VADRK155/Cortex-4-Beta-Flash-Story

Cortex-4-Beta-Flash-Story

A small GPT model for story generation, trained completely from scratch (custom PyTorch architecture, no transformers library involved).

• —Parameters: ~40M
• —Weights format: fp16
• —Context length: 128 tokens

How to run

1. 1.Install dependencies:

pip install -r requirements.txt

1. 1.Run:

python chat.py

Example

You: Once upon a time Cortex_2: Once upon a time there was a little girl who wanted to explore the world...

Limitations

This is a small model, so it may lose coherence, mix up facts, or cut off mid-thought — expected behavior for this parameter count.