Using GPT base model trained on Embedded C Code for designing Recommendation System.
pip install c_code_genFill me in please! Don’t forget code examples:
import torchif __name__ == "__main__":
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
x = torch.tensor([[1, 5, 6, 4, 3, 9, 5, 2, 0], [1, 8, 7, 3, 4, 5, 6, 7, 2]]).to(device)
trg = torch.tensor([[1, 7, 4, 3, 5, 9, 2, 0], [1, 5, 6, 2, 4, 7, 6, 2]]).to(device)
src_pad_idx = 0 # index of the padding token in source vocabulary
trg_pad_idx = 0 # index of the padding token in target vocabulary
src_vocab_size = 10 # number of unique tokens in source vocabulary
trg_vocab_size = 10 # number of unique tokens in target vocabulary
print(f"Input shape: {x.shape}")
print(f"Target shape: {trg.shape}")
print(f"Device available: {device}")
model = Transformer(src_vocab_size, trg_vocab_size, src_pad_idx, trg_pad_idx, device=device).to(device)
out = model(x, trg[:, :-1])
print(f"Output shape: {out.shape}")
print(f"Output: {out}")Input shape: torch.Size([2, 9])
Target shape: torch.Size([2, 8])
Device available: cuda
Output shape: torch.Size([2, 7, 10])
Output: tensor([[[ 0.4464, -0.5610, -0.7114, 0.9363, 0.6822, -1.5460, -0.5701,
-0.0960, 0.4808, 0.1313],
[-0.7031, 0.6683, -0.6762, -0.0794, -0.2506, -0.9622, -0.1848,
-0.7650, -0.2054, -0.5386],
[-0.0112, 0.4172, -0.1490, -1.0593, 0.2641, -0.8530, -0.3859,
-0.3926, -0.3144, -0.1417],
[ 0.4123, 0.3738, 0.6268, 0.8212, 1.1357, -1.1602, -0.0434,
-1.7120, 0.1721, -0.5142],
[-0.5740, 0.6748, 0.4170, 1.0975, -0.0173, -0.5885, -1.8482,
0.1379, 0.7698, -0.3862],
[ 0.6030, -0.1450, -0.4451, 1.1064, 0.1838, -1.0696, -0.4320,
0.0764, 0.5091, -0.2963],
[ 0.0264, 0.1590, -0.4393, 0.9079, 0.7149, -1.4549, 0.1765,
0.3150, 0.3267, -0.9601]],
[[ 0.5317, -0.5054, -0.6930, 0.9477, 0.7169, -1.3674, -0.5864,
-0.1622, 0.5145, 0.1502],
[-0.5181, 1.1593, -0.3028, 0.6865, -0.1220, -0.7017, -1.0549,
-0.4249, -0.0154, -0.7563],
[ 0.0823, 0.9191, -0.1109, 0.1114, 0.0602, -1.0653, -0.8787,
0.1198, -0.4894, -0.1040],
[ 0.1353, 0.4007, 0.1736, 0.0703, 1.2294, -1.2375, -0.2426,
-1.0955, 0.2159, -0.7532],
[ 0.1648, 0.3638, -0.1407, -0.5300, 0.3209, -0.3451, -1.0195,
0.1148, 0.8064, 0.1274],
[-0.6308, 0.8116, -0.6778, 0.9686, 0.0346, -0.8795, -0.4404,
-0.3469, 0.3887, -0.2115],
[ 0.1550, 0.5274, -0.3766, 0.5200, -0.2350, -1.2167, -0.4607,
0.2098, -0.1927, -0.5351]]], device='cuda:0',
grad_fn=<ViewBackward0>)