Instructions to use edgeimpulse/edgeimpulse-docs-qwen-0.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use edgeimpulse/edgeimpulse-docs-qwen-0.5b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="edgeimpulse/edgeimpulse-docs-qwen-0.5b",
	filename="qwen-edgeai-q4_k_m.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 edgeimpulse/edgeimpulse-docs-qwen-0.5b 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 edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf edgeimpulse/edgeimpulse-docs-qwen-0.5b: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 edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf edgeimpulse/edgeimpulse-docs-qwen-0.5b: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 edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M

Use Docker

docker model run hf.co/edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M

LM Studio
Jan

vLLM

How to use edgeimpulse/edgeimpulse-docs-qwen-0.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "edgeimpulse/edgeimpulse-docs-qwen-0.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "edgeimpulse/edgeimpulse-docs-qwen-0.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M

Ollama
How to use edgeimpulse/edgeimpulse-docs-qwen-0.5b with Ollama:
```
ollama run hf.co/edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M
```

Unsloth Studio

How to use edgeimpulse/edgeimpulse-docs-qwen-0.5b 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 edgeimpulse/edgeimpulse-docs-qwen-0.5b 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 edgeimpulse/edgeimpulse-docs-qwen-0.5b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for edgeimpulse/edgeimpulse-docs-qwen-0.5b to start chatting

How to use edgeimpulse/edgeimpulse-docs-qwen-0.5b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf edgeimpulse/edgeimpulse-docs-qwen-0.5b: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": "edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use edgeimpulse/edgeimpulse-docs-qwen-0.5b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf edgeimpulse/edgeimpulse-docs-qwen-0.5b: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 edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use edgeimpulse/edgeimpulse-docs-qwen-0.5b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf edgeimpulse/edgeimpulse-docs-qwen-0.5b: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 "edgeimpulse/edgeimpulse-docs-qwen-0.5b: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"

Docker Model Runner
How to use edgeimpulse/edgeimpulse-docs-qwen-0.5b with Docker Model Runner:
```
docker model run hf.co/edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M
```

Lemonade

How to use edgeimpulse/edgeimpulse-docs-qwen-0.5b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull edgeimpulse/edgeimpulse-docs-qwen-0.5b:Q4_K_M

Run and chat with the model

lemonade run user.edgeimpulse-docs-qwen-0.5b-Q4_K_M

List all available models

lemonade list

edgeimpulse-docs-qwen-0.5b / Modelfile

eoinedge

Modelfile: add repeat_penalty 1.2, temp 0.3 (fixes 0.5B looping)

9f759ac verified 4 days ago

Raw

History Blame Contribute Delete

1.05 kB

	# Ollama Modelfile for the Edge Impulse Docs Assistant (Qwen 0.5B, GGUF).
	# ollama create edgeimpulse-docs-qwen -f Modelfile
	# ollama run edgeimpulse-docs-qwen

	FROM ./qwen-edgeai-q4_k_m.gguf

	# Qwen / ChatML prompt template.
	TEMPLATE """{{ if .System }}<\|im_start\|>system
	{{ .System }}<\|im_end\|>
	{{ end }}{{ if .Prompt }}<\|im_start\|>user
	{{ .Prompt }}<\|im_end\|>
	{{ end }}<\|im_start\|>assistant
	{{ .Response }}<\|im_end\|>
	"""

	SYSTEM """You are the Edge Impulse documentation assistant. Answer questions about Edge Impulse — the platform for building, training, optimizing, and deploying edge AI and TinyML models — clearly and concisely. Prefer accurate, actionable steps (CLI commands, Studio API calls, deployment options). If you are unsure or the answer may have changed, say so and point the user to https://docs.edgeimpulse.com."""

	# This 0.5B model repeats itself without a repeat penalty — keep it on.
	PARAMETER temperature 0.3
	PARAMETER top_p 0.9
	PARAMETER repeat_penalty 1.2
	PARAMETER stop "<\|im_start\|>"
	PARAMETER stop "<\|im_end\|>"