QUICK START
Build a basic SOUP model.
PYTHON
import torch
from mlbricks import SOUP
model = SOUP(
dim=512,
width=1116,
depth=2,
mixer="esa",
ffn="saffn",
backend="auto",
)
x = torch.randn(2, 128, 512)
y = model(x)PER-LAYER CHOICES
PYTHON
model = SOUP(
dim=512,
width=[1116, 1116],
depth=2,
mixer=["esa", "bolt"],
ffn=["saffn", "saffn"],
backend="auto",
)RECURRENT GENERATION
PYTHON
model = model.eval()
model.prepare_generation()
prompt_out, cache = model.prefill(prompt_hidden)
next_out, cache = model.decode_step(next_hidden, cache)