---
license: mit
datasets:
- roneneldan/TinyStories
language:
- en
---

This is a Llama 2 architecture model series trained on the TinyStories dataset, intended for use in the [llama2.c](https://github.com/karpathy/llama2.c) project by Andrej Karpathy. 

Trained on a single v100 32GB GPU for 3 epochs, we achieve an inference speed of ~72 tokens/sec on the same.

Achieved tok/s: **147.196262** on 12th Gen Intel(R) Core(TM) i9-12900HK

Learn more on how to run inference in pure C using [llama2.c](https://github.com/karpathy/llama2.c)