Instructions to use Haruster/Ordinal-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Haruster/Ordinal-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="Haruster/Ordinal-v1.0", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Haruster/Ordinal-v1.0", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Haruster/Ordinal-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Haruster/Ordinal-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Haruster/Ordinal-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Haruster/Ordinal-v1.0

SGLang

How to use Haruster/Ordinal-v1.0 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 "Haruster/Ordinal-v1.0" \
    --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": "Haruster/Ordinal-v1.0",
		"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 "Haruster/Ordinal-v1.0" \
        --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": "Haruster/Ordinal-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Haruster/Ordinal-v1.0 with Docker Model Runner:
```
docker model run hf.co/Haruster/Ordinal-v1.0
```

🛡️ Ordinal LLM — ordinal-5b

5.0B Security-Specialized Language Model with Anti-Hallucination Architecture

⚠️ This is the model architecture and configuration. Trained weights will be uploaded separately after training.

Architecture

Parameter	Value
Parameters	~5.0B
Hidden Size	3584
Layers	36
Attention Heads	28 (GQA: 4 KV heads)
Head Dim	128
Intermediate	9216
Vocab Size	50304
Max Context	8192
Dtype	bfloat16

Anti-Hallucination Features

Confidence Head: Per-token reliability score (threshold: 0.7)
Retrieval-Augmented Attention: 4 retrieval heads, dim=256
Fact Verification Layers: At layers [12, 24, 35]
Source Grounding Embeddings: 16 source types

Usage

from transformers import AutoModelForCausalLM, AutoConfig

# Load config
config = AutoConfig.from_pretrained("Haruster/ordinal-5b", trust_remote_code=True)

# Load model (after weights are uploaded)
model = AutoModelForCausalLM.from_pretrained("Haruster/ordinal-5b", trust_remote_code=True)

Chat Template

<|system|>
You are Ordinal, a cybersecurity AI assistant.<|end_turn|>
<|user|>
What is CVE-2021-44228?<|end_turn|>
<|assistant|>

Training Data

17,000+ instruction/response pairs from verified public databases:

NVD CVEs (CRITICAL/HIGH/MEDIUM/LOW)
MITRE ATT&CK (techniques, groups, software)
CAPEC attack patterns
CISA KEV (actively exploited)
GitHub Security Advisories
500+ anti-hallucination training examples

Recommended Hardware

Quantization	VRAM Required
FP16	~10 GB
INT8	~5 GB
INT4	~2 GB

Citation

@software{ordinal_llm_2026,
  title={Ordinal LLM: Security-Specialized Language Model},
  author={KaztoRay},
  year={2026},
  url={https://github.com/Haruster/Ordinal}
}

Downloads last month: 16

Evaluation results

SecurityBench Score on Ordinal Security Dataset
self-reported

0.796
Anti-Hallucination Score on Ordinal Security Dataset
self-reported

0.920