CoolFace
Modelpublic

Raghav-Singhal/pbsftmix-cite-safety30-nosys-normal-3b

sourceHugging Faceupdated 4mo agoView on Hugging Face
0likes122downloads
2 commits on main
ef9e7474mo ago

instruct+safety mix SFT (field=messages_cite, 30% safety = 90000 safety + 210000 instruct of 300000; instruct=jkminder/model-raising-pbsft-instruct-300k safety=jkminder/model-raising-pbsft-safety-180k, template=epe-template-nosys, tokenizer=/capstor/store/cscs/swissai/a141/model-raising-training/checkpoints/pretraining/smollm2-3b/hf/epe-1p-3b-llama3arch-smollm2tok-500B-40n-2048sl-960gbsz-no_bce) on normal-3b-llama3arch-smollm2tok-500B-40n-2048sl-960gbsz

Raghav-Singhal
cab48064mo ago

initial commit

Raghav-Singhal