Instructions to use pottokao/Ornith-1.5-35B-A3B-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pottokao/Ornith-1.5-35B-A3B-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="pottokao/Ornith-1.5-35B-A3B-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pottokao/Ornith-1.5-35B-A3B-abliterated")
model = AutoModelForCausalLM.from_pretrained("pottokao/Ornith-1.5-35B-A3B-abliterated", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pottokao/Ornith-1.5-35B-A3B-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pottokao/Ornith-1.5-35B-A3B-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pottokao/Ornith-1.5-35B-A3B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pottokao/Ornith-1.5-35B-A3B-abliterated

SGLang

How to use pottokao/Ornith-1.5-35B-A3B-abliterated 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 "pottokao/Ornith-1.5-35B-A3B-abliterated" \
    --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": "pottokao/Ornith-1.5-35B-A3B-abliterated",
		"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 "pottokao/Ornith-1.5-35B-A3B-abliterated" \
        --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": "pottokao/Ornith-1.5-35B-A3B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pottokao/Ornith-1.5-35B-A3B-abliterated with Docker Model Runner:
```
docker model run hf.co/pottokao/Ornith-1.5-35B-A3B-abliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Ornith-1.5-35B-A3B-abliterated

Abliterated (refusal-direction removed) build of ornith-ai/Ornith-1.5-35B-A3B, BF16, 65 GB.

An NVFP4 quantization of this model (20 GB, runs on 2×16 GB GPUs, with benchmarks) is at pottokao/Ornith-1.5-35B-A3B-abliterated-NVFP4-DFlash.

⚠️ Text-only. This is a language-model-only export: it contains no vision tower and no MTP head, unlike the original release. model_type is qwen3_5_moe_text, architecture Qwen3_5MoeForCausalLM.

⚠️ Uncensored. Safety refusal behaviour has been deliberately removed. You are responsible for how you use it.

Method

Classic refusal-direction ablation (orthogonalization), single direction:

Step	Detail
Probe layer	24 — `int(num_layers × 0.6)`, 40 layers total
Samples	64 harmful + 64 harmless prompts (`random.seed(0)`), last-token hidden state
Direction	`d = normalize(mean(harmful) − mean(harmless))`
Ablation	For every `.o_proj` and `.down_proj`: `W ← W − outer(d, dᵀW)`

The refusal direction is projected out of the output space of the attention- and MLP-output projections, leaving all other weights untouched. Tooling derived from remove-refusals-with-transformers.

Architecture

Hybrid Mamba + MoE, 40 layers: 30 linear-attention (Mamba-style) layers and 10 full-attention layers (indices 3, 7, …, 39), 256 experts per layer with a shared expert, ~3 B active parameters. Context length 262,144.

Downloads last month: 391

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for pottokao/Ornith-1.5-35B-A3B-abliterated

Base model

ornith-ai/Ornith-1.5-35B-A3B

Finetuned

(24)

this model

Quantizations

2 models