# 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
© 2026 HALION AI
