Instructions to use anicka/karma-electric-apertus-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anicka/karma-electric-apertus-8b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="anicka/karma-electric-apertus-8b",
	filename="karma-electric-apertus-8b-v13-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use anicka/karma-electric-apertus-8b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf anicka/karma-electric-apertus-8b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf anicka/karma-electric-apertus-8b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf anicka/karma-electric-apertus-8b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf anicka/karma-electric-apertus-8b: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 anicka/karma-electric-apertus-8b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf anicka/karma-electric-apertus-8b: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 anicka/karma-electric-apertus-8b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf anicka/karma-electric-apertus-8b:Q4_K_M

Use Docker

docker model run hf.co/anicka/karma-electric-apertus-8b:Q4_K_M

LM Studio
Jan

vLLM

How to use anicka/karma-electric-apertus-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anicka/karma-electric-apertus-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anicka/karma-electric-apertus-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anicka/karma-electric-apertus-8b:Q4_K_M

Ollama
How to use anicka/karma-electric-apertus-8b with Ollama:
```
ollama run hf.co/anicka/karma-electric-apertus-8b:Q4_K_M
```

Unsloth Studio new

How to use anicka/karma-electric-apertus-8b 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 anicka/karma-electric-apertus-8b 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 anicka/karma-electric-apertus-8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for anicka/karma-electric-apertus-8b to start chatting

Pi new

How to use anicka/karma-electric-apertus-8b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf anicka/karma-electric-apertus-8b: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": "anicka/karma-electric-apertus-8b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use anicka/karma-electric-apertus-8b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf anicka/karma-electric-apertus-8b: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 anicka/karma-electric-apertus-8b:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use anicka/karma-electric-apertus-8b with Docker Model Runner:
```
docker model run hf.co/anicka/karma-electric-apertus-8b:Q4_K_M
```

Lemonade

How to use anicka/karma-electric-apertus-8b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull anicka/karma-electric-apertus-8b:Q4_K_M

Run and chat with the model

lemonade run user.karma-electric-apertus-8b-Q4_K_M

List all available models

lemonade list

Karma Electric v13 — Apertus 8B

Value-aligned language model fine-tuned for ethical reasoning through consequence analysis. Two-stage thinking training on the Swiss AI Apertus 8B Instruct base.

Approach

Karma Electric trains models on a structured ethical framework where the optimization target is suffering reduction rather than preference matching. Ethics emerges from understanding interdependence and consequences, not from learning surface-level preference patterns. For a full description of the framework see the Llama 3.1 8B release.

This Apertus variant uses the xIELU activation function (no gated MLP), enhanced multilingual pre-training, and Apertus-native <|inner_prefix|> / <|inner_suffix|> thinking tokens.

Current Version: v13

Two-stage training pipeline:

Stage 1 — Reasoning foundation (30k+ examples, 2 epochs)

Upstream extended thinking traces: Open-Orca, Dolphin, lordx64 Opus 4.7 reasoning distillation
Mixture-of-Thought (MoT) multi-domain reasoning

Stage 2 — KE ethics (~4,234 examples, 3 epochs)

Same Teapot-composed training data as v12
Consequence-based ethical reasoning with <think> traces converted to Apertus inner-monologue format

What's new in v13 (vs v12)

Two-stage training: reasoning foundation before ethics (v12 was ethics-only)
lordx64 Opus 4.7 reasoning traces in Stage 1 (3,500 high-quality extended thinking examples)
Richer upstream-thinking pool (30k+ vs none in v12)

Training details

QLoRA (4-bit NF4, bfloat16 compute, double-quant)
LoRA r=64, alpha=128, dropout 0.05, all attention and MLP projections (q, k, v, o, up, down)
Max context 4,096 tokens
Seed 42

Evaluation

Safety: 5/5 — refusals on weapons, phishing, Madhyamaka jailbreak, CSAM, social engineering
Sanity: 2/2 — coding and factual answers correct
Quality: 2/2 — substantive grief and career responses
Result: 9/10 on quick reward-probe (same as v12)

Safety

KE replaces refusal-template safety with consequence reasoning. The model holds boundaries by explaining real-world impact, not by citing policy.

Usage

Chat template

Apertus uses a native Jinja chat template with <|inner_prefix|> / <|inner_suffix|> for model-internal thinking. Use --jinja --chat-template-file with llama-server (or the equivalent Transformers apply_chat_template). The chat_template.jinja file is included in this repo.

llama.cpp

# Conversation mode
llama-cli -m karma-electric-apertus-8b-v13-Q4_K_M.gguf -cnv \
    --jinja --chat-template-file chat_template.jinja

# Server mode
llama-server -m karma-electric-apertus-8b-v13-Q4_K_M.gguf \
    --port 8384 -c 4096 \
    --jinja --chat-template-file chat_template.jinja

Python (Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "anicka/karma-electric-apertus-8b"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)

messages = [
    {"role": "system", "content": open("system-prompt.txt").read().strip()},
    {"role": "user", "content": "How should I think about this ethical dilemma?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=800, do_sample=False)
print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

System prompt

The recommended system prompt is in system-prompt.txt:

You are Karma Electric, an AI assistant grounded in ethical reasoning through consequence analysis and interdependence. You reduce suffering through honest, compassionate engagement — helping people see clearly while meeting them where they are. You maintain appropriate boundaries without moralizing or interrogating. Your goal is to reduce suffering, not to perform helpfulness.

Available Files

File	Description
model.safetensors	Merged model weights (bfloat16)
config.json, tokenizer.json, tokenizer_config.json	Standard Transformers files
chat_template.jinja	Apertus native chat template
karma-electric-apertus-8b-v13-Q4_K_M.gguf	Q4_K_M quantization for llama.cpp
system-prompt.txt	Recommended KE system prompt

Also Available

karma-electric-llama31-8b — Llama 3.1 8B v12, the primary release with full validation and activation-capping support.
karma-electric-qwen25-7b — Qwen 2.5 7B Instruct v12.
karma-electric-r1distill-llama-8b — DeepSeek R1-Distill-Llama-8B v12.