Instructions to use ccarrillomanzanares/ccmai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ccarrillomanzanares/ccmai with Transformers:

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

pipe = pipeline("text-generation", model="ccarrillomanzanares/ccmai")
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("ccarrillomanzanares/ccmai")
model = AutoModelForMultimodalLM.from_pretrained("ccarrillomanzanares/ccmai", device_map="auto")
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 ccarrillomanzanares/ccmai with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ccarrillomanzanares/ccmai

SGLang

How to use ccarrillomanzanares/ccmai 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 "ccarrillomanzanares/ccmai" \
    --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": "ccarrillomanzanares/ccmai",
		"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 "ccarrillomanzanares/ccmai" \
        --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": "ccarrillomanzanares/ccmai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ccarrillomanzanares/ccmai with Docker Model Runner:
```
docker model run hf.co/ccarrillomanzanares/ccmai
```

CCMAI: Sovereign SRE Assistant

CCMAI (Carrillo Manzanares Artificial Intelligence) is a fine-tuned version of the Gemma 3 architecture, specifically optimized for System Administration, SRE (Site Reliability Engineering), and Linux infrastructure management.

Built to be the "brain" behind the LinuxPilot voice assistant, this model combines high-level reasoning with deep technical knowledge of terminal environments, kernel logs, and cloud infrastructure.

🚀 Key Features

SRE Specialization: Trained to analyze logs, suggest kernel fixes, and automate terminal workflows.
Infrastructure Aware: Optimized for reasoning about complex system architectures and cloud deployments.
Privacy & Sovereignty: Designed to run locally via Ollama, ensuring technical data never leaves your infrastructure.
Gemma 3 Core: Leverages Google's latest architecture for state-of-the-art performance in reasoning and instruction following.

🛠️ Usage

This model is intended for use within the Ollama ecosystem or via the Transformers library.

Ollama

ollama run ccarrillomanzanares/ccmai

Downloads last month: 20

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for ccarrillomanzanares/ccmai

Base model

google/gemma-3-27b-pt

Finetuned

google/gemma-3-27b-it

Finetuned

(449)

this model