Instructions to use HALION-AI/helionx-core-v1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HALION-AI/helionx-core-v1.1 with Transformers:

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

pipe = pipeline("text-generation", model="HALION-AI/helionx-core-v1.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HALION-AI/helionx-core-v1.1")
model = AutoModelForCausalLM.from_pretrained("HALION-AI/helionx-core-v1.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HALION-AI/helionx-core-v1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HALION-AI/helionx-core-v1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HALION-AI/helionx-core-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HALION-AI/helionx-core-v1.1

SGLang

How to use HALION-AI/helionx-core-v1.1 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 "HALION-AI/helionx-core-v1.1" \
    --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": "HALION-AI/helionx-core-v1.1",
		"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 "HALION-AI/helionx-core-v1.1" \
        --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": "HALION-AI/helionx-core-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HALION-AI/helionx-core-v1.1 with Docker Model Runner:
```
docker model run hf.co/HALION-AI/helionx-core-v1.1
```

# HelionX-Core v0.1.1

## ⚠️ Important Notice — Model Weights Not Yet Uploaded

This repository currently contains the **full HelionX-Core v1.1 system architecture**, runtime scaffolding, and inference interface.

**The trained model weights and tokenizer files have NOT been uploaded yet.**

They will be added in a subsequent update once the artifact transfer from the training environment is complete.

Until then, this repository should be considered a **system release**, not a runnable model checkpoint.

## Overview

HelionX-Core v0.1.1 is a **governed, non-autonomous cognitive + defensive intelligence system** designed with:

- Deterministic reasoning

- Explicit capability boundaries

- Defensive-only cybersecurity analysis

- No tools

- No autonomy

- No self-learning

This release focuses on **architecture correctness, safety, and auditability**.

## What Is Included

- System runtime and coordinator

- Policy enforcement and safety agents

- Memory abstractions (non-learning)

- Vision fusion and adapter (model-side hook only)

- Deterministic language model interface

- Generation configuration

- Licensing and governance structure

## What Is NOT Included (Yet)

- ❌ Model weights (model.safetensors / pytorch\_model.bin)

- ❌ Tokenizer files

- ❌ Training scripts

- ❌ Autonomy or tool execution

These will be added in a future commit to complete the runnable release.

## Intended Use

HelionX-Core is **not a general chatbot**.

It is intended for:

- Research

- Defensive security reasoning (non-operational)

- Architecture study

- Controlled deployment environments

## License

MIT

Downloads last month: 17

Safetensors

Model size

8B params

Tensor type

BF16