Instructions to use DavidrPatton/Gemma-4-31B-Fable-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavidrPatton/Gemma-4-31B-Fable-Coder with Transformers:

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

pipe = pipeline("image-text-to-text", model="DavidrPatton/Gemma-4-31B-Fable-Coder")
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("DavidrPatton/Gemma-4-31B-Fable-Coder")
model = AutoModelForMultimodalLM.from_pretrained("DavidrPatton/Gemma-4-31B-Fable-Coder")
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 DavidrPatton/Gemma-4-31B-Fable-Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidrPatton/Gemma-4-31B-Fable-Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidrPatton/Gemma-4-31B-Fable-Coder",
		"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/DavidrPatton/Gemma-4-31B-Fable-Coder

SGLang

How to use DavidrPatton/Gemma-4-31B-Fable-Coder 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 "DavidrPatton/Gemma-4-31B-Fable-Coder" \
    --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": "DavidrPatton/Gemma-4-31B-Fable-Coder",
		"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 "DavidrPatton/Gemma-4-31B-Fable-Coder" \
        --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": "DavidrPatton/Gemma-4-31B-Fable-Coder",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Studio

How to use DavidrPatton/Gemma-4-31B-Fable-Coder 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 DavidrPatton/Gemma-4-31B-Fable-Coder 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 DavidrPatton/Gemma-4-31B-Fable-Coder to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DavidrPatton/Gemma-4-31B-Fable-Coder to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="DavidrPatton/Gemma-4-31B-Fable-Coder",
    max_seq_length=2048,
)

Docker Model Runner
How to use DavidrPatton/Gemma-4-31B-Fable-Coder with Docker Model Runner:
```
docker model run hf.co/DavidrPatton/Gemma-4-31B-Fable-Coder
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Gemma-4-31B-Fable-Coder

Developed by: DavidrPatton
License: Apache-2.0
Finetuned from model: unsloth/gemma-4-31b-it-unsloth-bnb-4bit

This model is a highly specialized, locally deployable 31-billion parameter Vision-Language-Action (VLA) engine. It was engineered specifically to act as an autonomous orchestration layer for self-hosted AI frameworks. Rather than focusing on a single programming language, this model was trained exclusively to master multi-step agentic reasoning, strict tool-calling schema adherence, and multimodal graphical user interface (GUI) interaction.

This model was trained 2x faster with Unsloth and Huggingface's TRL library.

🛠️ Core Capabilities & Training Data Elaboration

This model was fine-tuned on a heavily curated, deduplicated mixture of four distinct datasets. The objective was to combine high-level architectural reasoning with native visual-interaction capabilities without suffering from catastrophic forgetting.

1. Agentic Logic & Chain-of-Thought (CoT)

Dataset: Glint-Research/Fable-5-traces

What it learned: This dataset injected 4,659 cleartext agentic-coding traces distilled directly from Anthropic's Fable 5 preview model.
The resulting capability: The model learned how to "think" methodically before acting. It forces a rigorous Chain-of-Thought logical buffer before outputting its final response. It also learned how to perfectly format and execute strict <tool_use> XML schemas for multi-step software engineering cycles, interactive debugging, and autonomous file-system manipulation.

2. Native Desktop GUI Control

Dataset: Writer/omniact

What it learned: OmniACT provided thousands of image-instruction pairs mapping natural language directly to host-level operating system actions.
The resulting capability: The model can analyze a visual screenshot of a heavy desktop application and output precise X/Y coordinates for PyAutoGUI execution, allowing the agent to effectively "click" and "type" anywhere on a native OS screen.

3. Web Dashboard Navigation & DOM Parsing

Dataset: McGill-NLP/WebLINX

What it learned: WebLINX provided multi-turn conversational web navigation data, heavily emphasizing DOM trees and UI component grounding.
The resulting capability: Instead of just reading text, the model can parse complex browser layouts, enabling it to autonomously navigate web interfaces, visual management dashboards, and router portals by understanding the relationship between visual web elements and underlying HTML/DOM structures.

4. Visual Schema Enforcement

Dataset: ScaleAI/VisualToolBench

What it learned: A highly specific dataset engineered to map visual contexts directly to structured tool calls.
The resulting capability: This acts as the connective tissue between the model's vision and its logic. It ensures that when the agent "sees" a specific UI element or a visual error code in a screenshot, it outputs the exact, deterministic JSON/XML syntax required by the backend routing framework without hallucinating conversational filler.

⚙️ Architecture & Fine-Tuning Details

Framework: Unsloth FastVisionModel (Multimodal setup).
Precision: Merged 16-bit .safetensors.
Prompt/Chat Template: gemma-4-thinking
Modality Formatting Note: When inferencing with multimodal inputs, ensure the image and/or visual content is placed before the text in the system/user prompt for optimal attention mapping.

Downloads last month: 36

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for DavidrPatton/Gemma-4-31B-Fable-Coder

Quantizations

2 models