phuocsang/mta-csd download history

phuocsang/mta-csd is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 187 times (46 in the last 7 days), and 957 times in total. It ranks #71,228 among datasets by monthly downloads.

Use Entropy Weight Currently, Distilm and CSD are supported. See example in distillm-master/scripts/gpt2/spandistillm/train_0.1B_1.5B_entropy.sh Use flag OPTS+=" --entropy_weight"

Open phuocsang/mta-csd on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.