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

Libraries

How to use neuralbroker/blitzkode with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="neuralbroker/blitzkode",
	filename="blitzkode.gguf",
)

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

llama-cpp-python

How to use neuralbroker/blitzkode with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="neuralbroker/blitzkode",
	filename="blitzkode.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 neuralbroker/blitzkode with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf neuralbroker/blitzkode
# Run inference directly in the terminal:
llama-cli -hf neuralbroker/blitzkode

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf neuralbroker/blitzkode
# Run inference directly in the terminal:
llama-cli -hf neuralbroker/blitzkode

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 neuralbroker/blitzkode
# Run inference directly in the terminal:
./llama-cli -hf neuralbroker/blitzkode

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 neuralbroker/blitzkode
# Run inference directly in the terminal:
./build/bin/llama-cli -hf neuralbroker/blitzkode

Use Docker

docker model run hf.co/neuralbroker/blitzkode

LM Studio
Jan

vLLM

How to use neuralbroker/blitzkode with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/neuralbroker/blitzkode

Ollama
How to use neuralbroker/blitzkode with Ollama:
```
ollama run hf.co/neuralbroker/blitzkode
```

Unsloth Studio

How to use neuralbroker/blitzkode 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 neuralbroker/blitzkode 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 neuralbroker/blitzkode to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for neuralbroker/blitzkode to start chatting

How to use neuralbroker/blitzkode with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf neuralbroker/blitzkode

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": "neuralbroker/blitzkode"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use neuralbroker/blitzkode with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf neuralbroker/blitzkode

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 neuralbroker/blitzkode

Run Hermes

hermes

Docker Model Runner
How to use neuralbroker/blitzkode with Docker Model Runner:
```
docker model run hf.co/neuralbroker/blitzkode
```

Lemonade

How to use neuralbroker/blitzkode with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull neuralbroker/blitzkode

Run and chat with the model

lemonade run user.blitzkode-{{QUANT_TAG}}

List all available models

lemonade list

neuralbroker commited on 27 days ago

Commit

4fe8118

verified ·

1 Parent(s): ba3b381

Update docker-compose.yml (v2.1 production)

Browse files

Files changed (1) hide show

docker-compose.yml +83 -0

docker-compose.yml ADDED Viewed

	@@ -0,0 +1,83 @@

+# BlitzKode — Docker Compose
+#
+# Quick start (CPU-only):
+#   docker compose up --build
+#
+# With GPU (see blitzkode-gpu service below):
+#   docker compose --profile gpu up --build
+#
+# Override GPU layers at runtime without editing this file:
+#   BLITZKODE_GPU_LAYERS=35 docker compose up
+services:
+  # ─── CPU service (default) ──────────────────────────────────────────────────
+  blitzkode:
+    build: .
+    image: blitzkode:latest
+    ports:
+      - "7860:7860"
+    volumes:
+      # The GGUF model is NOT baked into the image.
+      # Place blitzkode.gguf next to this file and it will be mounted read-only.
+      - ./blitzkode.gguf:/app/blitzkode.gguf:ro
+    environment:
+      BLITZKODE_MODEL_PATH: /app/blitzkode.gguf
+      BLITZKODE_HOST: "0.0.0.0"
+      BLITZKODE_PORT: "7860"
+      # Set BLITZKODE_GPU_LAYERS in your shell or a .env file to override.
+      # 0 = CPU-only (default), -1 = all layers on GPU.
+      BLITZKODE_GPU_LAYERS: "${BLITZKODE_GPU_LAYERS:-0}"
+      BLITZKODE_N_CTX: "2048"
+      BLITZKODE_THREADS: "4"
+      BLITZKODE_BATCH: "128"
+      BLITZKODE_PRELOAD_MODEL: "true"
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-sf", "http://localhost:7860/health"]
+      interval: 30s
+      timeout: 10s
+      start_period: 90s
+      retries: 3
+  # ─── GPU service (commented out — requires nvidia-container-toolkit) ─────────
+  #
+  # Prerequisites on the host:
+  #   1. NVIDIA driver installed
+  #   2. nvidia-container-toolkit installed (https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html)
+  #   3. Docker daemon configured with nvidia runtime (nvidia-ctk runtime configure --runtime=docker)
+  #
+  # To start: docker compose --profile gpu up --build
+  #
+  # blitzkode-gpu:
+  #   build: .
+  #   image: blitzkode:latest
+  #   profiles: [gpu]
+  #   ports:
+  #     - "7860:7860"
+  #   volumes:
+  #     - ./blitzkode.gguf:/app/blitzkode.gguf:ro
+  #   environment:
+  #     BLITZKODE_MODEL_PATH: /app/blitzkode.gguf
+  #     BLITZKODE_HOST: "0.0.0.0"
+  #     BLITZKODE_PORT: "7860"
+  #     # Tune to your GPU's layer count (run `./scripts/healthcheck.sh` after start)
+  #     BLITZKODE_GPU_LAYERS: "35"
+  #     BLITZKODE_N_CTX: "4096"
+  #     BLITZKODE_THREADS: "4"
+  #     BLITZKODE_BATCH: "512"
+  #     BLITZKODE_PRELOAD_MODEL: "true"
+  #   deploy:
+  #     resources:
+  #       reservations:
+  #         devices:
+  #           - driver: nvidia
+  #             count: 1
+  #             capabilities: [gpu]
+  #   runtime: nvidia
+  #   restart: unless-stopped
+  #   healthcheck:
+  #     test: ["CMD", "curl", "-sf", "http://localhost:7860/health"]
+  #     interval: 30s
+  #     timeout: 10s
+  #     start_period: 90s
+  #     retries: 3