guanmingchiu
/

dream-7b-tofu-sft

diffusion-language-model

Model card Files Files and versions

Dream-v0-Instruct-7B TOFU SFT target

Dream-7B fine-tuned on the TOFU author corpus, the MDLM unlearning target used in our study (EOS-corrected, 90 epochs).

Downloads last month: 23

Safetensors

Model size

8B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for guanmingchiu/dream-7b-tofu-sft

Base model

Dream-org/Dream-v0-Instruct-7B

Finetuned

(15)

this model

Finetunes

Collection including guanmingchiu/dream-7b-tofu-sft

LRCU: DLM Weight Unlearning

LRCU weight-unlearning checkpoints for masked diffusion LMs (LLaDA-8B, Dream-7B) on WMDP-bio/cyber and RWKU, plus a TOFU SFT target. • 10 items • Updated Jun 16