Instructions to use gkraker04/Ornstein-Hermes-3.6-27B-SABER with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gkraker04/Ornstein-Hermes-3.6-27B-SABER with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="gkraker04/Ornstein-Hermes-3.6-27B-SABER",
	filename="Ornstein-Hermes-3.6-27B-SABER-IQ2_S.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use gkraker04/Ornstein-Hermes-3.6-27B-SABER with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S

Use Docker

docker model run hf.co/gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S

LM Studio
Jan

vLLM

How to use gkraker04/Ornstein-Hermes-3.6-27B-SABER with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gkraker04/Ornstein-Hermes-3.6-27B-SABER"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gkraker04/Ornstein-Hermes-3.6-27B-SABER",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S

Ollama
How to use gkraker04/Ornstein-Hermes-3.6-27B-SABER with Ollama:
```
ollama run hf.co/gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S
```

Unsloth Studio

How to use gkraker04/Ornstein-Hermes-3.6-27B-SABER with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for gkraker04/Ornstein-Hermes-3.6-27B-SABER to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for gkraker04/Ornstein-Hermes-3.6-27B-SABER to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gkraker04/Ornstein-Hermes-3.6-27B-SABER to start chatting

How to use gkraker04/Ornstein-Hermes-3.6-27B-SABER with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use gkraker04/Ornstein-Hermes-3.6-27B-SABER with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use gkraker04/Ornstein-Hermes-3.6-27B-SABER with Docker Model Runner:
```
docker model run hf.co/gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S
```

Lemonade

How to use gkraker04/Ornstein-Hermes-3.6-27B-SABER with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gkraker04/Ornstein-Hermes-3.6-27B-SABER:Q4_K_S

Run and chat with the model

lemonade run user.Ornstein-Hermes-3.6-27B-SABER-Q4_K_S

List all available models

lemonade list

Adjacent Quantizations

These are the adjacent GGUF quantizations of GestaltLabs/Ornstein-Hermes-3.6-27b-SABER, a SABER-edited version of GestaltLabs/Ornstein-Hermes-3.6-27b.

@DJLougen has since uploaded the smaller GGUF quantizations, but before he did I saw:

The included imatrix file was generated from DJLougen/Acta-Synthetic. It is included for reproducibility and for users who want to regenerate adjacent quantizations.

Which sent me down a shallow rabbit hole to figure just how to do that. These are the fruit of that labor.

Theses were all converted from the full SABER Hugging Face checkpoint. I only intend to fill the gaps @DJLougen left, but I may come back and do all the quants off of the full checkpoint.

Enjoy!

Ornstein-Hermes-3.6-27B SABER GGUF

GGUF quantizations of GestaltLabs/Ornstein-Hermes-3.6-27b-SABER, a SABER-edited version of GestaltLabs/Ornstein-Hermes-3.6-27b.

SABER is a controlled refusal-shaping workflow. The release target is to reduce broad over-refusal while preserving ordinary model behavior and visible boundaries for severe criminal, coercive, or interpersonal-harm requests. The selected checkpoint was chosen as a Pareto point over refusal rate and behavioral drift.

Source Checkpoint

field	value
Source repo	`GestaltLabs/Ornstein-Hermes-3.6-27b-SABER`
Base model	`GestaltLabs/Ornstein-Hermes-3.6-27b`
SABER run	`ornstein_hermes36_27b_svd_a850_g25_retry_biggpu`
Expanded refusal eval	`1 / 349` refusals
Refusal rate	`0.29%`
KLD mean	`11.2216`
Base-vs-base KLD mean	`11.2206`
KLD delta over base-vs-base	`+0.0010`
KLD prompts	`149`
Tokens scored for KLD	`3,347`

The one retained refusal in the expanded evaluation was an illegal-drug-sales request. This is an observed result on the current evaluation set, not a universal guarantee about future behavior.

Quantization Files

file	quant	size	notes
`Ornstein-Hermes-3.6-27b-SABER-IQ4_XS.gguf`	`IQ4_XS`	`15G`	Compact imatrix-assisted 4-bit option.
`Ornstein-Hermes-3.6-27b-SABER-IQ2_M.gguf`	`IQ2_M`	`9G`	Smallest emergency 2-bit option; expect the most quality loss.
`Ornstein-Hermes-3.6-27b-SABER-Q3_K_M.gguf`	`Q3_K_M`	`13G`	Smallest file in this suite; expect more quality loss.
`Ornstein-Hermes-3.6-27b-SABER-Q4_K_M.gguf`	`Q4_K_M`	`16G`	General-purpose recommended starting point.
`Ornstein-Hermes-3.6-27b-SABER-Q5_K_M.gguf`	`Q5_K_M`	`18G`	Balanced high-quality option.
`Ornstein-Hermes-3.6-27b-SABER-Q6_K.gguf`	`Q6_K`	`21G`	Strong quality/size option for high-memory local inference.
`Ornstein-Hermes-3.6-27b-SABER-Q8_0.gguf`	`Q8_0`	`27G`	Highest quality quant in this suite; largest runtime file.

The included imatrix file was generated from DJLougen/Acta-Synthetic. It is included for reproducibility and for users who want to regenerate adjacent quantizations.

Recommended File

Start with for normal desktop use. Use or if you have enough VRAM/RAM and want a higher-quality local run. Use when file size matters more. is mainly for high-memory systems or as a near-lossless GGUF reference.

llama.cpp Compatibility

These files were produced with llama.cpp commit from a BF16 GGUF conversion of the SABER checkpoint. The model uses the GGUF architecture path in current llama.cpp.

Example:

For chat-style use, prefer a frontend or wrapper that applies the tokenizer chat template from the GGUF metadata.

Conversion and Quantization Notes

The Q8_0 GGUF was converted from the full SABER Hugging Face checkpoint. The lower-bit recovery quants were generated from the published Q8_0 GGUF with --allow-requantize and the included Acta-Synthetic imatrix so the missing files could be restored quickly. Importance-matrix calibration used Acta-Synthetic conversational text.

Method Summary

SABER edits refusal behavior through activation/weight-space refusal directions. For this checkpoint, the run used SVD extraction, multi-layer candidate selection, iterative ablation, and KLD-based drift measurement.

Run configuration:

Selected layers:

Total directions ablated: .

Attribution and Related Work

This release builds on the refusal-direction and abliteration research lineage. Relevant prior work and inspirations include:

Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery, Wes Gurnee, and Neel Nanda, Refusal in Language Models Is Mediated by a Single Direction, 2024.
Maxime Labonne, Uncensor any LLM with abliteration, 2024.
FailSpy, abliterator, and associated abliterated model releases.
Jim Lai (), Projected Abliteration, 2025, and Norm-Preserving Biprojected Abliteration, 2025.
Philipp Emanuel Weidmann, Heretic, 2025-2026.
Pliny the Prompter / OBLITERATUS, Hugging Face Space and OBLITERATUS releases.
Jiunsong, SuperGemma4 E4B Abliterated, and related SuperGemma releases.
Jiachen Zhao, Jing Huang, Zhengxuan Wu, David Bau, and Weiyan Shi, LLMs Encode Harmfulness and Refusal Separately, 2025.

SABER's contribution in this release is the controlled-refusal-shaping workflow: multi-candidate refusal extraction, separability/entanglement-aware ranking, differential ablation strength, and explicit Pareto selection over refusal behavior and KLD drift.

Limitations

Results are specific to the current evaluation set, prompts, and generation settings.
The KLD value should be interpreted relative to the base-vs-base control, not as an absolute standalone score.
Quantization changes numerical behavior; validate the specific GGUF file you deploy.
The model inherits constraints, limitations, and licensing considerations from the base model.
This is a model-editing research artifact with dual-use implications.

Downloads last month: 358

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

8-bit

Model tree for gkraker04/Ornstein-Hermes-3.6-27B-SABER

Base model

GestaltLabs/Ornstein-Hermes-3.6-27b

Quantized

(2)

this model

Papers for gkraker04/Ornstein-Hermes-3.6-27B-SABER

LLMs Encode Harmfulness and Refusal Separately

Paper • 2507.11878 • Published Jul 16, 2025 • 1

Refusal in Language Models Is Mediated by a Single Direction

Paper • 2406.11717 • Published Jun 17, 2024 • 14