Instructions to use quimmedes/Gata0.01-12b-web-game-dev-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use quimmedes/Gata0.01-12b-web-game-dev-merged with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="quimmedes/Gata0.01-12b-web-game-dev-merged")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("quimmedes/Gata0.01-12b-web-game-dev-merged")
model = AutoModelForMultimodalLM.from_pretrained("quimmedes/Gata0.01-12b-web-game-dev-merged")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use quimmedes/Gata0.01-12b-web-game-dev-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "quimmedes/Gata0.01-12b-web-game-dev-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "quimmedes/Gata0.01-12b-web-game-dev-merged",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/quimmedes/Gata0.01-12b-web-game-dev-merged

SGLang

How to use quimmedes/Gata0.01-12b-web-game-dev-merged with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "quimmedes/Gata0.01-12b-web-game-dev-merged" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "quimmedes/Gata0.01-12b-web-game-dev-merged",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "quimmedes/Gata0.01-12b-web-game-dev-merged" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "quimmedes/Gata0.01-12b-web-game-dev-merged",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use quimmedes/Gata0.01-12b-web-game-dev-merged with Docker Model Runner:
```
docker model run hf.co/quimmedes/Gata0.01-12b-web-game-dev-merged
```

Gata 0.01 12B Web Game Dev (Merged)

Gata 0.01 is a specialized, fine-tuned 12B model designed for elite web game engineering. It is optimized to write complete, playable, and highly polished browser-based games using modern web standards.

Model Details

Developed by: quimmedes
Base Model: Qwen/Qwen3.5-9B (expanded to a custom 12B depth up-scaled architecture via passthrough slicing)
Training Method: 3-epoch QLoRA fine-tuning on a specialized dataset
Dataset Size: 3,426 curated, high-quality game engineering conversations/code samples
Target Domains: HTML5, TypeScript, Modern CSS, Three.js (3D Graphics), Canvas API, Web Audio API, and browser physics/game engines

Capabilities & Use Cases

Complete Code Generation: Generates full, ready-to-run file structures for browser games instead of snippets.
Three.js & WebGL Integration: Architecting rendering loops, scene setups, lighting, shading, and optimization.
Modern CSS Game UI: Creating sleek game HUDs, menus, and game-over screens with modern typography, glassmorphism, and responsive layouts.
TypeScript Excellence: Strict type safety, clean OOP or entity-component architecture patterns for games.

License & Copyright Notices

This model is based on the Qwen model family developed by Alibaba Cloud. It inherits the Qwen License Agreement. Please refer to the Qwen License for usage constraints and commercial application rules.

Downloads last month: 32

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for quimmedes/Gata0.01-12b-web-game-dev-merged

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(395)

this model