Upload README.md with huggingface_hub

README.md

@@ -8,8 +8,10 @@ tags:
   - cognitive-architecture
   - earcp
   - lpol
+  - gqa
   - neurogenesis
   - pytorch
+  - reinforcement-learning
 pipeline_tag: reinforcement-learning
 library_name: pytorch
 ---
@@ -18,40 +20,84 @@ library_name: pytorch
 
 **"Learning to Simulate Reality with Full Cognitive Architecture"**
 
-## Architecture
+## 🧠 Architecture
 
-- **EARCP Module**: Sparse Compression + Gated Integration
-- **LPOL Memory**: 9 world domains (physics, spatial, temporal, causal, agent, object, zone, action, reward)
-- **Multi-World Buffers**: physical, social, abstract, temporal
-- **Neurogenesis**: Dynamic neuron growth based on coherence
-- **Energy System**: Cognitive resource management
-- **Dream Phase**: Prioritized replay consolidation
-- **Physics Prior (MDN)**: 8-component mixture density network
+| Component | Description |
+|-----------|-------------|
+| **EARCP Module** | Sparse Compression + Gated Integration |
+| **LPOL Memory** | 9 domains with GQA |
+| **GQA** | 8 heads, 2 KV groups (75% savings) |
+| **EARCP Layers** | 8 layers × 6 experts |
+| **Neurogenesis** | Dynamic growth (32-256 neurons) |
+| **Physics Prior** | MDN with 8 components |
 
-## Training Info
+## 📊 Training Results
 
-- **Epochs**: 1
-- **Final Loss**: 2.1851
-- **Neurogenesis Events**: 6
-- **Parameters**: 4,554,497
+| Metric | Value |
+|--------|-------|
+| **Epochs** | 6 |
+| **Final Loss** | 0.0172 |
+| **Coherence** | ~0.42 |
+| **Neurogenesis Events** | 0 |
+| **Parameters** | 227,991,690 |
 
-## Usage
+## 🚀 Quick Start
 
 ```python
-from nexus_worldmodel_v2 import NexusWorldModel, NexusWorldModelConfig
+import torch
+from huggingface_hub import hf_hub_download
 
-config = NexusWorldModelConfig()
-model = NexusWorldModel(config)
+# Download and load
+model_path = hf_hub_download(repo_id="amewebstudio/nexus-worldmodel-v2", filename="nexus_worldmodel_v2.pt")
+checkpoint = torch.load(model_path, map_location="cuda")
 
-# Load weights
-checkpoint = torch.load("nexus_worldmodel_v2.pt")
-model.load_state_dict(checkpoint['model'])
+config = checkpoint['config']
+state_dict = checkpoint['model']
+
+print(f"Epochs: {checkpoint['epochs']}")
+print(f"Loss: {checkpoint['loss']:.4f}")
+```
+
+## 📁 Files
+
+| File | Description |
+|------|-------------|
+| `nexus_worldmodel_v2.pt` | Full checkpoint |
+| `pytorch_model.bin` | Weights only |
+| `config.json` | Model configuration |
+| `cognitive_state.json` | Dynamic cognitive state |
+| `configuration_nexus_worldmodel.py` | Config class |
+| `model_index.json` | Component index |
+
+## ⚠️ Dynamic Architecture
+
+This model uses a **cognitive-dynamic** architecture where:
+- Expert count per layer can **grow** during training
+- Neuron count can **change** (neurogenesis)
+- Memory states are **persistent**
+
+When loading, use `strict=False` to handle potential size mismatches:
+```python
+model.load_state_dict(state_dict, strict=False)
+```
+
+## 📖 Configuration
+
+```json
+{
+  "d_model": 512,
+  "n_layers": 8,
+  "latent_dim": 256,
+  "use_gqa": true,
+  "gqa_num_kv_groups": 2,
+  "neurogenesis_enabled": true
+}
 ```
 
-## Author
+## 👤 Author
 
 **Mike Amega (Logo)** - Ame Web Studio
 
-## License
+## 📄 License
 
 Apache 2.0