Hugging Face's logo

D0men1c0
/
ISSR_Dark_Web_26Topics_Raid

Text Classification
BERTopic
Model card Files Community
D0men1c0 commited on
Commit
45d9df9
•
1 Parent(s): a0ddcbb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -96
README.md CHANGED
@@ -1,96 +1,103 @@
1
-
2
- ---
3
- tags:
4
- - bertopic
5
- library_name: bertopic
6
- pipeline_tag: text-classification
7
- ---
8
-
9
- # ISSR_Dark_Web_26Topics_Raid
10
-
11
- This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model.
12
- BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
13
-
14
- ## Usage
15
-
16
- To use this model, please install BERTopic:
17
-
18
- ```
19
- pip install -U bertopic
20
- ```
21
-
22
- You can use the model as follows:
23
-
24
- ```python
25
- from bertopic import BERTopic
26
- topic_model = BERTopic.load("D0men1c0/ISSR_Dark_Web_26Topics_Raid")
27
-
28
- topic_model.get_topic_info()
29
- ```
30
-
31
- ## Topic overview
32
-
33
- * Number of topics: 27
34
- * Number of training documents: 94407
35
-
36
- <details>
37
- <summary>Click here for an overview of all topics.</summary>
38
-
39
- | Topic ID | Topic Keywords | Topic Frequency | Label |
40
- |----------|----------------|-----------------|-------|
41
- | -1 | free - how - accounts - logs - the | 594 | -1_free_how_accounts_logs |
42
- | 0 | database - data - db - databases - dump | 36319 | Data Collection |
43
- | 1 | hacking - security - course - windows - hacker | 7773 | Windows Hacking Course |
44
- | 2 | mega - onlyfans - collection - gb - nsfw | 5313 | NSFW Mega OnlyFans Pack |
45
- | 3 | email - pass - mail - email pass - access | 4326 | Email Pass Access Combo |
46
- | 4 | the - kek - de - dodgy - vs | 4292 | MMA Fights |
47
- | 5 | combo - combolist - hq - private - gaming | 4707 | Gaming Combo List |
48
- | 6 | accounts - account - premium - capture - with | 2961 | Origin Account Capture |
49
- | 7 | htb - flag - writeup - hackthebox - root | 3649 | Hack The Box Root Flags Writeup |
50
- | 8 | leak - leaked - leaked download - database leaked - download | 2275 | Data Leak |
51
- | 9 | hello - hi - new - hey - im | 2027 | Hello New Member |
52
- | 10 | raid - raidforums - server - raiding - raid raid | 1732 | Server Raids |
53
- | 11 | anime - manga - animes - best - naruto | 2056 | Anime Favorites |
54
- | 12 | crypto - money - bitcoin - make - earn | 1120 | Earn Bitcoin Free Crypto Money Methods |
55
- | 13 | vpn - nordvpn - nord - accounts - nord vpn | 1811 | NordVPN Premium Accounts |
56
- | 14 | netflix - spotify - steam - minecraft - combo | 1017 | words or less |
57
- | 15 | twitch - youtube - streamer - stream - raid | 1136 | Twitch Raid Streams |
58
- | 16 | music - song - songs - favorite - cd | 1260 | Music Favorite |
59
- | 17 | spotify - spotify premium - premium - accounts - spotify accounts | 1002 | Spotify Premium Accounts |
60
- | 18 | dox - doxing - dox dox - doxed - doxxing | 864 | Doxing Tutorial |
61
- | 19 | discord - discord server - server - tokens - discord tokens | 810 | Discord Server Tokens |
62
- | 20 | scam - scam report - report - banned - banned scam | 881 | Scam |
63
- | 21 | proxy - proxies - socks - proxy list - http | 674 | Proxy Lists |
64
- | 22 | thread - help - what - new - time | 636 | Thread |
65
- | 23 | netflix - hulu - accounts - premium - netflix premium | 3631 | Premium Netflix Accounts |
66
- | 24 | instagram - twitter - followers - instagram account - account | 773 | Social Media Accounts for Sale |
67
- | 25 | discord - raid - discord raid - raid discord - discord server | 768 | Discord Raids |
68
-
69
- </details>
70
-
71
- ## Training hyperparameters
72
-
73
- * calculate_probabilities: True
74
- * language: None
75
- * low_memory: False
76
- * min_topic_size: 10
77
- * n_gram_range: (1, 4)
78
- * nr_topics: None
79
- * seed_topic_list: None
80
- * top_n_words: 10
81
- * verbose: True
82
- * zeroshot_min_similarity: 0.7
83
- * zeroshot_topic_list: None
84
-
85
- ## Framework versions
86
-
87
- * Numpy: 1.26.4
88
- * HDBSCAN: 0.8.36
89
- * UMAP: 0.5.6
90
- * Pandas: 2.2.1
91
- * Scikit-Learn: 1.4.1.post1
92
- * Sentence-transformers: 3.0.1
93
- * Transformers: 4.39.3
94
- * Numba: 0.60.0
95
- * Plotly: 5.22.0
96
- * Python: 3.12.2
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - bertopic
5
+ library_name: bertopic
6
+ pipeline_tag: text-classification
7
+ ---
8
+
9
+ # ISSR_Dark_Web_26Topics_Raid
10
+
11
+ This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model.
12
+ BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
13
+
14
+ ## Usage
15
+
16
+ To use this model, please install BERTopic:
17
+
18
+ ```
19
+ pip install -U bertopic
20
+ ```
21
+
22
+ You can use the model as follows:
23
+
24
+ ```python
25
+ from bertopic import BERTopic
26
+ topic_model = BERTopic.load("D0men1c0/ISSR_Dark_Web_26Topics_Raid")
27
+
28
+ topic_model.get_topic_info()
29
+ ```
30
+
31
+ You can make predictions as follows:
32
+ ```python
33
+ sentence = ['porn']
34
+ topic, _ = topic_model.transform(sentence)
35
+ topic_model.get_topic_info(topic[0])
36
+ ```
37
+
38
+ ## Topic overview
39
+
40
+ * Number of topics: 27
41
+ * Number of training documents: 94407
42
+
43
+ <details>
44
+ <summary>Click here for an overview of all topics.</summary>
45
+
46
+ | Topic ID | Topic Keywords | Topic Frequency | Label |
47
+ |----------|----------------|-----------------|-------|
48
+ | -1 | free - how - accounts - logs - the | 594 | -1_free_how_accounts_logs |
49
+ | 0 | database - data - db - databases - dump | 36319 | Data Collection |
50
+ | 1 | hacking - security - course - windows - hacker | 7773 | Windows Hacking Course |
51
+ | 2 | mega - onlyfans - collection - gb - nsfw | 5313 | NSFW Mega OnlyFans Pack |
52
+ | 3 | email - pass - mail - email pass - access | 4326 | Email Pass Access Combo |
53
+ | 4 | the - kek - de - dodgy - vs | 4292 | MMA Fights |
54
+ | 5 | combo - combolist - hq - private - gaming | 4707 | Gaming Combo List |
55
+ | 6 | accounts - account - premium - capture - with | 2961 | Origin Account Capture |
56
+ | 7 | htb - flag - writeup - hackthebox - root | 3649 | Hack The Box Root Flags Writeup |
57
+ | 8 | leak - leaked - leaked download - database leaked - download | 2275 | Data Leak |
58
+ | 9 | hello - hi - new - hey - im | 2027 | Hello New Member |
59
+ | 10 | raid - raidforums - server - raiding - raid raid | 1732 | Server Raids |
60
+ | 11 | anime - manga - animes - best - naruto | 2056 | Anime Favorites |
61
+ | 12 | crypto - money - bitcoin - make - earn | 1120 | Earn Bitcoin Free Crypto Money Methods |
62
+ | 13 | vpn - nordvpn - nord - accounts - nord vpn | 1811 | NordVPN Premium Accounts |
63
+ | 14 | netflix - spotify - steam - minecraft - combo | 1017 | words or less |
64
+ | 15 | twitch - youtube - streamer - stream - raid | 1136 | Twitch Raid Streams |
65
+ | 16 | music - song - songs - favorite - cd | 1260 | Music Favorite |
66
+ | 17 | spotify - spotify premium - premium - accounts - spotify accounts | 1002 | Spotify Premium Accounts |
67
+ | 18 | dox - doxing - dox dox - doxed - doxxing | 864 | Doxing Tutorial |
68
+ | 19 | discord - discord server - server - tokens - discord tokens | 810 | Discord Server Tokens |
69
+ | 20 | scam - scam report - report - banned - banned scam | 881 | Scam |
70
+ | 21 | proxy - proxies - socks - proxy list - http | 674 | Proxy Lists |
71
+ | 22 | thread - help - what - new - time | 636 | Thread |
72
+ | 23 | netflix - hulu - accounts - premium - netflix premium | 3631 | Premium Netflix Accounts |
73
+ | 24 | instagram - twitter - followers - instagram account - account | 773 | Social Media Accounts for Sale |
74
+ | 25 | discord - raid - discord raid - raid discord - discord server | 768 | Discord Raids |
75
+
76
+ </details>
77
+
78
+ ## Training hyperparameters
79
+
80
+ * calculate_probabilities: True
81
+ * language: None
82
+ * low_memory: False
83
+ * min_topic_size: 10
84
+ * n_gram_range: (1, 4)
85
+ * nr_topics: None
86
+ * seed_topic_list: None
87
+ * top_n_words: 10
88
+ * verbose: True
89
+ * zeroshot_min_similarity: 0.7
90
+ * zeroshot_topic_list: None
91
+
92
+ ## Framework versions
93
+
94
+ * Numpy: 1.26.4
95
+ * HDBSCAN: 0.8.36
96
+ * UMAP: 0.5.6
97
+ * Pandas: 2.2.1
98
+ * Scikit-Learn: 1.4.1.post1
99
+ * Sentence-transformers: 3.0.1
100
+ * Transformers: 4.39.3
101
+ * Numba: 0.60.0
102
+ * Plotly: 5.22.0
103
+ * Python: 3.12.2