Instructions to use Coralfil/Atlantis-Obelisk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Coralfil/Atlantis-Obelisk with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-14B-Instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "Coralfil/Atlantis-Obelisk")

Transformers

How to use Coralfil/Atlantis-Obelisk with Transformers:

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

pipe = pipeline("text-generation", model="Coralfil/Atlantis-Obelisk")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Coralfil/Atlantis-Obelisk", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Coralfil/Atlantis-Obelisk with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Coralfil/Atlantis-Obelisk

SGLang

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

Unsloth Desktop
Docker Model Runner
How to use Coralfil/Atlantis-Obelisk with Docker Model Runner:
```
docker model run hf.co/Coralfil/Atlantis-Obelisk
```

Atlantis-Obelisk: Sovereign Edge Marine LLM

Atlantis-Obelisk is Coralfil's sovereign edge foundation coprocessor fine-tuned for physical oceanography, mariculture formulation, benthic restoration, and Canadian maritime statutory compliance (DFO, Transport Canada, IMO).

It is optimized for low-latency onboard maritime vessel deployments, autonomous sensor nodes, and workstations.

Architecture & Specifications

Base Architecture: Qwen 2.5 14B Instruct (4-bit base)
Fine-Tuning: Rank-Stabilized LoRA (r=16, alpha=32) covering all 7 attention projection layers (q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj).
Context Length: 32,768 tokens (up to 128k via YaRN scaling).
Domain Benchmarks: Evaluated on the 52-scenario sovereign AboveBoard benchmark (96.15% marine domain precision).
Live Web Console: https://atlantis-llm.io
Coastal Telemetry Network: https://coralfil.com/monitor

Download & Run Locally

With Hugging Face CLI:

huggingface-cli download Coralfil/Atlantis-Obelisk --local-dir ./atlantis-obelisk

With Python (Transformers & PEFT):

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base_model_id = "Qwen/Qwen2.5-14B-Instruct"
adapter_id = "Coralfil/Atlantis-Obelisk"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
model = PeftModel.from_pretrained(base_model, adapter_id)

prompt = "Explain how omega aragonite saturation deficit impacts juvenile Crassostrea gigas larval settlement."
inputs = tokenizer(f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n", return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Citation & Attribution

@software{coralfil_atlantis_obelisk_2026,
  author = {Coralfil Marine Intelligence},
  title = {Atlantis-Obelisk: Sovereign Edge Marine Foundation Coprocessor},
  url = {https://atlantis-llm.io},
  year = {2026}
}

Downloads last month: 5

Model tree for Coralfil/Atlantis-Obelisk

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-14B-Instruct

Quantized

unsloth/Qwen2.5-14B-Instruct-bnb-4bit

Adapter

(8)

this model