Full finetune of Qwen3-0.6B on the surprisal test dataset. This model has a lot of issues, but for the best results, it should be prefilled with a tag at the beginning of it's response.

Downloads last month
-
Safetensors
Model size
0.6B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support