Athspi LLM

🧠 A small but capable language model for creative story generation, trained on the TinyStories dataset.

Athspi Banner

Model Details

Architecture

  • Model Type: Transformer-based language model
  • Layers: 4
  • Embedding Dim: 384
  • Heads: 6
  • Sequence Length: 128 tokens
  • Parameters: ~28M

Training Data

  • Dataset: TinyStories
  • Training Coverage: 5% of dataset (~100k samples)

Usage

Installation

pip install torch transformers sentencepiece
Downloads last month
3
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.