This Deepseek "Minny" was a somewhat naive attempt at pushing the capabilities of a 1.5B model, without retraining.
-
ForSureTesterSim/merge-test-4-battle-of-rl-paradigms
Text Generation • 2B • Updated • 6 -
ForSureTesterSim/merge-test-3-deep-delta
Text Generation • 2B • Updated • 4 -
ForSureTesterSim/merge-test-2-sibling-violation
Text Generation • 2B • Updated • 7 -
ForSureTesterSim/merge-test-1-golden-triangle
Text Generation • 2B • Updated • 7