Instructions to use MagistrTheOne/asterias-v73 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MagistrTheOne/asterias-v73 with Transformers:

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

pipe = pipeline("text-generation", model="MagistrTheOne/asterias-v73")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MagistrTheOne/asterias-v73")
model = AutoModelForCausalLM.from_pretrained("MagistrTheOne/asterias-v73")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MagistrTheOne/asterias-v73 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MagistrTheOne/asterias-v73"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MagistrTheOne/asterias-v73",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MagistrTheOne/asterias-v73

SGLang

How to use MagistrTheOne/asterias-v73 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 "MagistrTheOne/asterias-v73" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MagistrTheOne/asterias-v73",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "MagistrTheOne/asterias-v73" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MagistrTheOne/asterias-v73",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MagistrTheOne/asterias-v73 with Docker Model Runner:
```
docker model run hf.co/MagistrTheOne/asterias-v73
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🜂 ASTERIAS

NULLXES Digital Execution Model

A deterministic, execution-oriented language model engineered for enterprise workflows and AI digital employees.

📌 Overview

ASTERIAS is a research project by NULLXES, focused on building deterministic language models for real-world enterprise execution. This release is an early iteration — the project is actively scaling toward a 70B parameter model as its next training milestone.

The model is designed around four core principles:

Principle	Description
🎯 Strict output control	Responses follow predefined structure with no deviation
🔇 Minimal noise	No filler, no apologies, no meta-commentary
🧩 Structured reasoning	Outputs are machine-parseable by default
🔁 Predictable behavior	Same input → same output, reliably

⚙️ Operating Rules

ASTERIAS operates under strict generation constraints:

❌ No explanations
❌ No extra text
❌ No repetition
✅ Structured, deterministic output only

🧠 Behavior

Simple Queries

Returns direct, minimal answers.

Complex Queries

Returns strictly structured output suitable for downstream automation, agent pipelines, and digital-employee workflows.

🔬 Research Status

This is a research project. ASTERIAS is being developed as a stepping stone toward a 70B-parameter deterministic execution model. The current checkpoint is intended for evaluation, benchmarking, and integration testing in enterprise agent environments.

📫 Contact

NULLXES 📧 ceo@nullxes.com

📄 License

Released under the Apache 2.0 license.

Downloads last month: 245

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for MagistrTheOne/asterias-v73

Quantizations

2 models