def smollm2_135m

bend-ml-llama@0.2.1.0 · main.bend:150

import Base

150# SmolLM2-135M (HuggingFaceTB/SmolLM2-135M): 3 key/value heads of 3 query heads each, heads of 64
151def smollm2_135m() -> Cfg:
152  Cfg{3n, 3n, 32n, 1536n, 30n, 49152n, 0.00001, 100000.0}