Ornith-1.0-35B-AEON-Uncensored

Instructions to use ansulev/Ornith-1.0-35B-AEON-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ansulev/Ornith-1.0-35B-AEON-Uncensored with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ansulev/Ornith-1.0-35B-AEON-Uncensored")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ansulev/Ornith-1.0-35B-AEON-Uncensored")
model = AutoModelForMultimodalLM.from_pretrained("ansulev/Ornith-1.0-35B-AEON-Uncensored", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ansulev/Ornith-1.0-35B-AEON-Uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ansulev/Ornith-1.0-35B-AEON-Uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ansulev/Ornith-1.0-35B-AEON-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ansulev/Ornith-1.0-35B-AEON-Uncensored

SGLang

How to use ansulev/Ornith-1.0-35B-AEON-Uncensored with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ansulev/Ornith-1.0-35B-AEON-Uncensored" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ansulev/Ornith-1.0-35B-AEON-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ansulev/Ornith-1.0-35B-AEON-Uncensored" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ansulev/Ornith-1.0-35B-AEON-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ansulev/Ornith-1.0-35B-AEON-Uncensored with Docker Model Runner:
```
docker model run hf.co/ansulev/Ornith-1.0-35B-AEON-Uncensored
```

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

An uncensored / abliterated build of 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:

SSM conv1d outlier repair (FernflowerAI method) — rescaled 2 outlier blocks (layers 36/37, σ 0.10→0.062) before abliteration to prevent coherence collapse.
Abliteration with abliterix v1.9: 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.
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)

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 (MIT)
Driver: abliterix (Wangzhang Wu) · upstream 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).

Downloads last month: 17

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for ansulev/Ornith-1.0-35B-AEON-Uncensored

Base model

deepreinforce-ai/Ornith-1.0-35B

Finetuned

(18)

this model

Collection including ansulev/Ornith-1.0-35B-AEON-Uncensored

fine-tune-model-sources

Collection

10 items • Updated 1 day ago