A scalable, effective, and general way to augment LLMs with billion-scale knowledge graphs using very little GPU memory cost.
-
HaoyuHuang2/AtlasKV_all-MiniLM-L6-v2_train_atlas_cc_qkv_llama3_step_3000
9B • Updated • 5 -
HaoyuHuang2/AtlasKV_all-MiniLM-L6-v2_train_atlas_cc_qkv_llama3_step_3000_encoder
Updated -
HaoyuHuang2/AtlasKV_all-MiniLM-L6-v2_train_atlas_wiki_qkv_llama3_step_3000
9B • Updated • 4 -
HaoyuHuang2/AtlasKV_all-MiniLM-L6-v2_train_atlas_wiki_qkv_llama3_step_3000_encoder
Updated