PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference
Paper • 2502.13502 • Published • 3
Pretrained PLDR-LLMs with KVG cache (Pytorch/Transformers)
PLDR-LLMs pretrained for paper titled "PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference"
-
-
fromthesky/PLDR-LLM-v51-104M
Text Generation • 0.1B • Updated • 12 -
fromthesky/PLDR-LLM-v51-110M-1
Text Generation • 0.1B • Updated • 11 -
fromthesky/PLDR-LLM-v51-110M-2
Text Generation • 0.1B • Updated • 16 -
fromthesky/PLDR-LLM-v51-110M-3
Text Generation • 0.1B • Updated • 16 -
fromthesky/PLDR-LLM-v51-110M-4
Text Generation • 0.1B • Updated • 11 -
fromthesky/PLDR-LLM-v51-110M-5
Text Generation • 0.1B • Updated • 10 -
fromthesky/PLDR-LLM-v51-DAG-110M
Text Generation • 0.1B • Updated • 11 -
fromthesky/PLDR-LLM-v51G-106M-1
Text Generation • 0.1B • Updated • 7 -
fromthesky/PLDR-LLM-v51G-106M-2
Text Generation • 0.1B • Updated • 12 -
fromthesky/PLDR-LLM-v51G-106M-3
Text Generation • 0.1B • Updated • 8