CoolFace
Modelpublic

jhyuckkim/DeepSeek-V2-Lite-Dense-3B-CP-K6

sourceHugging Faceotherupdated 28d agoView on Hugging Face
0likes559downloads
10 commits on main
5522fb928d ago

Align naming and results with the published arXiv version

jhyuckkim
815bf4628d ago

Match Qwen3 table convention, drop PPL column

jhyuckkim
f7db6d128d ago

Link released rows by name instead of a separate column

jhyuckkim
caf03f428d ago

Show full comparison table and link the paper

jhyuckkim
1a4098d28d ago

Remove internal paths from training info

jhyuckkim
457cec428d ago

Update citation, drop internal paths

jhyuckkim
e320e2928d ago

Add model card

jhyuckkim
88897cc28d ago

Add config with use_cache enabled

jhyuckkim
b98d66628d ago

Add distilled dense student weights

jhyuckkim
e1d1e0828d ago

initial commit

jhyuckkim