Instructions to use developmentseed/gazet-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use developmentseed/gazet-model with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="developmentseed/gazet-model",
	filename="models/ckpt-q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use developmentseed/gazet-model with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf developmentseed/gazet-model:Q8_0
# Run inference directly in the terminal:
llama-cli -hf developmentseed/gazet-model:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf developmentseed/gazet-model:Q8_0
# Run inference directly in the terminal:
llama-cli -hf developmentseed/gazet-model:Q8_0

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 developmentseed/gazet-model:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf developmentseed/gazet-model:Q8_0

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 developmentseed/gazet-model:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf developmentseed/gazet-model:Q8_0

Use Docker

docker model run hf.co/developmentseed/gazet-model:Q8_0

LM Studio
Jan

vLLM

How to use developmentseed/gazet-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/developmentseed/gazet-model:Q8_0

Ollama
How to use developmentseed/gazet-model with Ollama:
```
ollama run hf.co/developmentseed/gazet-model:Q8_0
```

Unsloth Studio new

How to use developmentseed/gazet-model 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 developmentseed/gazet-model 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 developmentseed/gazet-model to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for developmentseed/gazet-model to start chatting

Pi new

How to use developmentseed/gazet-model with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf developmentseed/gazet-model:Q8_0

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": "gazet-model"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use developmentseed/gazet-model with Docker Model Runner:
```
docker model run hf.co/developmentseed/gazet-model:Q8_0
```

Lemonade

How to use developmentseed/gazet-model with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull developmentseed/gazet-model:Q8_0

Run and chat with the model

lemonade run user.gazet-model-Q8_0

List all available models

lemonade list

Gazet Model

LoRA-finetuned Qwen3.5-0.8B for natural-language geocoding over Overture Maps and Natural Earth parquet datasets.

Two tasks:

Place extraction: Given a user query, extract structured place names with optional country codes and subtypes
Text-to-SQL: Given a user query and fuzzy-matched candidate entities, generate a DuckDB spatial SQL query

Files

File	Description
ckpt-q8_0.gguf	Q8_0 quantized GGUF (812 MB), ready for llama-server
merged/	Full merged safetensors (for re-quantization or further finetuning)

Usage

Serve with llama-server:

# Download
hf download developmentseed/gazet-model ckpt-q8_0.gguf

# Serve
llama-server -m ckpt-q8_0.gguf -ngl 99 --port 9000 --ctx-size 2048

The model exposes /v1/chat/completions on port 9000.

Or use with the full gazet stack via Docker Compose (see gazet repo).

Training

Base model: unsloth/Qwen3.5-0.8B
Method: LoRA (r=16, alpha=32) via Unsloth
Data: developmentseed/gazet-dataset
Hardware: Single H200 on Modal (~2 hrs/epoch)
Optimizer: AdamW 8-bit, lr=1e-4, linear schedule
Max sequence length: 2048
Loss: Train on assistant responses only (Unsloth train_on_responses_only)
Full training code: github.com/developmentseed/gazet

Downloads last month: 1,032

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

8-bit

Model tree for developmentseed/gazet-model

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Quantized

(106)

this model

developmentseed
/

gazet-model

Gazet Model

Files

Usage

Training

Model tree for developmentseed/gazet-model

Dataset used to train developmentseed/gazet-model

Space using developmentseed/gazet-model 1