Edit model card

GPT-2, But With Mistral's Tokenizer

Finally, an answer to one of the biggest open questions in NLP:

Q: Wouldn't it be messed up if someone grafted the tokenizer from Mistral 7B onto GPT-2?
A: Ya :)

Downloads last month
9
Safetensors
Model size
110M params
Tensor type
F32
·

Finetuned from