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
- -
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.