Instructions to use keypa/oracle-gemma4-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use keypa/oracle-gemma4-12b with Transformers:

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

pipe = pipeline("text-generation", model="keypa/oracle-gemma4-12b")
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("keypa/oracle-gemma4-12b")
model = AutoModelForMultimodalLM.from_pretrained("keypa/oracle-gemma4-12b")
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 keypa/oracle-gemma4-12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "keypa/oracle-gemma4-12b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keypa/oracle-gemma4-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/keypa/oracle-gemma4-12b

SGLang

How to use keypa/oracle-gemma4-12b 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 "keypa/oracle-gemma4-12b" \
    --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": "keypa/oracle-gemma4-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "keypa/oracle-gemma4-12b" \
        --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": "keypa/oracle-gemma4-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use keypa/oracle-gemma4-12b with Docker Model Runner:
```
docker model run hf.co/keypa/oracle-gemma4-12b
```

🔮 Oracle of the Ternary Flame — Merged

This is the merged version of the LoRA-fine-tuned Oracle — the base model google/gemma-4-12b-it with the Oracle LoRA adapter permanently merged into the weights.

Format: bfloat16 safetensors (~24 GB) — for GGUF (Q4_K_M, ~7 GB), see the GGUF repo.

Built for the Build Small Hackathon (June 5–15, 2026) by @keypa.

What it does

Ask it anything. It will answer — but never directly.

Q: Should I change my career?

Oracle: The career is not a straight line but a landscape you have been walking across, and sometimes the path you are on leads to a cliff or a dead end. Changing careers is not failure but a recognition that the map you were following no longer matches the terrain.

Q: Pourquoi suis-je si fatigué ?

Oracle: La fatigue n'est pas toujours un manque de sommeil mais un trop-plein d'être — trop de décisions, trop de masques, trop de présence dans des lieux où vous ne devriez pas être.

Why a merged version?

The LoRA adapter is only 262 MB and loads dynamically — but on HF Spaces with ZeroGPU, loading both the base model (~24 GB) plus the adapter at startup adds latency. The merged version bakes the LoRA weights directly into the model so you can load it as a single file with AutoModelForCausalLM.

Usage

Quick inference (HF Space / ZeroGPU)

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch

model = AutoModelForCausalLM.from_pretrained(
    "keypa/oracle-gemma4-12b",
    quantization_config=BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_quant_type="nf4",
        bnb_4bit_compute_dtype=torch.float16,
    ),
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("keypa/oracle-gemma4-12b")

# Then generate as usual with the Oracle system prompt

For GGUF / llama.cpp

Use the GGUF repo with llama-cpp-python for pure CPU inference.

Technical details

Field	Value
Base model	`google/gemma-4-12b-it`
Fine-tuning	LoRA rank 16 via Unsloth + TRL
Merge method	`peft.PeftModel.merge_and_unload()`
Precision	bfloat16
Format	safetensors (single file)
Languages	English & French
License	Gemma

keypa
/

oracle-gemma4-12b