Instructions to use json-l/ecu-pilot-qwen3-8b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use json-l/ecu-pilot-qwen3-8b-GGUF 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 json-l/ecu-pilot-qwen3-8b-GGUF
# Run inference directly in the terminal:
llama cli -hf json-l/ecu-pilot-qwen3-8b-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf json-l/ecu-pilot-qwen3-8b-GGUF
# Run inference directly in the terminal:
llama cli -hf json-l/ecu-pilot-qwen3-8b-GGUF

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 json-l/ecu-pilot-qwen3-8b-GGUF
# Run inference directly in the terminal:
./llama-cli -hf json-l/ecu-pilot-qwen3-8b-GGUF

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 json-l/ecu-pilot-qwen3-8b-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf json-l/ecu-pilot-qwen3-8b-GGUF

Use Docker

docker model run hf.co/json-l/ecu-pilot-qwen3-8b-GGUF

LM Studio
Jan

vLLM

How to use json-l/ecu-pilot-qwen3-8b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "json-l/ecu-pilot-qwen3-8b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "json-l/ecu-pilot-qwen3-8b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/json-l/ecu-pilot-qwen3-8b-GGUF

Ollama
How to use json-l/ecu-pilot-qwen3-8b-GGUF with Ollama:
```
ollama run hf.co/json-l/ecu-pilot-qwen3-8b-GGUF
```
Unsloth Desktop

How to use json-l/ecu-pilot-qwen3-8b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf json-l/ecu-pilot-qwen3-8b-GGUF

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": "json-l/ecu-pilot-qwen3-8b-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use json-l/ecu-pilot-qwen3-8b-GGUF with Docker Model Runner:
```
docker model run hf.co/json-l/ecu-pilot-qwen3-8b-GGUF
```

Lemonade

How to use json-l/ecu-pilot-qwen3-8b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull json-l/ecu-pilot-qwen3-8b-GGUF

Run and chat with the model

lemonade run user.ecu-pilot-qwen3-8b-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use json-l/ecu-pilot-qwen3-8b-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf json-l/ecu-pilot-qwen3-8b-GGUF

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 json-l/ecu-pilot-qwen3-8b-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use json-l/ecu-pilot-qwen3-8b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf json-l/ecu-pilot-qwen3-8b-GGUF

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 "json-l/ecu-pilot-qwen3-8b-GGUF" \
  --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"

ecu-pilot-qwen3-8b-GGUF / README.md

json-l

Upload README.md with huggingface_hub

e344c68 verified 5 months ago

preview code

Raw

History Blame Contribute Delete

3.47 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen3-8B
	tags:
	- dbt
	- tool-calling
	- gguf
	- qwen3
	- fine-tuned
	- unsloth
	model_type: qwen3
	quantized_by: llama.cpp
	pipeline_tag: text-generation
	---

	# ecu-pilot-qwen3-8b-GGUF

	A fine-tuned Qwen3-8B model for dbt project assistance via tool calling against [dbt-index](https://github.com/dbt-labs/dbt-index).

	## Overview

	ecu-pilot is trained to autonomously select and call the correct dbt-index tool (out of 9 available tools) based on natural language questions about a dbt project, then summarize the results concisely.

	### Tools

	\| Tool \| Description \|
	\|------\|-------------\|
	\| `status` \| Project overview — model/test/source counts \|
	\| `schema` \| Database schema exploration \|
	\| `search` \| Full-text search across models, columns, descriptions \|
	\| `node` \| Detailed info on a specific model/source/test \|
	\| `lineage` \| Upstream/downstream dependency graph \|
	\| `query` \| Run SQL against the dbt-index DuckDB \|
	\| `report` \| Coverage reports (tests, docs, etc.) \|
	\| `impact` \| Blast radius analysis for model changes \|
	\| `diff` \| Compare project state across branches \|

	## Training

	- Base model: Qwen3-8B (via `unsloth/Qwen3-8B-bnb-4bit`)
	- Method: QLoRA (r=32, alpha=32) with Unsloth + TRL SFTTrainer
	- Data: 667 tool-calling conversation examples from 8 dbt projects (BIRD benchmark databases)
	- Epochs: 1
	- Hardware: AWS EC2 g6 (NVIDIA L40S 48GB)

	## Quantization

	- Format: GGUF Q4_K_M (4-bit quantized via llama.cpp)
	- Size: ~4.7 GB

	## Chat Template

	This model uses a custom chat template for tool calling. The template is included as [`chat_template.jinja`](chat_template.jinja) in this repo.

	Key differences from stock Qwen3:
	- Tool definitions are injected into the system message within `<tools>` XML tags
	- Tool calls use `<tool_call>` / `</tool_call>` XML delimiters
	- Tool responses are wrapped in `<tool_response>` / `</tool_response>` and sent as user messages

	When using with inference servers that support Jinja templates (vLLM, TGI, llama.cpp server), point to this template file.

	## Usage

	### LM Studio

	1. Download the `.gguf` file
	2. Place in `~/.lmstudio/models/json-l/ecu-pilot-qwen3-8b-GGUF/`
	3. Load in LM Studio, set the chat template to the contents of `chat_template.jinja`, and start the local server

	### Ollama

	Create a `Modelfile`:

	```
	FROM ./ecu-pilot-qwen3-8b-q4km.gguf

	TEMPLATE """{{- if .System }}<\|im_start\|>system
	{{ .System }}<\|im_end\|>
	{{ end }}{{- if .Tools }}<\|im_start\|>system
	# Tools
	You are provided with function signatures within <tools></tools> XML tags:
	<tools>
	{{- range .Tools }}
	{{ json . }}
	{{- end }}
	</tools>
	<\|im_end\|>
	{{ end }}{{- range .Messages }}<\|im_start\|>{{ .Role }}
	{{- if .Content }}
	{{ .Content }}
	{{- end }}{{- if .ToolCalls }}
	<tool_call>
	{{- range .ToolCalls }}
	{"name": "{{ .Function.Name }}", "arguments": {{ json .Function.Arguments }}}
	{{- end }}
	</tool_call>
	{{- end }}<\|im_end\|>
	{{ end }}<\|im_start\|>assistant
	"""

	SYSTEM """You are an expert dbt project assistant with access to a dbt-index metadata server."""

	PARAMETER stop "<\|im_end\|>"
	PARAMETER stop "<tool_call>"
	PARAMETER temperature 0.7
	PARAMETER num_ctx 4096
	```

	Then:

	```bash
	ollama create ecu-pilot -f Modelfile
	ollama run ecu-pilot
	```

	## Evaluation

	On 8 test prompts (2 runs each):

	\| Metric \| Score \|
	\|--------\|-------\|
	\| Tool called \| 88% \|
	\| Correct tool \| 75% \|
	\| Answer generated \| 100% \|

	## License

	Apache 2.0