README.md

---
license: apache-2.0
datasets:
- pico-lm/pretokenized-dolma
language:
- en
metrics:
- pico-lm/perplexity
pipeline_tag: text-generation
---

# Pico Decoder Large

**pico-decoder-large** is the largest model (570M) in the current `pico-decoder` suite. It is a full-scale research model designed for in-depth interpretability studies of transformer learning. Trained with [`pico-train`](https://github.com/pico-lm) and fully compatible with [`pico-analyze`](https://github.com/pico-lm), it offers rich checkpointing and analytical insight into large-scale LM behavior.

## 🔧 Model Details

| Field               | Value                              |
|---------------------|------------------------------------|
| **Architecture**     | Decoder-only transformer (LLaMA-style) |
| **Parameters**       | 570M                              |
| **Layers**           | 12                                |
| **Hidden Size**      | 1536                              |
| **Feed Forward Size**| 6144                              |
| **Attention Heads**  | 12                                |
| **Key/Value Heads**  | 4                                |

## 📚 Training

- **Dataset**: [`pretokenized-dolma`](https://github.com/pico-lm)
- **Training steps**: 200,000
- **Batch size**: 1024
- **Sequence length**: 2048
- **Optimizer**: AdamW
- **Learning rate schedule**: Linear decay with warmup
- **Compute**: 16 A100-SXM4-80GB GPUs

## 📈 Evaluation and Analysis

This model supports fine-grained analysis using [pico-analyze](https://github.com/pico-lm). This tool enables researchers to understand how learning unfolds over training, even at very small scales.

We also evaluate perplexity of the model on the [pico-paloma-tinsy](https://huggingface.co/datasets/pico-lm/pretokenized-paloma-tinsy) dataset.

## 📄 Citation

```bibtex
@software{pico2025,
    author = {Diehl Martinez, Richard},
    title = {Pico: A Lightweight Framework for Studying Language Model Learning Dynamics},
    year = {2025},
    url = {https://github.com/pico-lm}
}