File size: 2,471 Bytes
ce52391
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f5b2141
 
 
 
 
 
 
 
 
ce52391
f5b2141
ce52391
f5b2141
 
 
 
 
 
 
 
 
 
 
0c783bc
 
 
 
 
45df06f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0c783bc
 
45df06f
 
 
 
 
 
 
 
0c783bc
f5b2141
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
---
dataset_info:
  features:
  - name: en
    dtype: string
  - name: vi
    dtype: string
  splits:
  - name: test
    num_bytes: 192744
    num_examples: 2000
  - name: train
    num_bytes: 82614470
    num_examples: 1000000
  - name: validation
    num_bytes: 194721
    num_examples: 2000
  download_size: 59201490
  dataset_size: 83001935
task_categories:
- translation
language:
- en
- vi
tags:
- LM
size_categories:
- 1M<n<10M
---
# Opus100

- Source: https://huggingface.co/datasets/opus100
- Num examples: 
  - 1,000,000 (train)
  - 2,000 (validation)
  - 192,744 (test)
- Language: English

```python
from datasets import load_dataset

load_dataset("tdtunlp/opus100_envi")
```

- Format for Translation task

```python
def preprocess(
    sample,
    instruction_key="### Instruction:",
    input_key="Input:",
    response_key="<|endofprompt|>",
    end_key="<|endoftext|>",
    en2vi=True,
):
    if en2vi:
        if random.random() < 0.5:
            instruction = "Translate the following sentences from English into Vietnamese."
        else:
            instruction = "Dịch các câu sau từ tiếng Anh sang tiếng Việt."
        
        input = sample['en'].strip()
        response = sample['vi'].strip()
    else:
        if random.random() < 0.5:
            instruction = "Translate the following sentences from Vietnamese into English."
        else:
            instruction = "Dịch các câu sau từ tiếng Việt sang tiếng Anh."
        
        input = sample['vi'].strip()
        response = sample['en'].strip()

    return {'text': """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
{instruction_key}
{instruction}
{input_key} 
{input}
{response_key}
{response}
{end_key}""".format(
    instruction_key=instruction_key,
    instruction=instruction,
    input_key=input_key,
    input=input,
    response_key=response_key,
    response=response,
    end_key=end_key,
)}

"""
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
Dịch các câu sau từ tiếng Anh sang tiếng Việt.
Input: 
Toast falls jelly-side down, children hit tables and people get hurt.
<|endofprompt|>
Bánh mì nướng rơi đông lại, trẻ con va vào bàn và con người bị thương.
<|endoftext|>
"""
```