Open mirek190 opened 1 year ago
Are you planning WizardLM 65B model? Just asking ;)
Noways running such big models is quite easy with the cheap rtx 3090 and llama.cpp for instance - getting 2 tokens/s
yes, we are working on WizardLM 65B.
Are you planning WizardLM 65B model? Just asking ;)
Noways running such big models is quite easy with the cheap rtx 3090 and llama.cpp for instance - getting 2 tokens/s