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
6
Safetensors
Model size
6.75B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.