License: MIT Hugging Face Parameters Format

This is a transformer-based GPT model.

Trained from scratch ( 50 tokens per parameter, according to Chinchilla rules, the optimal ratio is 20 tokens per parameter. )

Trained on texts, 50 million tokens (FineWeb-Edu + TinyStoryes tokens)

πŸ’¬ Example Conversations

Temperature: 0.5


You: Once upon a tree and I

AI: can help you want to the park. The cat. The dog was very happy. The bird had a big ball. The little boy named Sue was so unexpected happened, but he said, "Yes, but they could not know what. They played together.
Tim went to the dog! You have a big ball. It's mom told the ball was sad.
...

You: Once upon

AI: a big and started to play with his toys, but he saw a big and the cat.
The little girl named Tim. They saw a big, "Yes, but it. He found a big door. The bird said, "I am something unexpected happened. They played with his friends, but she did not want to play with her friends, "Don't know what it, "No, but she could not get the tree. She wanted to the park.
One day, they decided to play with the car. He went to help her toy.
...

use.py

Downloads last month
28
Safetensors
Model size
1.02M params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for VDC-team/VDrontGPT1m-Storyteller

Finetuned
(2)
this model

Dataset used to train VDC-team/VDrontGPT1m-Storyteller

Collection including VDC-team/VDrontGPT1m-Storyteller