qwriter-en-7b

It's Qwen 2 7B, with the Mistral tokenizer, retrained with one billion tokens of equal parts fineweb-edu and straight up smut.

Still pretty smart, but much more likely to make things weird and uncomfortable. A+ base model!

Downloads last month
-
Safetensors
Model size
7B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support