| ---
|
| library_name: transformers
|
| tags:
|
| - symbolic-decoder
|
| - aletheia
|
| - pytorch
|
| - onnx
|
| - philosophical-agi
|
| - gnai-creator
|
| license: apache-2.0
|
| datasets:
|
| - custom
|
| language:
|
| - en
|
| pipeline_tag: text-generation
|
| ---
|
|
|
| # 🧠 Noesis Decoder (AletheiaEngine)
|
|
|
| **Repository:** [gnai-creator/noesis-decoder](https://huggingface.co/gnai-creator/noesis-decoder)
|
| **Author:** Felipe M. Muniz (`gnai-creator`)
|
| **License:** Apache-2.0
|
|
|
| ---
|
|
|
| ## 🔍 Overview
|
|
|
| **Noesis Decoder** is the proprietary symbolic decoder of **AletheiaEngine** — a hybrid symbolic–neural system designed for *philosophical artificial general intelligence*.
|
|
|
| Unlike conventional text generators, Noesis translates **symbolic embeddings (ψₛ)** into meaningful language based on *epistemic coherence*, rather than statistical prediction.
|
|
|
| ---
|
|
|
| ## ⚙️ Model Architecture
|
|
|
| * **Framework:** PyTorch → ONNX Runtime
|
| * **Files:**
|
|
|
| * `model_infer.onnx` – Inference model (optimized)
|
| * `noesis.pt` – PyTorch checkpoint (training artifact)
|
| * `inference.py` – Custom ONNX handler
|
| * **Input:** float32 symbolic vector, shape `[1, D]`
|
| * **Output:** decoded float or token embeddings (depending on context)
|
|
|
| ---
|
|
|
| ## 🧩 Example Usage
|
|
|
| ### 🔹 Python + ONNX Runtime
|
|
|
| ```python
|
| from huggingface_hub import hf_hub_download
|
| import onnxruntime as ort
|
| import numpy as np
|
|
|
| # Download ONNX model
|
| onnx_path = hf_hub_download(
|
| repo_id="gnai-creator/noesis-decoder",
|
| filename="model_infer.onnx",
|
| repo_type="model"
|
| )
|
|
|
| # Load runtime
|
| sess = ort.InferenceSession(onnx_path, providers=["CPUExecutionProvider"])
|
| input_name = sess.get_inputs()[0].name
|
| output_name = sess.get_outputs()[0].name
|
|
|
| # Example symbolic vector ψₛ
|
| x = np.random.randn(1, 300).astype("float32")
|
|
|
| # Run inference
|
| y = sess.run([output_name], {input_name: x})[0]
|
| print("Output shape:", y.shape)
|
| ```
|
|
|
| ---
|
|
|
| ## 💡 Training Data
|
|
|
| Trained on **symbolic text pairs** generated from philosophical, logical, and reflective corpora within the AletheiaEngine ecosystem.
|
| Goal: alignment between **symbolic intention (ψₛ)** and **natural language output**.
|
|
|
| ---
|
|
|
| ## 📊 Metrics (Indicative)
|
|
|
| | Metric | Value | Description |
|
| | ------------- | ------------ | ------------------------------------------ |
|
| | Cosine(Q) | 0.83 | Symbolic alignment measure |
|
| | Perplexity | 2.41 | Statistical readability proxy |
|
| | Latency (CPU) | ~28 ms/token | Inference on Intel Sapphire Rapids (1vCPU) |
|
|
|
| ---
|
|
|
| ## 🚀 Deployment
|
|
|
| This model is compatible with **Hugging Face Inference Endpoints** using the `Custom` engine and the included `inference.py` handler.
|
|
|
| Recommended hardware:
|
|
|
| * **CPU:** Intel Sapphire Rapids (1vCPU / 2GB)
|
| * **GPU:** NVIDIA T4 for larger batch inference
|
|
|
| ---
|
|
|
| ## ⚠️ Limitations
|
|
|
| * Not a conventional LLM — requires symbolic vectors as input.
|
| * Outputs are contextualized to Aletheia’s symbolic reasoning pipeline.
|
| * Not suited for free-form text generation.
|
|
|
| ---
|
|
|
| ## 📜 License
|
|
|
| This repository is distributed under the **Apache License 2.0**.
|
| See [LICENSE](./LICENSE) for details.
|
|
|
| ---
|
|
|
| > *“Truth is not imposed; it emerges from alignment.”*
|
| > — *Felipe M. Muniz (2025)*
|
|
|
|
|
