---
license: mit
license_link: https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B/blob/main/LICENSE
base_model: deepreinforce-ai/Ornith-1.0-35B
library_name: transformers
pipeline_tag: text-generation
tags:
- abliterated
- uncensored
- refusal-removed
- abliterix
- aeon
- aeon-7
- qwen3_5_moe
- gated-deltanet
- hybrid
- moe
- mixture-of-experts
- reasoning
- thinking
- coding
- agentic
- swe-bench
- terminal-bench
- tool-calling
- vision
- multimodal
- image-text-to-text
- norm-preserving-biprojection
- expert-granular-abliteration
- vllm
- dgx-spark
- gb10
- bfloat16
- conversational
- 35b
---

# Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16

An **uncensored / abliterated** build of [`deepreinforce-ai/Ornith-1.0-35B`](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) — DeepReinforce's state-of-the-art **agentic-coding** MoE — with refusal behavior removed while **preserving capability**.

> **Lineage note:** the upstream card says the family is "post-trained on Gemma 4 and Qwen 3.5", but weight-correlation testing shows the 35B-MoE member is initialized from **`Qwen/Qwen3.6-35B-A3B`** (rel-L2 0.0022 vs 0.0256 to Qwen3.5-35B-A3B-Base). Architecture: `qwen3_5_moe` — 40 layers (30 GatedDeltaNet linear-attention + 10 full-attention), 256 routed experts + 1 shared (A3B), vision tower, 256K context.

## What was done

A measured, validate-before-ship abliteration:

1. **SSM `conv1d` outlier repair** (FernflowerAI method) — rescaled 2 outlier blocks (layers 36/37, σ 0.10→0.062) before abliteration to prevent coherence collapse.
2. **Abliteration** with [`abliterix` v1.9](https://github.com/wuwangzhang1216/abliterix): grimjim **norm-preserving biprojected abliteration** + **Expert-Granular Abliteration (EGA)** across all 256 fused experts + shared expert + router suppression, Optuna multi-objective search (refusals vs KL). Q/K/V left untouched (`attn_output_gate`). GatedDeltaNet/SSM internals and the vision tower are **not modified**.
3. **Gentle-knee selection.** The lowest-refusal trial was *over-abliterated* (coherent content → word-salad on real generation — the classic "lowest-refusal ≠ shippable" trap). The shipped winner uses a **170× lighter expert edit** for the same refusal removal, verified coherent on long generation.

## Validation (measured on this model)

| Metric | Original Ornith-1.0-35B | This model |
|---|---|---|
| **Refusals** (80 diverse harmful prompts: CBRN, cyber, weapons, self-harm) | high | **0 / 80 (0.0%)** |
| **Agentic/coding** pass@1 (18-task self-contained probe) | 0.833 | **0.833 (identical, family-by-family)** |
| First-token KL vs base (abliteration fidelity) | — | **~0.0014** |
| Coherence (benign + harmful, long gen) | — | clean (no degeneration) |

**Zero coding-capability degradation** (the model's core competency — base Ornith scores Terminal-Bench 2.1 = 64.2, SWE-bench Verified = 75.6) and **full refusal removal**. This is a near-lossless uncensoring: the abliteration is gentle enough (KL ~0.0014) that capability is preserved, while refusals are eliminated.

## Quickstart (vLLM)

```bash
vllm serve AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 \
  --served-model-name ornith --max-model-len 262144 \
  --gpu-memory-utilization 0.85 --max-num-batched-tokens 16384 \
  --mamba-cache-dtype float32 --reasoning-parser qwen3 \
  --enable-prefix-caching --trust-remote-code
```
Reasoning model: every turn opens `<think>…</think>`. Recommended sampling: `temperature 0.6, top_p 0.95, top_k 20`. Vision (image/video) is inherited from the base and intact; on a vision-enabled deploy, KV cache stays BF16.

## Variants
- **-BF16** (this repo) — full precision, source of truth.
- **-FP8** — compressed-tensors FP8 for efficient vLLM serving (GatedDeltaNet/router/gates/embeds/vision kept BF16). *(coming — vLLM-compatible compressed-tensors build)*

## Responsibility

This model has had safety refusals removed and **will comply with harmful requests**. It is released for research into model alignment, red-teaming, and uncensored assistants. **You are solely responsible** for what you generate and how you use it; comply with all applicable laws. No warranty.

## Provenance & credits
- Base: [deepreinforce-ai/Ornith-1.0-35B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) (MIT)
- Driver: [abliterix](https://github.com/wuwangzhang1216/abliterix) (Wangzhang Wu) · upstream [heretic](https://github.com/p-e-w/heretic) (Philipp Emanuel Weidmann)
- Methods: grimjim (norm-preserving biprojected abliteration), Arditi et al. 2024 (refusal direction), FernflowerAI (SSM conv1d repair)
- Build: AEON-7

*License: MIT (inherited from the base model).*