MCPcopy Create free account
hub / github.com/OpenBitSys/BitDistiller / padding

Function padding

data/generation/generate.py:111–123  ·  view source on GitHub ↗
(inputs, padding_token, cutoff = None)

Source from the content-addressed store, hash-verified

109 return dict(input_ids=self.input_ids[i], labels=self.labels[i], id=i)
110
111def padding(inputs, padding_token, cutoff = None):
112 num_elems = len(inputs)
113 if cutoff is None:
114 cutoff = max([len(item) for item in inputs])
115 else:
116 cutoff = min(max([len(item) for item in inputs]), cutoff)
117
118 tokens = torch.ones(num_elems, cutoff).long().to(inputs[0].device) * padding_token
119 for i in range(num_elems):
120 toks = inputs[i]
121 length = min(cutoff, len(toks))
122 tokens[i, -length:] = toks[-length:]
123 return tokens
124
125@dataclass
126class DataCollatorForSupervisedDataset(object):

Callers 1

__call__Method · 0.70

Calls

no outgoing calls

Tested by

no test coverage detected