Instructions

Download All Files (Safetensors isnt needed)
Make sure all of the files are in the same folder
Run "Inference.py"

Information

12M Parameters
100M Tokens
9106 Tera Flops
17 Hours

Configuration

Intel i5 7200u
Nvidia 940MX

Speed

Disclaimer: These speeds are achieved with an Nvidia 940MX Initialization: 7 Seconds (From start to being able to generate)
Story: 1.5-2.5 Seconds (Depends on the length)

Output

Below is an example of what you should expect:

Once upon a time, there was a little boy named Timmy. Timmy loved to play outside in the park. One day, Timmy found a big, red ball. He picked it up and started to play with it. Suddenly, he heard a loud noise. It was a big truck! Timmy was very scared and didn't know what to do. Suddenly, the truck stopped and looked at Timmy's foot. It was a fire truck! Timmy was so happy that he ran towards the truck. He told his mom about the fire truck and how he found it. His mom smiled and said, "I told you it was a good thing to do, Timmy." Timmy felt better and went back to playing with the big, red ball. He was happy that he found a way to play with the truck and that he had learned something important. The end.

Downloads last month
11
Safetensors
Model size
12.3M params
Tensor type
F32
·
BOOL
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train ThatHungarian/AuroraStories-12M