|
|
--- |
|
|
license: mit |
|
|
datasets: |
|
|
- roneneldan/TinyStories |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- LLM |
|
|
- pytorch |
|
|
- Story |
|
|
- Text |
|
|
--- |
|
|
|
|
|
# Story-LLM (TinyStories Transformer) |
|
|
|
|
|
 |
|
|
|
|
|
Story-LLM is a small GPT-style Transformer language model trained from scratch on the **TinyStories** dataset. |
|
|
|
|
|
This repository contains **pretrained weights and a tokenizer**. |
|
|
The model uses a **custom PyTorch architecture** and **ByteLevel BPE tokenizer**. |
|
|
|
|
|
👉 **For full documentation, training code, and usage instructions, see the GitHub repository:** |
|
|
**https://github.com/Daniel-Gia/Story-LLM** |
|
|
|
|
|
--- |
|
|
|
|
|
### Notes |
|
|
|
|
|
- ~29M parameters |
|
|
|
