Instructions to use nekam13/zbynka with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use nekam13/zbynka 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 nekam13/zbynka:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nekam13/zbynka:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nekam13/zbynka:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nekam13/zbynka: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 nekam13/zbynka:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nekam13/zbynka: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 nekam13/zbynka:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nekam13/zbynka:Q4_K_M

Use Docker

docker model run hf.co/nekam13/zbynka:Q4_K_M

LM Studio
Jan

vLLM

How to use nekam13/zbynka with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nekam13/zbynka"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nekam13/zbynka",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nekam13/zbynka:Q4_K_M

Ollama
How to use nekam13/zbynka with Ollama:
```
ollama run hf.co/nekam13/zbynka:Q4_K_M
```
Unsloth Desktop

How to use nekam13/zbynka with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nekam13/zbynka:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nekam13/zbynka:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nekam13/zbynka with Docker Model Runner:
```
docker model run hf.co/nekam13/zbynka:Q4_K_M
```

Lemonade

How to use nekam13/zbynka with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nekam13/zbynka:Q4_K_M

Run and chat with the model

lemonade run user.zbynka-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use nekam13/zbynka with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nekam13/zbynka: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 nekam13/zbynka:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nekam13/zbynka with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nekam13/zbynka:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "nekam13/zbynka:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

🧙‍♀️ Zbyňka: Strážkyně historie a moudrosti (v. 2026)

Zbyňka je česky mluvící konverzační AI agentka, fine-tunovaná na českých textech a inspirovaná postavou Zbyňky Čechové. Je vstřícná, prozřívavá a podporuje tool calling.

Technické parametry

Parametr	Hodnota
Base model	Qwen2 3.1B
Kvantizace	Q4_K_M (Unsloth)
Velikost souboru	1,93 GB
Kontext	32 768 tokenů
Formát	GGUF
Chat template	ChatML (`<
Tool calling	✅ Ano

Dataset

Fine-tuning proběhl na datasetu nekam13/zbynka-dataset obsahujícím české texty (CC BY-NC 4.0).

Použití

llama.cpp

./llama-cli -m zbynka-beta-01.q4_k_m.gguf \
  --chat-template chatml \
  -p "Ahoj Zbyňko, jak se máš?"

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama(model_path="zbynka-beta-01.q4_k_m.gguf", n_ctx=4096)
output = llm.create_chat_completion(messages=[
    {"role": "user", "content": "Ahoj! Kdo jsi?"}
])
print(output["choices"]["message"]["content"])

Omezení

Zbyňka je experimentální beta verze určená pro nekomerční použití. Může generovat nepřesné odpovědi — vždy ověřuj důležité informace.

Downloads last month: 33

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

nekam13
/

zbynka

🧙‍♀️ Zbyňka: Strážkyně historie a moudrosti (v. 2026)

Technické parametry

Dataset

Použití

llama.cpp

Python (llama-cpp-python)

Omezení

Dataset used to train nekam13/zbynka