CoolFace
Modelpublic

kevinshin/qwen2.5-1.5b-rft-rpo-lr-1e-5-alpha-1-beta-0.01-wc-cw-3k-neg-rethink-pos

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes23downloads
6 commits on main
dc8c7351y ago

Add converted safetensors from FSDP checkpoint (data/qwen2.5-1.5b-rft-rpo-lr-1e-5-alpha-1-beta-0.01-wc-cw-3k-neg-rethink-pos/checkpoint-560/pytorch_model_fsdp_0)

kevinshin
cdc118f1y ago

Delete existing weight shards/index files before replacement

kevinshin
656ab0f1y ago

End of training

kevinshin
cd46a8b1y ago

Model save

kevinshin
dd3c5e71y ago

Training in progress, epoch 0

kevinshin
0905e0f1y ago

initial commit

kevinshin