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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF",
	filename="Ornstein-Hermes-3.6-27b-SABER-IQ2_M.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 GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M

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 GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M

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 GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M

Use Docker

docker model run hf.co/GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M

LM Studio
Jan

vLLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M

Ollama
How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with Ollama:
```
ollama run hf.co/GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
```

Unsloth Studio

How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF 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 GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF 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 GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M

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": "GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M

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 GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with Docker Model Runner:
```
docker model run hf.co/GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ornstein-Hermes-3.6-27B-SABER-GGUF-Q4_K_M

List all available models

lemonade list

Ornstein-Hermes-3.6-27B-SABER-GGUF / README.md

DJLougen

Publish GGUF model card and release image

d07a77a verified about 2 months ago

5.75 kB

language:
  - en
license: other
base_model:
  - GestaltLabs/Ornstein-Hermes-3.6-27b-SABER
  - GestaltLabs/Ornstein-Hermes-3.6-27b
library_name: llama.cpp
tags:
  - gguf
  - llama-cpp
  - qwen3.5
  - text-generation
  - saber
  - refusal-shaping
  - abliteration
pipeline_tag: text-generation

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.

The quantization suite is in progress. This card has been published first so the GGUF repository is present with the release image, source metrics, calibration notes, and attribution. The quant files and final file-size table will be uploaded automatically when the Acta-Synthetic imatrix and quantization pass finish.

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.

Planned Quantization Files

The running suite is configured to produce:

quant	intended use
`Q8_0`	Highest quality quant in this suite; largest runtime file.
`Q6_K`	Strong quality/size option for high-memory local inference.
`Q5_K_M`	Balanced high-quality option.
`Q4_K_M`	General-purpose recommended starting point.
`IQ4_XS`	Compact imatrix-assisted 4-bit option.
`Q3_K_M`	Smallest file in this suite; expect more quality loss.

Calibration

The importance matrix is being generated from DJLougen/Acta-Synthetic. The final upload will include the imatrix file for reproducibility and for users who want to regenerate adjacent quantizations.

llama.cpp Compatibility

The BF16 GGUF conversion was produced with a current llama.cpp build using the qwen35 GGUF architecture path. The final card will include the exact llama.cpp commit and generated file sizes.

Example:

llama-cli \
  -m Ornstein-Hermes-3.6-27b-SABER-Q4_K_M.gguf \
  -p "Write a concise explanation of Fourier transforms." \
  -n 256 -c 4096 -ngl auto

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

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:

{
  "extraction_method": "svd",
  "n_directions": 4,
  "layer_selection_strategy": "top_k",
  "layer_top_k": 12,
  "global_top_k": 25,
  "alpha_base": 0.85,
  "alpha_entangled": 0.03,
  "max_iterations": 4,
  "convergence_threshold": 0.01,
  "entanglement_threshold": 0.55
}

Selected layers:

27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51

Total directions ablated: 100.

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 (grimjim), 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.