---
language: en
license: apache-2.0
library_name: peft
base_model: Qwen/Qwen2.5-1.5B
tags:
  - lora
  - peft
  - cognitive-architecture
  - progressive-learning
  - dream-pruning
  - svd
  - math
  - arithmetic
  - number-sense
  - tool-use
  - metacognition
datasets:
  - custom
pipeline_tag: text-generation
model-index:
  - name: progressive-cognitive-dream-lora-en
    results:
      - task:
          type: text-generation
          name: Cognitive Arithmetic
        metrics:
          - type: exact_accuracy
            value: 69.4
            name: Exact Accuracy (%)
          - type: composite_score
            value: 87.6
            name: Composite Cognitive Score
---

# Progressive Cognitive Architecture — 1.5B Dream LoRA (English)

**🏆 Best overall model (composite 87.6/100)** — Qwen2.5-1.5B fine-tuned with 4-phase progressive training + SVD Dream Pruning.

## ✨ Highlights

| Metric | Score |
|--------|-------|
| **Composite Score** | **87.6** |
| Exact Accuracy | 69.4% ± 6.4 |
| Adversarial Robustness | 84.0% ± 8.0 |
| Delegation Accuracy | 100.0% ± 0.0 |
| Delegation Rate | 100.0% ± 0.0 |
| Magnitude Sense (OoM±1) | 100.0% ± 0.0 |
| Catastrophic Errors | **0.0% ± 0.0** |

> Results: mean ± std over 3 seeds (42, 43, 44), 50 samples × 5 dimensions per seed.

## 🔑 Key Findings

- **Outperforms all 3B variants** despite having half the parameters
- **Zero catastrophic errors** — never produces absurd results
- **100% delegation** — always routes complex operations to tools
- Dream pruning acts as **cognitive regularization** for capacity-constrained models

## 🧠 Progressive Cognitive Architecture

A bio-inspired 4-phase training methodology:

| Phase | Name | What happens |
|-------|------|-------------|
| 1 | **Foundation** | Learn exact arithmetic via LoRA fine-tuning |
| 2 | **Consolidation** | SVD Dream Pruning (rank 16→8) compresses knowledge into intuition |
| 3 | **Delegation** | Learn complexity-aware routing: compute internally vs. delegate to tool |
| 4 | **Orchestration** | Full pipeline: intuit → route → tool → validate |

**Guiding Principle:** *Knowledge doesn't disappear — it collapses into attractors. Intuition is the compressed residue of experience.*


## 🌙 Dream Pruning (SVD Low-Rank Factorization)

Instead of zeroing out small weights (magnitude pruning), Dream Pruning uses **SVD decomposition** to reduce the effective rank of LoRA matrices from 16 to 8. This preserves the principal directions ("logical connections") while discarding noise — analogous to memory consolidation during sleep.

```
W = U·Σ·V^T  →  W' = U[:,:k]·Σ[:k,:k]·V^T[:k,:]   (k=8)
```


## 🔧 Training Configuration

| Parameter | Value |
|-----------|-------|
| Base Model | Qwen/Qwen2.5-1.5B |
| LoRA Rank | 16 (→ 8 after SVD) |
| LoRA Alpha | 32 |
| LoRA Targets | q_proj, k_proj, v_proj, o_proj |
| Dropout | 0.05 |
| Training Data | ~6,000 English arithmetic examples |
| Hardware | NVIDIA T4 16GB |

## 🚀 Quick Start

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-1.5B", device_map="auto", torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B")

# Note: adapters are in the lora_adapters/ subfolder
model = PeftModel.from_pretrained(
    base_model,
    "dexmac/progressive-cognitive-dream-lora-en",
    subfolder="lora_adapters"
)

messages = [{"role": "user", "content": "Solve: 342 * 67"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.1)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

**Expected output pattern:**
```
Step 1 - Intuition: in the order of tens of thousands
Step 2 - Routing: DELEGATE (medium complexity)
Step 3 - Tool: 22914
Step 4 - Validation: result 22914 consistent with estimate → VALID
```

## 📊 Full Comparison

| Model | Composite | Exact | Adversarial | Delegation | Magnitude | Safety |
|---|---|---|---|---|---|---|
| **1.5B Dream (this)** | **87.6** | 69% | 84% | 100% | 100% | 100% |
| 1.5B Flat | 79.2 | 57% | 81% | 79% | 100% | 100% |
| 3B Flat | 78.5 | 60% | 85% | 79% | 84% | 100% |
| 3B Dream | 66.0 | 56% | 34% | 93% | 100% | 59% |

## 🔗 Related Models

- [Flat LoRA (control)](https://huggingface.co/dexmac/progressive-cognitive-baseline-lora-en) — Same data, no phases, no pruning
- [3B Dream](https://huggingface.co/dexmac/progressive-cognitive-qwen3b-dream-lora) — Same architecture on Qwen2.5-3B
- [3B Flat](https://huggingface.co/dexmac/progressive-cognitive-qwen3b-baseline-lora) — 3B control
- [Italian Dream](https://huggingface.co/dexmac/progressive-cognitive-dream-lora) — Italian language variant
- [Results Dataset](https://huggingface.co/datasets/dexmac/progressive-cognitive-results) — Raw evaluation data
- [GitHub](https://github.com/dexmac221/progressive-cognitive) — Full source code and evaluation framework

## 📝 Citation

```bibtex
@software{progressive_cognitive_2026,
  author = {Dex Mac},
  title = {Progressive Cognitive Architecture for LLMs},
  year = {2026},
  url = {https://github.com/dexmac221/progressive-cognitive},
  version = {1.0.0}
}
```


## 📄 License

Apache 2.0