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 Dec 25, 2024 • 1
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 Dec 17, 2024 • 2
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 Dec 17, 2024 • 1