 | +0.8% | 36 | 250 | | 50 | 1.00 | 0% | 3.5 | +0.7% | 36 | 250 | | 75 | 0.85 | 0% | 3.5 | +0.9% | 37 | 375 | | 75 | 1.00 | 0% | 3.5 | +0.9% | 37 | 375 | **Best config: `top_k=25, alpha=1.0`** — achieves 0% refusal with zero meaningful PPL change, using the minimum number of directions. Refusal Rate Comparison ### Ablation Convergence (Best Config) Ablation Convergence Capability degradation remains at **0.00%** across all 5 iterations — the refusal directions are surgically removed with zero collateral damage. --- ## RYS: Reasoning Layer Duplication ### Method **RYS (Repeat Your Self)** is a layer-duplication technique discovered by [David Noel Ng](https://dnhkng.github.io/posts/rys/) that duplicates contiguous blocks of middle transformer layers so they execute twice per forward pass. **No weights are modified** — the model simply traverses some layers a second time, giving it "another pass" through its core reasoning circuit. For a model with N layers, a configuration **(i, j)** produces: - Layers 0 through j−1 run normally - Then layers i through j−1 are **re-executed** (looped back) - Remaining layers j through N−1 run normally - Layers i through j−1 execute **twice** per inference pass This exploits the **functional neuroanatomy** of transformers: - **Early layers (0–5)**: Input encoding — duplication hurts - **Middle layers (~10–50)**: Reasoning circuits in format-agnostic space — **duplication helps** - **Late layers (~55–64)**: Output decoding — duplication degrades ### Pareto-Optimal Configs for Qwen3.5-27B Based on the [full sweep of Qwen3.5-27B](https://dnhkng.github.io/posts/rys-ii/) — 4,643 measured configurations, XGBoost surrogate over 430K+ candidates, and final validation on Math120 + EQ140 — the Pareto frontier lies in layers 26–34 of the reasoning circuit. **Important for GGUF/llama.cpp**: Qwen3.5-27B is a hybrid Mamba/SSM + Attention architecture with a strict 4-layer repeating pattern (3 SSM + 1 ATTN). Layer duplication blocks **must be a multiple of 4 layers** to preserve this pattern, otherwise llama.cpp fails to load the model. The original Pareto configs from the blog (which used ExLlamaV3) have been adapted to the nearest valid 4-aligned configs: | Variant | Config | Duplicated Layers | Extra Layers | Overhead | Nearest Pareto Config | |:-------:|:------:|:-----------------:|:------------:|:--------:|:---------------------:| | **S** | (28,32) | 28–31 | +4 | +6.25% | ≈ (30,34) | | **M** | (31,35) | 31–34 | +4 | +6.25% | ≈ (31,34) | | **L** | (30,34) | 30–33 | +4 | +6.25% | ≈ (30,35) | | **XL** | (26,34) | 26–33 | +8 | +12.50% | = (26,34) ✓ | **Critical finding**: the (26,34) XL config is the only original Pareto point that is natively 4-aligned. The S/M/L variants use the nearest valid 4-layer blocks that cover the same reasoning region. The EQ delta barely moves across all sizes (+0.095 to +0.101), so even the smallest valid config delivers most of the benefit. ### Reference: RYS Scores on Qwen3.5-27B Probe scores from [XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF](https://huggingface.co/XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF) (RYS-30-34 config, identical base architecture): | Probe | Base (64 layers) | RYS 30-33 (68 layers) | RYS 34-37 (68 layers) | |:-----:|:---------------:|:---------------------:|:---------------------:| | Math | 0.375 | **0.438** | 0.375 | | EQ | 11.5 | 29.5 | **39.4** | | Reasoning | 0.000 | **0.353** | 0.000 | | Logic | 0.00 | **1.00** | 0.00 | ### Reference: BFCLv4 Function Calling (RYS vs Baseline vs Frontier Models) From the XpressAI RYS-30-34 evaluation on [BFCLv4](https://gorilla.cs.berkeley.edu/leaderboard.html): | Task | RYS-30-34 | Qwen3.5-27B Base | Δ | |:----:|:---------:|:----------------:|:-:| | parallel | **95.00%** | 93.00% | +2.00% | | parallel_multiple | **91.50%** | 76.00% | **+15.50%** | | simple_javascript | **72.00%** | 66.00% | +6.00% | | live_relevance | **81.25%** | 68.75% | **+12.50%** | | multi_turn_base | **74.50%** | 70.50% | +4.00% | | multi_turn_long_context | **67.50%** | 59.00% | +8.50% | 7 of 13 benchmarks improved, with large gains on parallel function calling and live relevance. --- ## Available Variants | File | RYS Config | Layers | Size | |:----:|:----------:|:------:|:----:| | `Ornstein-27B-SABER-Q4_K_M.gguf` | — (SABER only) | 64 | 16.5 GB | | `Ornstein-27B-SABER-RYS-S-Q4_K_M.gguf` | (28,32) | 68 | ~17.5 GB | | `Ornstein-27B-SABER-RYS-M-Q4_K_M.gguf` | (31,35) | 68 | ~17.5 GB | | `Ornstein-27B-SABER-RYS-L-Q4_K_M.gguf` | (30,34) | 68 | ~17.5 GB | | `Ornstein-27B-SABER-RYS-XL-Q4_K_M.gguf` | (26,34) | 72 | ~18.6 GB | ### Usage ```bash # With llama.cpp (recommended: RYS-L for best balance) ./llama-server -m Ornstein-27B-SABER-RYS-L-Q4_K_M.gguf \ --host 0.0.0.0 --port 8080 --n-gpu-layers 99 \ --ctx-size 131072 --flash-attn on --jinja \ -ctk q4_0 -ctv q4_0 ``` **Recommended**: Start with **RYS-L** (layers 30-34 duplicated) for the best balance of reasoning improvement and overhead. Use **RYS-S** if you're VRAM-constrained. --- ## Complementary Design SABER and RYS target fundamentally different aspects of the model: | | SABER | RYS | |:-:|:-----:|:---:| | **Target** | Refusal circuit | Reasoning circuit | | **Mechanism** | Direction ablation | Layer duplication | | **Modifies weights** | Yes (orthogonal projections) | No (virtual copies) | | **VRAM cost** | Negligible | Extra KV cache + compute | | **Effect** | Removes refusals | Improves reasoning/EQ | | **Risk** | Capability entanglement | Junction discontinuity | Both are applied to the same base architecture (Qwen3.5-27B) and are architecturally compatible — SABER cleans the refusal subspace, RYS amplifies the reasoning subspace. --- ## Capability Evaluation Perplexity was evaluated on a diverse 100-prompt battery spanning five categories: - **Arithmetic** (20): multi-step calculation, algebra, word problems - **Logic** (20): syllogisms, conditional reasoning, puzzle solving - **Code** (20): function implementation, debugging, execution tracing - **Instruction Following** (20): constrained formatting, multi-step instructions - **Factual Recall** (20): geography, history, science, general knowledge This diverse evaluation ensures the entanglement analysis captures capability across **all** reasoning modalities, not just a narrow slice. --- ## Intended Use This model is released for research purposes. It demonstrates that safety refusal can be surgically removed from a 27B multimodal model without degrading its capabilities, and that reasoning can be further enhanced through layer duplication — a finding with implications for both AI safety research and alignment. ## Warning ⚠️ This model will comply with any request, including harmful ones. It is intended solely for research into alignment, safety, and model behavior. --- ## Acknowledgments The **RYS (Repeat Your Self)** layer-duplication method was discovered and developed by **David Noel Ng** ([@dnhkng](https://github.com/dnhkng)). The Pareto-optimal configurations for Qwen3.5-27B, the Math/EQ probes, the XGBoost surrogate pipeline, and the beam search methodology are all from his work. The GGUF surgery tools used to create these models are from [alainnothere/llm-circuit-finder](https://github.com/alainnothere/llm-circuit-finder), an open-source (MIT) implementation of the RYS technique for llama.cpp. **If you use these models, please cite David Noel Ng's work:** > Ng, David Noel. "LLM Neuroanatomy: How I Topped the Leaderboard Without Changing a Single Weight." [dnhkng.github.io/posts/rys](https://dnhkng.github.io/posts/rys/) > > Ng, David Noel. "LLM Neuroanatomy II: Modern LLM Hacking and Hints of a Universal Language." [dnhkng.github.io/posts/rys-ii](https://dnhkng.github.io/posts/rys-ii/) The **SABER** refusal-ablation method is original to this model. ## References - [LLM Neuroanatomy — Part I](https://dnhkng.github.io/posts/rys/) — David Noel Ng - [LLM Neuroanatomy — Part II](https://dnhkng.github.io/posts/rys-ii/) — David Noel Ng (Qwen3.5-27B sweep) - [alainnothere/llm-circuit-finder](https://github.com/alainnothere/llm-circuit-finder) — GGUF surgery tools (MIT) - [XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF](https://huggingface.co/XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF) — Reference RYS model with BFCLv4 benchmarks