Experimental models Collection Models which we made as an experiment. Usually more advanced chat models. • 2 items • Updated 1 day ago • 1
PGAM Collection Pinkstack general accuracy model(s). Created to hopefully be as accurate as possible. • 3 items • Updated 1 day ago • 2
Parm v2 Collection Advanced chat reasoning models trained on many different datasets, such as qwq and sonnet 3.5, these models excel in math, coding, explaining things. • 4 items • Updated about 11 hours ago • 2
PRAM v2 Collection Very advanced reasoning models trained on many different datasets, such as qwq and sonnet 3.5, these models excel in math, RP, explaining things. • 4 items • Updated 9 days ago • 1
PGAM Collection Pinkstack general accuracy model(s): trained to be accurate using different datasets such as Roblox luau dataset, etc. Not tested for reasoning. • 3 items • Updated 1 day ago • 1
PRAM v1 Collection Pinkstack reasoning accuracy model(s) are generally trained/fine tuned to be better at reasoning than original. V1 version, v2 is better overall. • 3 items • Updated 9 days ago • 1