Spaces:

LisaMegaWatts
/

MonarchSLM

Running

App Files Files Community

MonarchSLM / server.jl

Commit History

Cache Monarch matrices + causal mask for faster inference

76b7110

Running
verified

LisaMegaWatts commited on about 1 month ago

Fix completion_tokens: count tokens not decoded characters

f0aedd4
verified

LisaMegaWatts commited on Feb 26

Upload server.jl with huggingface_hub

91c86b7
verified

LisaMegaWatts commited on Feb 25