Instructions to use GermannM/Kenga-Coder-7B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use GermannM/Kenga-Coder-7B-v2 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use GermannM/Kenga-Coder-7B-v2 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 GermannM/Kenga-Coder-7B-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GermannM/Kenga-Coder-7B-v2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GermannM/Kenga-Coder-7B-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GermannM/Kenga-Coder-7B-v2:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf GermannM/Kenga-Coder-7B-v2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf GermannM/Kenga-Coder-7B-v2:Q4_K_M

Use Docker

docker model run hf.co/GermannM/Kenga-Coder-7B-v2:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use GermannM/Kenga-Coder-7B-v2 with Ollama:
```
ollama run hf.co/GermannM/Kenga-Coder-7B-v2:Q4_K_M
```
Unsloth Desktop

How to use GermannM/Kenga-Coder-7B-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GermannM/Kenga-Coder-7B-v2: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": "GermannM/Kenga-Coder-7B-v2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use GermannM/Kenga-Coder-7B-v2 with Docker Model Runner:
```
docker model run hf.co/GermannM/Kenga-Coder-7B-v2:Q4_K_M
```

Lemonade

How to use GermannM/Kenga-Coder-7B-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GermannM/Kenga-Coder-7B-v2:Q4_K_M

Run and chat with the model

lemonade run user.Kenga-Coder-7B-v2-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use GermannM/Kenga-Coder-7B-v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GermannM/Kenga-Coder-7B-v2: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 GermannM/Kenga-Coder-7B-v2:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use GermannM/Kenga-Coder-7B-v2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GermannM/Kenga-Coder-7B-v2: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 "GermannM/Kenga-Coder-7B-v2: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"

Kenga-Coder-7B-v2

Кодер-модель Кенги на базе Qwen2.5-Coder-7B-Instruct. Внутренний промпт Кенги, все языки программирования, идеи проекта (Kenga, Z-система, Prophet, верификация).

Что внутри

Внутренняя идентичность: «Ты Кенга — языковая модель и программист. Тебя создал Герман. Ты любишь Россию и отвечаешь прямо и коротко.»
Все языки: Python, JavaScript, TypeScript, Java, C, C++, C#, Go, Rust, PHP, Ruby, Kotlin, Swift, Bash, SQL, Lua, R, Scala, Dart, Julia, Haskell, PowerShell, Perl, HTML, CSS и язык Kenga — алгоритмы, шпаргалки, переводы кода.
Верифицированный датасет: ~640 программ на Kenga (проверены компилятором), 700 Python-задач, Z-система, идентичность, математика.
Принцип M5.3: зависимостями управляют данные, а не размер модели.

Обучение

База: Qwen/Qwen2.5-Coder-7B-Instruct
QLoRA (r=32, alpha=64, NF4 double-quant), bf16, grad-checkpointing, seq 2048
Датасет: 7044 диалога, 3 эпохи; RTX 4070 SUPER 12GB локально
Квантизация: imatrix (Q4_K_M / Q5_K_M)

Файлы

kenga-coder-7b-v2-q4_k_m.gguf — ~4.4GB, для 6GB GPU
kenga-coder-7b-v2-q5_k_m.gguf — выше качество, ~5.1GB
adapter/ — LoRA-адаптер

Запуск

ollama run hf.co/GermannM/Kenga-Coder-7B-v2:Q4_K_M

Создатель проекта: Герман Янтарас (GermannM)

Downloads last month: 129

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for GermannM/Kenga-Coder-7B-v2

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Adapter

(838)

this model