def __init__(self):
super(LargeModel, self).__init__()
dim = 15
n = 4 * 100
self.emb = nn.Embedding(n, dim)
self.lin1 = nn.Linear(dim, 1)
self.seq = nn.Sequential(
self.emb,
self.lin1,
)
def __init__(self,
n_token: int,
n_head: int = 8,
d_model: int = 512,
d_ff: int = 2048):
super().__init__()
p_dropout = nn.ValueChoice([0.1, 0.2, 0.3, 0.4, 0.5],
label='p_dropout')
n_layer = nn.ValueChoice([5, 6, 7, 8, 9], label='n_layer')
self.encoder = nn.TransformerEncoder(
nn.TransformerEncoderLayer(d_model, n_head, d_ff, p_dropout),
n_layer)
self.d_model = d_model
self.decoder = nn.Linear(d_model, n_token)
self.embeddings = nn.Embedding(n_token, d_model)
self.position = PositionalEncoding(d_model)
def __init__(self, config):
super(SNLIClassifier, self).__init__()
self.config = config
self.embed = nn.Embedding(config.n_embed, config.d_embed)
self.projection = Linear(config.d_embed, config.d_proj)
self.encoder = Encoder(config)
self.dropout = nn.Dropout(p=config.dp_ratio)
self.relu = nn.ReLU()
seq_in_size = 2 * config.d_hidden
if self.config.birnn:
seq_in_size *= 2
lin_config = [seq_in_size] * 2
self.out = nn.Sequential(Linear(*lin_config), self.relu,
self.dropout, Linear(*lin_config),
self.relu, self.dropout,
Linear(*lin_config), self.relu,
self.dropout,
Linear(seq_in_size, config.d_out))
def __init__(self, config):
super(SNLIClassifier, self).__init__()
self.embed = nn.Embedding(config["n_embed"], config["d_embed"])
self.projection = Linear(config["d_embed"], config["d_proj"])
self.encoder = Encoder(config)
self.dropout = nn.Dropout(p=config["dp_ratio"])
self.relu = nn.ReLU()
seq_in_size = 2 * config["d_hidden"]
if config["birnn"]:
seq_in_size *= 2
lin_config = [seq_in_size] * 2
self.out = nn.Sequential(Linear(*lin_config), self.relu,
self.dropout, Linear(*lin_config),
self.relu, self.dropout,
Linear(*lin_config), self.relu,
self.dropout,
Linear(seq_in_size, config["d_out"]))
self.fix_emb = config["fix_emb"]
self.project = config["projection"]