---
language:
- en
license: mit
library_name: pytorch
tags:
- continual-learning
- memory-augmented
- transformer-alternative
- zero-backpropagation
- associative-memory
- pytorch
metrics:
- perplexity
- accuracy
---

# 🧬 CellularFlow v4: Memory-Augmented Continual Learning LLM

**Author:** [Celcilin C S](https://github.com/celcilin)  
**Codebase:** [https://github.com/celcilin/cellularflow](https://github.com/celcilin/cellularflow)  
**Hugging Face:** [https://huggingface.co/celcilin/cellularflow-v4](https://huggingface.co/celcilin/cellularflow-v4)  
**License:** MIT  

CellularFlow is a memory-augmented neural architecture designed as a continual-learning alternative to standard Transformers. By replacing dense Feed-Forward Networks (FFN/MLP) with **Multi-Head Associative DNA Memory Banks** and an **Episodic Memory Slot Buffer**, CellularFlow decouples factual knowledge storage from sequence reasoning.

It achieves **83.9% domain retention** across sequential domains (eliminating catastrophic forgetting) and enables **zero-backprop streaming learning** during inference.

---

## 🌟 Benchmark Results

| Architecture | Parameters | Perplexity | Accuracy | 5-Domain Retention |
| :--- | :--- | :--- | :--- | :--- |
| **GPT-mini (Vanilla Transformer)** | 810K | 8.51 | 36.4% | 61.8% |
| **CellularFlow v4 (Hybrid CMC)** | **379K (2.1× fewer)** | **2.54 (−70.3%)** | **73.7%** | **83.9% (+22.1 pp)** |

---

## 🚀 Quickstart: Loading from Hugging Face

### 1. Install CellularFlow
```bash
pip install git+https://github.com/celcilin/cellularflow.git
```

### 2. Run Inference
```python
import torch
from huggingface_hub import hf_hub_download
from cellularflow import CellularFlowLM, CellularFlowTrainer

REPO_ID = "celcilin/cellularflow-v4"

# Download model weights and tokenizer from Hugging Face
weights_file = hf_hub_download(repo_id=REPO_ID, filename="CMC_BaseModel.pt")

# Instantiate CellularFlow v4
model = CellularFlowLM(
    vocab_size=8192,
    dim=512,
    n_layers=6,
    n_heads=8,
    n_entries=256,
    context_len=256,
    use_episodic=True
)

# Load pretrained weights
state_dict = torch.load(weights_file, map_location="cpu")
model.load_state_dict(state_dict)
model.eval()

print("CellularFlow v4 loaded successfully!")
```

---

## 🔬 Continual Learning Regimes

1. **Mode 1 — Live Learn (`inference_write=True`):** Updates DNA memory values on the fly via Exponential Moving Average (EMA) with zero backward pass. Protected by **Spherical Anisotropy Regularization**.
2. **Mode 2 — Selective Fine-Tuning (`set_mode("selective")`):** Freezes ~85% of the backbone and updates only DNA memory banks, eliminating catastrophic forgetting.
3. **Mode 3 — Episodic Fact Injection (`inject_fact()`):** Writes facts into slot-based episodic memory with temporal decay and post-epoch consolidation.

---

## 📖 Citation

```bibtex
@article{celcilin2026cellularflow,
  title={CellularFlow: A Memory-Augmented Continual-Learning Architecture Decoupling Associative Memory from Sequence Reasoning},
  author={Celcilin C S},
  journal={arXiv preprint},
  year={2026},
  url={https://github.com/celcilin/cellularflow}
}
```