ImadSaddik commited on
Commit
99fcf92
·
verified ·
1 Parent(s): 453a1e8

Updated README.md

Browse files
Files changed (1) hide show
  1. README.md +153 -24
README.md CHANGED
@@ -1,24 +1,153 @@
1
- ---
2
- license: mit
3
- dataset_info:
4
- features:
5
- - name: messages
6
- list:
7
- - name: content
8
- dtype: string
9
- - name: role
10
- dtype: string
11
- - name: language
12
- dtype: string
13
- splits:
14
- - name: train
15
- num_bytes: 58434
16
- num_examples: 100
17
- download_size: 26218
18
- dataset_size: 58434
19
- configs:
20
- - config_name: default
21
- data_files:
22
- - split: train
23
- path: data/train-*
24
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ dataset_info:
4
+ features:
5
+ - name: messages
6
+ list:
7
+ - name: content
8
+ dtype: string
9
+ - name: role
10
+ dtype: string
11
+ - name: language
12
+ dtype: string
13
+ splits:
14
+ - name: train
15
+ num_bytes: 58434
16
+ num_examples: 100
17
+ download_size: 26218
18
+ dataset_size: 58434
19
+ configs:
20
+ - config_name: default
21
+ data_files:
22
+ - split: train
23
+ path: data/train-*
24
+ ---
25
+
26
+ # BoDmagh dataset 🧠
27
+
28
+ The BoDmagh dataset is a Supervised Fine-Tuning (SFT) dataset for the Darija language. I created it manually, ensuring high quality. The dataset is in JSON format and includes conversations between a user and an assistant.
29
+
30
+ I update the dataset daily, so make sure to check the repository regularly.
31
+
32
+ ## Time Spent
33
+
34
+ Creating this dataset has been a labor of love. I’ve dedicated approximately **5 hours and 48 minutes** so far, manually curating each entry to ensure high quality. I continue to add new entries daily, so this number will keep growing.
35
+
36
+ ## Content
37
+
38
+ ### 1. Structure
39
+
40
+ Each item in the JSON file is a list. The list contains multiple objects, where each object represents a turn in the conversation. The turns are marked as either `user` or `assistant`. The `system` message is not included, but you can add it at the start of the list if needed.
41
+
42
+ Here are 2 examples:
43
+
44
+ ```json
45
+ [
46
+ [
47
+ {
48
+ "role": "user",
49
+ "content": "السلام لباس؟"
50
+ },
51
+ {
52
+ "role": "assistant",
53
+ "content": "لاباس الحمد لله، كاين شي حاجا بغيتي نعاونك فيها؟"
54
+ },
55
+ {
56
+ "role": "user",
57
+ "content": "اه عافاك بغيت نسافر فالمغرب فالصيف ولكن معرفتش فين نمشي. ممكن تعاوني؟"
58
+ },
59
+ {
60
+ "role": "assistant",
61
+ "content": "بلان كاين بزاف ديال البلايص اللي تقد تمشي ليهم فالمغرب، انا كنقترح عليك هدو:\n\n- شفشاون: هدي مدينة فالجبل، الديور ديالها زرقين او الجو فالمدينة كيجيب الراحة.\n- الصويرة: هاد المدينة فيها البحر الا فيك ميعوم. البحر ديالها زوين او فيها المدينة القديمة.\n- الداخلة: الداخلة هي مدينة فالصحرا ديال المغرب، حتاهيا فيها البحر. الناس كيجيو ليه من العالم كامل باش يلعبوا السبور.\n- مراكش: هاد المدينة عزيزة على السياح لكيجيو من برا. فيها جامع الفنا، المدينة القديمة ولكن فالصيف دايرة بحال الفران.\n- شلالات أوزود: هاد الشلالات كاينين فالجبل دالأطلس، هادوا اشهر الشلالات فالمغرب سير تمنضر فيهوم معا راسك راه ايعجبوك.\n\nكاين بزاف ديال البلايس اخرين فالمغرب ولكن غولي بعدا واش هدوا عجبوك."
62
+ },
63
+ {
64
+ "role": "user",
65
+ "content": "شكرا بزاف اصاحبي"
66
+ },
67
+ {
68
+ "role": "assistant",
69
+ "content": "مرحبا، إلى بغيتي شت حاجة أخرى غولهالي انا هنا باش نعاونك."
70
+ },
71
+ {
72
+ "role": "user",
73
+ "content": "لالا صافي مبغيت حتى شي حاجة"
74
+ },
75
+ {
76
+ "role": "assistant",
77
+ "content": "اوكي اوا نمشي نرتاح شوية على هاد الحساب. ستمتع معا راسك بالتسافيرة."
78
+ }
79
+ ],
80
+ [
81
+ {
82
+ "role": "user",
83
+ "content": "عافاك شحال من مدينة كاينة فالمغرب؟"
84
+ },
85
+ {
86
+ "role": "assistant",
87
+ "content": "الصراحة صعيب تلقى رقم واحد ولكن على حساب متعلمت كاين شي 247 مدينة."
88
+ },
89
+ {
90
+ "role": "user",
91
+ "content": "اوكي شكرا."
92
+ },
93
+ {
94
+ "role": "assistant",
95
+ "content": "العفو، كاين شي حاجة أخرى بغيتي نعاونك فيها؟"
96
+ }
97
+ ]
98
+ ]
99
+ ```
100
+
101
+ ### 2. Assistant's name
102
+
103
+ Sometimes the assistant's name is included. The assistant's name is `بودماغ`. If you find this word, you can replace it with any other name. Here's an example:
104
+
105
+ ```json
106
+ [
107
+ {
108
+ "role": "user",
109
+ "content": "أهلا شنو سميتك؟"
110
+ },
111
+ {
112
+ "role": "assistant",
113
+ "content": "انا سميتي بودماغ، ساوبني عماد الصاديق باش نساعدك فاي حاجة اللي نقد نعاون فيها."
114
+ },
115
+ {
116
+ "role": "user",
117
+ "content": "هههه سمية واعرة عجباتني"
118
+ },
119
+ {
120
+ "role": "assistant",
121
+ "content": "هههه واييه راه عندي دماغ كبير غا باش نقد نعاونك فاي حاجة الى كنت نعرف ليها."
122
+ },
123
+ {
124
+ "role": "user",
125
+ "content": "شناهيا العاصمة دالمغرب؟"
126
+ },
127
+ {
128
+ "role": "assistant",
129
+ "content": "العاصمة دالمغرب هي الرباط."
130
+ }
131
+ ]
132
+ ```
133
+
134
+ ### 3. Special tokens
135
+
136
+ This dataset doesn't use any special tokens. Since everyone uses different tokens, feel free to add them as needed.
137
+
138
+ ## Contributing
139
+
140
+ As I mentioned, I'm manually creating this dataset to ensure high quality. If you'd like to help, follow these steps:
141
+
142
+ 1. Fork the repository.
143
+ 2. Create a new branch.
144
+ 3. Add entries to the dataset.
145
+ 4. Create a pull request.
146
+
147
+ ## Wanna talk?
148
+
149
+ You can contact me through:
150
+
151
+ - **Discord** - Username: imad_saddik
152
+ - **LinkedIn** – [Connect with me](https://www.linkedin.com/in/imadsaddik/).
153
+ - **Email** – [simad3647@gmail.com](mailto:simad3647@gmail.com).