MCPcopy Create free account
hub / github.com/CERT-Lab/lora-sb / load_and_preprocess_data

Function load_and_preprocess_data

utils/data_utils.py:27–146  ·  view source on GitHub ↗
(task, tokenizer, args)

Source from the content-addressed store, hash-verified

25)
26
27def load_and_preprocess_data(task, tokenizer, args):
28
29 if "mnli" in task:
30 dataset = load_dataset("glue", "mnli")
31 else:
32 dataset = load_dataset("glue", task)
33
34 def tokenize_function(examples):
35
36 # Handle different input formats
37 if "premise" in examples and "hypothesis" in examples:
38 # MNLI and similar tasks
39 return tokenizer(
40 examples["premise"],
41 examples["hypothesis"],
42 truncation=True,
43 padding="max_length",
44 max_length=args.max_seq_length,
45 )
46 elif "question" in examples and "sentence" in examples:
47 # QNLI and similar tasks
48 return tokenizer(
49 examples["question"],
50 examples["sentence"],
51 truncation=True,
52 padding="max_length",
53 max_length=args.max_seq_length,
54 )
55 elif "sentence1" in examples and "sentence2" in examples:
56 # MRPC, STS-B
57 return tokenizer(
58 examples["sentence1"],
59 examples["sentence2"],
60 truncation=True,
61 padding="max_length",
62 max_length=args.max_seq_length,
63 )
64 elif "question1" in examples and "question2" in examples:
65 # QQP
66 return tokenizer(
67 examples["question1"],
68 examples["question2"],
69 truncation=True,
70 padding="max_length",
71 max_length=args.max_seq_length,
72 )
73 elif "sentence" in examples:
74 # CoLA, SST-2
75 return tokenizer(
76 examples["sentence"],
77 truncation=True,
78 padding="max_length",
79 max_length=args.max_seq_length,
80 )
81 else:
82 raise ValueError(f"Unexpected format for task {task}")
83
84 tokenized_datasets = dataset.map(tokenize_function, batched=True)

Callers 1

finetuneFunction · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected