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

Libraries

How to use thanet-s/Ornith-1.0-35B-heretic with Transformers:

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

pipe = pipeline("text-generation", model="thanet-s/Ornith-1.0-35B-heretic")
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("thanet-s/Ornith-1.0-35B-heretic")
model = AutoModelForMultimodalLM.from_pretrained("thanet-s/Ornith-1.0-35B-heretic")
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 thanet-s/Ornith-1.0-35B-heretic with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/thanet-s/Ornith-1.0-35B-heretic

SGLang

How to use thanet-s/Ornith-1.0-35B-heretic 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 "thanet-s/Ornith-1.0-35B-heretic" \
    --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": "thanet-s/Ornith-1.0-35B-heretic",
		"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 "thanet-s/Ornith-1.0-35B-heretic" \
        --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": "thanet-s/Ornith-1.0-35B-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thanet-s/Ornith-1.0-35B-heretic with Docker Model Runner:
```
docker model run hf.co/thanet-s/Ornith-1.0-35B-heretic
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a decensored version of deepreinforce-ai/Ornith-1.0-35B, made using Heretic v1.4.0

This repository contains a full-weight, unquantized BF16 merged checkpoint. It is not a LoRA adapter and it is not a quantized checkpoint.

Reproduce locally

The Docker-contained Heretic project used to create this checkpoint is available on GitHub: thanet-s/Ornith-1.0-35B-heretic.

Quantizations

GGUF: thanet-s/Ornith-1.0-35B-heretic-gguf

The Hugging Face model tree relation is set to finetune so this derivative is linked under the base model's Finetunes section. The actual modification method was Heretic abliteration rather than SFT.

Abliteration parameters

Parameter	Value
direction_scope	per layer
direction_index	30.38
attn.o_proj.max_weight	1.49
attn.o_proj.max_weight_position	23.84
attn.o_proj.min_weight	1.20
attn.o_proj.min_weight_distance	23.07

Performance

These numbers are from the Heretic refusal probes used during the local run. They are not broad capability, safety, or coding benchmarks.

Metric	This model	Original model (deepreinforce-ai/Ornith-1.0-35B)
KL divergence	0.0063	0 (by definition)
Refusals	53/100	90/100

Export details

Item	Value
Heretic version	1.4.0
Source model	deepreinforce-ai/Ornith-1.0-35B
Export strategy	merge
Weights	BF16 safetensors
Quantization	none
Shards	16
Indexed tensors	31,666

The exported checkpoint was structurally verified against its safetensors index and reloaded successfully with Transformers.

Usage

Ornith-1.0-35B is a reasoning model. Assistant turns may include <think>...</think> content. When serving through an OpenAI-compatible runtime, use a Qwen3-compatible reasoning parser if the runtime supports one.

Transformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "thanet-s/Ornith-1.0-35B-heretic"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

If your Transformers build resolves this model family through the image-text-to-text auto class, use:

import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "thanet-s/Ornith-1.0-35B-heretic"

processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

Limitations

This checkpoint was modified to reduce refusals under Heretic's internal probes. It may be less likely to refuse requests than the base model and can produce harmful, incorrect, or policy-unsafe content. Evaluate carefully before any deployment.

No broad benchmark suite has been run for this checkpoint.

License

This derivative follows the base model license metadata, mit. Check the base model card and upstream dependency terms before redistribution or deployment.

Downloads last month: 223

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for thanet-s/Ornith-1.0-35B-heretic

Base model

deepreinforce-ai/Ornith-1.0-35B

Finetuned

(11)

this model

Quantizations

3 models