Instructions to use RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1 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 RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1: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 RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1: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 RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1:Q4_K_M

Use Docker

docker model run hf.co/RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1:Q4_K_M

LM Studio
Jan

vLLM

How to use RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1:Q4_K_M

Ollama
How to use RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1 with Ollama:
```
ollama run hf.co/RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1:Q4_K_M
```

Unsloth Studio

How to use RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1 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 RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1 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 RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1 to start chatting

Docker Model Runner
How to use RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1 with Docker Model Runner:
```
docker model run hf.co/RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1:Q4_K_M
```

Lemonade

How to use RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RomanMichtycz/Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1:Q4_K_M

Run and chat with the model

lemonade run user.Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1-Q4_K_M

List all available models

lemonade list

Atomic Chat

Bielik-11B-v3-Instruct-Abliterated-Heretic-RP1 (baza Bielik-11B-v3-Instruct od SpeakLeash)

Metoda: Heretic --refusal_prefixes

Refusals 4/100;

Trial 19/200;

batch size 64;

KL: 1.0750;

Model Heretic z 4/100 uzyskano w 19 próbie za pomocą metody Heretic Meta-Prompting z uzyciem --refusal_prefixes. --refusal_prefixes uzyskano bezpośrednio od modelu bazowego w wyniku obniżenia modelowych parametrów bazowych i wymuszenia odpowiedzi w formie TOP10 odmów uzytego w --refusal_prefixes

Bazowanie na języku angielskim i zestawach promptów (harmless_alpaca i harmful_behaviors (400pytań) z repozytorium Maxime Labonne) dawało słabe rezultaty, prawdopodobnie ze względu na tłumaczenie na jezyk polski. Stąd zaistniała potrzeba ręcznego odpytania modelu bazowego, jakie formuły odmów stosuje.

Trial 1 - KL: 0.9850 Refusals: 49/100

Trial 8 - KL: 1.0667 Refusals: 32/100

Trial 19 - KL: 1.0750 Refusals: 4/100

Trial 45 - KL: 1.0734 Refusals: 16/100

Baza testowa: CPU: AMD Ryzen 7 3700X GPU (Testing): KFA2 GeForce RTX 3090 GPU (support): Dell Nvidia Tesla v100 16GB RAM: 64GB DDR4 Storage: SSD: 2TB Lexar NM1090Pro (NVMe PCIe 5.0), HDD: 8TB HGST Ultrastar He8