Upload ModernBERT model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,777 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:901028
+- loss:CosineSimilarityLoss
+base_model: Shuu12121/CodeModernBERT-Owl
+widget:
+- source_sentence: "    public void scan() throws Throwable {\n        client = new\
+    \ FTPClient();\n        log.info(\"connecting to \" + host + \"...\");\n     \
+    \   client.connect(host);\n        log.info(client.getReplyString());\n      \
+    \  log.info(\"logging in...\");\n        client.login(\"anonymous\", \"\");\n\
+    \        log.info(client.getReplyString());\n        Date date = Calendar.getInstance().getTime();\n\
+    \        xmlDocument = new XMLDocument(host, dir, date);\n        scanDirectory(dir);\n\
+    \    }\n"
+  sentences:
+  - "    public static void zip(ZipOutputStream out, File f, String base) throws Exception\
+    \ {\n        if (f.isDirectory()) {\n            File[] fl = f.listFiles();\n\
+    \            base = base.length() == 0 ? \"\" : base + File.separator;\n     \
+    \       for (int i = 0; i < fl.length; i++) {\n                zip(out, fl[i],\
+    \ base + fl[i].getName());\n            }\n        } else {\n            out.putNextEntry(new\
+    \ org.apache.tools.zip.ZipEntry(base));\n            FileInputStream in = new\
+    \ FileInputStream(f);\n            IOUtils.copyStream(in, out);\n            in.close();\n\
+    \        }\n        Thread.sleep(10);\n    }\n"
+  - "    public static void zip(String destination, String folder) {\n        File\
+    \ fdir = new File(folder);\n        File[] files = fdir.listFiles();\n       \
+    \ PrintWriter stdout = new PrintWriter(System.out, true);\n        int read =\
+    \ 0;\n        FileInputStream in;\n        byte[] data = new byte[1024];\n   \
+    \     try {\n            ZipOutputStream out = new ZipOutputStream(new FileOutputStream(destination));\n\
+    \            out.setMethod(ZipOutputStream.DEFLATED);\n            for (int i\
+    \ = 0; i < files.length; i++) {\n                try {\n                    stdout.println(files[i].getName());\n\
+    \                    ZipEntry entry = new ZipEntry(files[i].getName());\n    \
+    \                in = new FileInputStream(files[i].getPath());\n             \
+    \       out.putNextEntry(entry);\n                    while ((read = in.read(data,\
+    \ 0, 1024)) != -1) {\n                        out.write(data, 0, read);\n    \
+    \                }\n                    out.closeEntry();\n                  \
+    \  in.close();\n                } catch (Exception e) {\n                    e.printStackTrace();\n\
+    \                }\n            }\n            out.close();\n        } catch (IOException\
+    \ ex) {\n            ex.printStackTrace();\n        }\n    }\n"
+  - "    private void copyFile(URL from, File to) {\n        try {\n            InputStream\
+    \ is = from.openStream();\n            IOUtils.copy(is, new FileOutputStream(to));\n\
+    \        } catch (IOException e) {\n            e.printStackTrace();\n       \
+    \ }\n    }\n"
+- source_sentence: "    public void createMd5Hash() {\n        try {\n           \
+    \ String vcardObject = new ContactToVcard(TimeZone.getTimeZone(\"UTC\"), \"UTF-8\"\
+    ).convert(this);\n            MessageDigest m = MessageDigest.getInstance(\"MD5\"\
+    );\n            m.update(vcardObject.getBytes());\n            this.md5Hash =\
+    \ new BigInteger(m.digest()).toString();\n            if (log.isTraceEnabled())\
+    \ {\n                log.trace(\"Hash is:\" + this.md5Hash);\n            }\n\
+    \        } catch (ConverterException ex) {\n            log.error(\"Error creating\
+    \ hash:\" + ex.getMessage());\n        } catch (NoSuchAlgorithmException noSuchAlgorithmException)\
+    \ {\n            log.error(\"Error creating hash:\" + noSuchAlgorithmException.getMessage());\n\
+    \        }\n    }\n"
+  sentences:
+  - "    public static void main(String[] args) {\n        try {\n            int\
+    \ encodeFlag = 0;\n            if (args[0].equals(\"-e\")) {\n               \
+    \ encodeFlag = Base64.ENCODE;\n            } else if (args[0].equals(\"-d\"))\
+    \ {\n                encodeFlag = Base64.DECODE;\n            }\n            String\
+    \ infile = args[1];\n            String outfile = args[2];\n            File fin\
+    \ = new File(infile);\n            FileInputStream fis = new FileInputStream(fin);\n\
+    \            BufferedInputStream bis = new BufferedInputStream(fis);\n       \
+    \     Base64.InputStream b64in = new Base64.InputStream(bis, encodeFlag | Base64.DO_BREAK_LINES);\n\
+    \            File fout = new File(outfile);\n            FileOutputStream fos\
+    \ = new FileOutputStream(fout);\n            BufferedOutputStream bos = new BufferedOutputStream(fos);\n\
+    \            byte[] buff = new byte[1024];\n            int read = -1;\n     \
+    \       while ((read = b64in.read(buff)) >= 0) {\n                bos.write(buff,\
+    \ 0, read);\n            }\n            bos.close();\n            b64in.close();\n\
+    \        } catch (Exception e) {\n            e.printStackTrace();\n        }\n\
+    \    }\n"
+  - "    public static String md5(String str) {\n        StringBuffer buf = new StringBuffer();\n\
+    \        try {\n            MessageDigest md = MessageDigest.getInstance(\"MD5\"\
+    );\n            byte[] data = new byte[32];\n            md.update(str.getBytes(md5Encoding),\
+    \ 0, str.length());\n            data = md.digest();\n            for (int i =\
+    \ 0; i < data.length; i++) {\n                int halfbyte = (data[i] >>> 4) &\
+    \ 0x0F;\n                int two_halfs = 0;\n                do {\n          \
+    \          if ((0 <= halfbyte) && (halfbyte <= 9)) buf.append((char) ('0' + halfbyte));\
+    \ else buf.append((char) ('a' + (halfbyte - 10)));\n                    halfbyte\
+    \ = data[i] & 0x0F;\n                } while (two_halfs++ < 1);\n            }\n\
+    \        } catch (Exception e) {\n            errorLog(\"{Malgn.md5} \" + e.getMessage());\n\
+    \        }\n        return buf.toString();\n    }\n"
+  - "    public static String md5(String text, String charset) {\n        MessageDigest\
+    \ msgDigest = null;\n        try {\n            msgDigest = MessageDigest.getInstance(\"\
+    MD5\");\n        } catch (NoSuchAlgorithmException e) {\n            throw new\
+    \ IllegalStateException(\"System doesn't support MD5 algorithm.\");\n        }\n\
+    \        msgDigest.update(text.getBytes());\n        byte[] bytes = msgDigest.digest();\n\
+    \        byte tb;\n        char low;\n        char high;\n        char tmpChar;\n\
+    \        String md5Str = new String();\n        for (int i = 0; i < bytes.length;\
+    \ i++) {\n            tb = bytes[i];\n            tmpChar = (char) ((tb >>> 4)\
+    \ & 0x000f);\n            if (tmpChar >= 10) {\n                high = (char)\
+    \ (('a' + tmpChar) - 10);\n            } else {\n                high = (char)\
+    \ ('0' + tmpChar);\n            }\n            md5Str += high;\n            tmpChar\
+    \ = (char) (tb & 0x000f);\n            if (tmpChar >= 10) {\n                low\
+    \ = (char) (('a' + tmpChar) - 10);\n            } else {\n                low\
+    \ = (char) ('0' + tmpChar);\n            }\n            md5Str += low;\n     \
+    \   }\n        return md5Str;\n    }\n"
+- source_sentence: "            @Override\n            public void run() {\n     \
+    \           try {\n                    IOUtils.copy(getSource(), processStdIn);\n\
+    \                    System.err.println(\"Copy done.\");\n                   \
+    \ close();\n                } catch (IOException e) {\n                    e.printStackTrace();\n\
+    \                    IOUtils.closeQuietly(ExternalDecoder.this);\n           \
+    \     }\n            }\n"
+  sentences:
+  - "    private String readJsonString() {\n        StringBuilder builder = new StringBuilder();\n\
+    \        HttpClient client = new DefaultHttpClient();\n        HttpGet httpGet\
+    \ = new HttpGet(SERVER_URL);\n        try {\n            HttpResponse response\
+    \ = client.execute(httpGet);\n            StatusLine statusLine = response.getStatusLine();\n\
+    \            int statusCode = statusLine.getStatusCode();\n            if (statusCode\
+    \ == 200) {\n                HttpEntity entity = response.getEntity();\n     \
+    \           InputStream content = entity.getContent();\n                BufferedReader\
+    \ reader = new BufferedReader(new InputStreamReader(content));\n             \
+    \   String line;\n                while ((line = reader.readLine()) != null) {\n\
+    \                    builder.append(line);\n                }\n            } else\
+    \ {\n                Log.e(TAG, \"Failed to download file\");\n            }\n\
+    \        } catch (ClientProtocolException e) {\n            e.printStackTrace();\n\
+    \        } catch (IOException e) {\n            e.printStackTrace();\n       \
+    \ }\n        return builder.toString();\n    }\n"
+  - "    public void run() {\n        LogPrinter.log(Level.FINEST, \"Started Download\
+    \ at : {0, date, long}\", new Date());\n        if (!PipeConnected) {\n      \
+    \      throw new IllegalStateException(\"You should connect the pipe before with\
+    \ getInputStream()\");\n        }\n        InputStream ins = null;\n        if\
+    \ (IsAlreadyDownloaded) {\n            LogPrinter.log(Level.FINEST, \"The file\
+    \ already Exists open and foward the byte\");\n            try {\n           \
+    \     ContentLength = (int) TheAskedFile.length();\n                ContentType\
+    \ = URLConnection.getFileNameMap().getContentTypeFor(TheAskedFile.getName());\n\
+    \                ins = new FileInputStream(TheAskedFile);\n                byte[]\
+    \ buffer = new byte[BUFFER_SIZE];\n                int read = ins.read(buffer);\n\
+    \                while (read >= 0) {\n                    Pipe.write(buffer, 0,\
+    \ read);\n                    read = ins.read(buffer);\n                }\n  \
+    \          } catch (IOException e) {\n                e.printStackTrace();\n \
+    \           } finally {\n                if (ins != null) {\n                \
+    \    try {\n                        ins.close();\n                    } catch\
+    \ (IOException e) {\n                    }\n                }\n            }\n\
+    \        } else {\n            LogPrinter.log(Level.FINEST, \"the file does not\
+    \ exist locally so we try to download the thing\");\n            File theDir =\
+    \ TheAskedFile.getParentFile();\n            if (!theDir.exists()) {\n       \
+    \         theDir.mkdirs();\n            }\n            for (URL url : ListFastest)\
+    \ {\n                FileOutputStream fout = null;\n                boolean OnError\
+    \ = false;\n                long timestart = System.currentTimeMillis();\n   \
+    \             long bytecount = 0;\n                try {\n                   \
+    \ URL newUrl = new URL(url.toString() + RequestedFile);\n                    LogPrinter.log(Level.FINEST,\
+    \ \"the download URL = {0}\", newUrl);\n                    URLConnection conn\
+    \ = newUrl.openConnection();\n                    ContentType = conn.getContentType();\n\
+    \                    ContentLength = conn.getContentLength();\n              \
+    \      ins = conn.getInputStream();\n                    fout = new FileOutputStream(TheAskedFile);\n\
+    \                    byte[] buffer = new byte[BUFFER_SIZE];\n                \
+    \    int read = ins.read(buffer);\n                    while (read >= 0) {\n \
+    \                       fout.write(buffer, 0, read);\n                       \
+    \ Pipe.write(buffer, 0, read);\n                        read = ins.read(buffer);\n\
+    \                        bytecount += read;\n                    }\n         \
+    \           Pipe.flush();\n                } catch (IOException e) {\n       \
+    \             OnError = true;\n                } finally {\n                 \
+    \   if (ins != null) {\n                        try {\n                      \
+    \      ins.close();\n                        } catch (IOException e) {\n     \
+    \                   }\n                    }\n                    if (fout !=\
+    \ null) {\n                        try {\n                            fout.close();\n\
+    \                        } catch (IOException e) {\n                        }\n\
+    \                    }\n                }\n                long timeend = System.currentTimeMillis();\n\
+    \                if (OnError) {\n                    continue;\n             \
+    \   } else {\n                    long timetook = timeend - timestart;\n     \
+    \               BigDecimal speed = new BigDecimal(bytecount).multiply(new BigDecimal(1000)).divide(new\
+    \ BigDecimal(timetook), MathContext.DECIMAL32);\n                    for (ReportCalculatedStatistique\
+    \ report : Listener) {\n                        report.reportUrlStat(url, speed,\
+    \ timetook);\n                    }\n                    break;\n            \
+    \    }\n            }\n        }\n        LogPrinter.log(Level.FINEST, \"download\
+    \ finished at {0,date,long}\", new Date());\n        if (Pipe != null) {\n   \
+    \         try {\n                Pipe.close();\n            } catch (IOException\
+    \ e) {\n                e.printStackTrace();\n            }\n        }\n    }\n"
+  - "    public void run(String srcf, String dst) {\n        final Path srcPath =\
+    \ new Path(\"./\" + srcf);\n        final Path desPath = new Path(dst);\n    \
+    \    try {\n            Path[] srcs = FileUtil.stat2Paths(hdfs.globStatus(srcPath),\
+    \ srcPath);\n            OutputStream out = FileSystem.getLocal(conf).create(desPath);\n\
+    \            for (int i = 0; i < srcs.length; i++) {\n                System.out.println(srcs[i]);\n\
+    \                InputStream in = hdfs.open(srcs[i]);\n                IOUtils.copyBytes(in,\
+    \ out, conf, false);\n                in.close();\n            }\n           \
+    \ out.close();\n        } catch (IOException ex) {\n            System.err.print(ex.getMessage());\n\
+    \        }\n    }\n"
+- source_sentence: "    private void readHomePage(ITestThread testThread) throws IOException\
+    \ {\n        if (null == testThread) {\n            throw new IllegalArgumentException(\"\
+    Test thread may not be null.\");\n        }\n        final InputStream urlIn =\
+    \ new URL(testUrl).openStream();\n        final int availableBytes = urlIn.available();\n\
+    \        if (0 == availableBytes) {\n            throw new IllegalStateException(\"\
+    Zero bytes on target host.\");\n        }\n        in = new BufferedReader(new\
+    \ InputStreamReader(urlIn));\n        String line;\n        while (null != in\
+    \ && null != (line = in.readLine())) {\n            page.append(line);\n     \
+    \       page.append('\\n');\n            if (0 != lineDelay) {\n             \
+    \   OS.sleep(lineDelay);\n            }\n            if (testThread.isActionStopped())\
+    \ {\n                break;\n            }\n        }\n    }\n"
+  sentences:
+  - "    @Override\n    public ReturnValue do_run() {\n        int bufLen = 500 *\
+    \ 1024;\n        ReturnValue ret = new ReturnValue();\n        ret.setExitStatus(ReturnValue.SUCCESS);\n\
+    \        File output = null;\n        if (((String) options.valueOf(\"input-file\"\
+    )).startsWith(\"s3://\")) {\n            Pattern p = Pattern.compile(\"s3://(\\\
+    \\S+):(\\\\S+)@(\\\\S+)\");\n            Matcher m = p.matcher((String) options.valueOf(\"\
+    input-file\"));\n            boolean result = m.find();\n            String accessKey\
+    \ = null;\n            String secretKey = null;\n            String URL = (String)\
+    \ options.valueOf(\"input-file\");\n            if (result) {\n              \
+    \  accessKey = m.group(1);\n                secretKey = m.group(2);\n        \
+    \        URL = \"s3://\" + m.group(3);\n            } else {\n               \
+    \ try {\n                    HashMap<String, String> settings = (HashMap<String,\
+    \ String>) ConfigTools.getSettings();\n                    accessKey = settings.get(\"\
+    AWS_ACCESS_KEY\");\n                    secretKey = settings.get(\"AWS_SECRET_KEY\"\
+    );\n                } catch (Exception e) {\n                    ret.setExitStatus(ReturnValue.SETTINGSFILENOTFOUND);\n\
+    \                    ret.setProcessExitStatus(ReturnValue.SETTINGSFILENOTFOUND);\n\
+    \                    return (ret);\n                }\n            }\n       \
+    \     if (accessKey == null || secretKey == null) {\n                ret.setExitStatus(ReturnValue.ENVVARNOTFOUND);\n\
+    \                ret.setProcessExitStatus(ReturnValue.ENVVARNOTFOUND);\n     \
+    \           return (ret);\n            }\n            AmazonS3 s3 = new AmazonS3Client(new\
+    \ BasicAWSCredentials(accessKey, secretKey));\n            p = Pattern.compile(\"\
+    s3://([^/]+)/(\\\\S+)\");\n            m = p.matcher(URL);\n            result\
+    \ = m.find();\n            if (result) {\n                String bucket = m.group(1);\n\
+    \                String key = m.group(2);\n                S3Object object = s3.getObject(new\
+    \ GetObjectRequest(bucket, key));\n                System.out.println(\"Content-Type:\
+    \ \" + object.getObjectMetadata().getContentType());\n                output =\
+    \ new File((String) options.valueOf(\"output-dir\") + File.separator + key);\n\
+    \                output.getParentFile().mkdirs();\n                if (!output.exists()\
+    \ || output.length() != object.getObjectMetadata().getContentLength()) {\n   \
+    \                 System.out.println(\"Downloading an S3 object from bucket: \"\
+    \ + bucket + \" with key: \" + key);\n                    BufferedInputStream\
+    \ reader = new BufferedInputStream(object.getObjectContent(), bufLen);\n     \
+    \               try {\n                        BufferedOutputStream writer = new\
+    \ BufferedOutputStream(new FileOutputStream(output), bufLen);\n              \
+    \          while (true) {\n                            int data = reader.read();\n\
+    \                            if (data == -1) {\n                             \
+    \   break;\n                            }\n                            writer.write(data);\n\
+    \                        }\n                        reader.close();\n        \
+    \                writer.close();\n                    } catch (FileNotFoundException\
+    \ e) {\n                        System.err.println(e.getMessage());\n        \
+    \            } catch (IOException e) {\n                        System.err.println(e.getMessage());\n\
+    \                    }\n                } else {\n                    System.out.println(\"\
+    Skipping download of S3 object from bucket: \" + bucket + \" with key: \" + key\
+    \ + \" since local output exists: \" + output.getAbsolutePath());\n          \
+    \      }\n            }\n        } else if (((String) options.valueOf(\"input-file\"\
+    )).startsWith(\"http://\") || ((String) options.valueOf(\"input-file\")).startsWith(\"\
+    https://\")) {\n            Pattern p = Pattern.compile(\"(https*)://(\\\\S+):(\\\
+    \\S+)@(\\\\S+)\");\n            Matcher m = p.matcher((String) options.valueOf(\"\
+    input-file\"));\n            boolean result = m.find();\n            String protocol\
+    \ = null;\n            String user = null;\n            String pass = null;\n\
+    \            String URL = (String) options.valueOf(\"input-file\");\n        \
+    \    if (result) {\n                protocol = m.group(1);\n                user\
+    \ = m.group(2);\n                pass = m.group(3);\n                URL = protocol\
+    \ + \"://\" + m.group(4);\n            }\n            URL urlObj = null;\n   \
+    \         try {\n                urlObj = new URL(URL);\n                if (urlObj\
+    \ != null) {\n                    URLConnection urlConn = urlObj.openConnection();\n\
+    \                    if (user != null && pass != null) {\n                   \
+    \     String userPassword = user + \":\" + pass;\n                        String\
+    \ encoding = new Base64().encodeBase64String(userPassword.getBytes());\n     \
+    \                   urlConn.setRequestProperty(\"Authorization\", \"Basic \" +\
+    \ encoding);\n                    }\n                    p = Pattern.compile(\"\
+    ://([^/]+)/(\\\\S+)\");\n                    m = p.matcher(URL);\n           \
+    \         result = m.find();\n                    if (result) {\n            \
+    \            String host = m.group(1);\n                        String path =\
+    \ m.group(2);\n                        output = new File((String) options.valueOf(\"\
+    output-dir\") + path);\n                        output.getParentFile().mkdirs();\n\
+    \                        if (!output.exists() || output.length() != urlConn.getContentLength())\
+    \ {\n                            System.out.println(\"Downloading an http object\
+    \ from URL: \" + URL);\n                            BufferedInputStream reader\
+    \ = new BufferedInputStream(urlConn.getInputStream(), bufLen);\n             \
+    \               BufferedOutputStream writer = new BufferedOutputStream(new FileOutputStream(output),\
+    \ bufLen);\n                            while (true) {\n                     \
+    \           int data = reader.read();\n                                if (data\
+    \ == -1) {\n                                    break;\n                     \
+    \           }\n                                writer.write(data);\n         \
+    \                   }\n                            reader.close();\n         \
+    \                   writer.close();\n                        } else {\n      \
+    \                      System.out.println(\"Skipping download of http object from\
+    \ URL: \" + URL + \" since local output exists: \" + output.getAbsolutePath());\n\
+    \                        }\n                    }\n                }\n       \
+    \     } catch (MalformedURLException e) {\n                System.err.println(e.getMessage());\n\
+    \            } catch (IOException e) {\n                System.err.println(e.getMessage());\n\
+    \            }\n        } else {\n            output = new File((String) options.valueOf(\"\
+    input-file\"));\n        }\n        boolean result = FileTools.unzipFile(output,\
+    \ new File((String) options.valueOf(\"output-dir\")));\n        if (!result) {\n\
+    \            ret.setStderr(\"Can't unzip software bundle \" + options.valueOf(\"\
+    input-file\") + \" to directory \" + options.valueOf(\"output-dir\"));\n     \
+    \       ret.setExitStatus(ReturnValue.RUNTIMEEXCEPTION);\n        }\n        return\
+    \ (ret);\n    }\n"
+  - "    public void writeConfigurationFile() throws IOException, ComponentException\
+    \ {\n        SystemConfig config = parent.getParentSystem().getConfiguration();\n\
+    \        File original = config.getLocation();\n        File backup = new File(original.getParentFile(),\
+    \ original.getName() + \".\" + System.currentTimeMillis());\n        FileInputStream\
+    \ in = new FileInputStream(original);\n        FileOutputStream out = new FileOutputStream(backup);\n\
+    \        byte[] buffer = new byte[2048];\n        try {\n            int bytesread\
+    \ = 0;\n            while ((bytesread = in.read(buffer)) > 0) {\n            \
+    \    out.write(buffer, 0, bytesread);\n            }\n        } catch (IOException\
+    \ e) {\n            logger.warn(\"Failed to copy backup of configuration file\"\
+    );\n            throw e;\n        } finally {\n            in.close();\n     \
+    \       out.close();\n        }\n        FileWriter replace = new FileWriter(original);\n\
+    \        replace.write(config.toFileFormat());\n        replace.close();\n   \
+    \     logger.info(\"Re-wrote configuration file \" + original.getPath());\n  \
+    \  }\n"
+  - "    @Override\n    protected void doGet(HttpServletRequest req, HttpServletResponse\
+    \ resp) throws ServletException, IOException {\n        resp.addHeader(\"Cache-Control\"\
+    , \"max-age=\" + Constants.HTTP_CACHE_SECONDS);\n        String uuid = req.getRequestURI().substring(req.getRequestURI().indexOf(Constants.SERVLET_FULL_PREFIX)\
+    \ + Constants.SERVLET_FULL_PREFIX.length() + 1);\n        boolean notScale = ClientUtils.toBoolean(req.getParameter(Constants.URL_PARAM_NOT_SCALE));\n\
+    \        ServletOutputStream os = resp.getOutputStream();\n        if (uuid !=\
+    \ null && !\"\".equals(uuid)) {\n            try {\n                String mimetype\
+    \ = fedoraAccess.getMimeTypeForStream(uuid, FedoraUtils.IMG_FULL_STREAM);\n  \
+    \              if (mimetype == null) {\n                    mimetype = \"image/jpeg\"\
+    ;\n                }\n                ImageMimeType loadFromMimeType = ImageMimeType.loadFromMimeType(mimetype);\n\
+    \                if (loadFromMimeType == ImageMimeType.JPEG || loadFromMimeType\
+    \ == ImageMimeType.PNG) {\n                    StringBuffer sb = new StringBuffer();\n\
+    \                    sb.append(config.getFedoraHost()).append(\"/objects/\").append(uuid).append(\"\
+    /datastreams/IMG_FULL/content\");\n                    InputStream is = RESTHelper.get(sb.toString(),\
+    \ config.getFedoraLogin(), config.getFedoraPassword(), false);\n             \
+    \       if (is == null) {\n                        return;\n                 \
+    \   }\n                    try {\n                        IOUtils.copyStreams(is,\
+    \ os);\n                    } catch (IOException e) {\n                      \
+    \  resp.setStatus(HttpURLConnection.HTTP_NOT_FOUND);\n                       \
+    \ LOGGER.error(\"Unable to open full image.\", e);\n                    } finally\
+    \ {\n                        os.flush();\n                        if (is != null)\
+    \ {\n                            try {\n                                is.close();\n\
+    \                            } catch (IOException e) {\n                     \
+    \           resp.setStatus(HttpURLConnection.HTTP_NOT_FOUND);\n              \
+    \                  LOGGER.error(\"Unable to close stream.\", e);\n           \
+    \                 } finally {\n                                is = null;\n  \
+    \                          }\n                        }\n                    }\n\
+    \                } else {\n                    Image rawImg = KrameriusImageSupport.readImage(uuid,\
+    \ FedoraUtils.IMG_FULL_STREAM, this.fedoraAccess, 0, loadFromMimeType);\n    \
+    \                BufferedImage scaled = null;\n                    if (!notScale)\
+    \ {\n                        scaled = KrameriusImageSupport.getSmallerImage(rawImg,\
+    \ 1250, 1000);\n                    } else {\n                        scaled =\
+    \ KrameriusImageSupport.getSmallerImage(rawImg, 2500, 2000);\n               \
+    \     }\n                    KrameriusImageSupport.writeImageToStream(scaled,\
+    \ \"JPG\", os);\n                    resp.setContentType(ImageMimeType.JPEG.getValue());\n\
+    \                    resp.setStatus(HttpURLConnection.HTTP_OK);\n            \
+    \    }\n            } catch (IOException e) {\n                resp.setStatus(HttpURLConnection.HTTP_NOT_FOUND);\n\
+    \                LOGGER.error(\"Unable to open full image.\", e);\n          \
+    \  } catch (XPathExpressionException e) {\n                resp.setStatus(HttpURLConnection.HTTP_NOT_FOUND);\n\
+    \                LOGGER.error(\"Unable to create XPath expression.\", e);\n  \
+    \          } finally {\n                os.flush();\n            }\n        }\n\
+    \    }\n"
+- source_sentence: "    public static boolean insert(final Cargo cargo) {\n      \
+    \  int result = 0;\n        final Connection c = DBConnection.getConnection();\n\
+    \        PreparedStatement pst = null;\n        if (c == null) {\n           \
+    \ return false;\n        }\n        try {\n            c.setAutoCommit(false);\n\
+    \            final String sql = \"insert into cargo (nome) values (?)\";\n   \
+    \         pst = c.prepareStatement(sql);\n            pst.setString(1, cargo.getNome());\n\
+    \            result = pst.executeUpdate();\n            c.commit();\n        }\
+    \ catch (final SQLException e) {\n            try {\n                c.rollback();\n\
+    \            } catch (final SQLException e1) {\n                e1.printStackTrace();\n\
+    \            }\n            System.out.println(\"[CargoDAO.insert] Erro ao inserir\
+    \ -> \" + e.getMessage());\n        } finally {\n            DBConnection.closePreparedStatement(pst);\n\
+    \            DBConnection.closeConnection(c);\n        }\n        if (result >\
+    \ 0) {\n            return true;\n        } else {\n            return false;\n\
+    \        }\n    }\n"
+  sentences:
+  - "    public String md5sum(String toCompute) throws Exception {\n        MessageDigest\
+    \ md = MessageDigest.getInstance(\"MD5\");\n        md.update(toCompute.getBytes());\n\
+    \        java.math.BigInteger hash = new java.math.BigInteger(1, md.digest());\n\
+    \        return hash.toString(16);\n    }\n"
+  - "    protected void runTest(URL pBaseURL, String pName, String pHref) throws Exception\
+    \ {\n        URL url = new URL(pBaseURL, pHref);\n        XSParser parser = new\
+    \ XSParser();\n        parser.setValidating(false);\n        InputSource isource\
+    \ = new InputSource(url.openStream());\n        isource.setSystemId(url.toString());\n\
+    \        String result;\n        try {\n            parser.parse(isource);\n \
+    \           ++numOk;\n            result = \"Ok\";\n        } catch (Exception\
+    \ e) {\n            ++numFailed;\n            result = e.getMessage();\n     \
+    \   }\n        log(\"Running test \" + pName + \" with URL \" + url + \": \" +\
+    \ result);\n    }\n"
+  - "    public String generateMappackMD5(File mapPackFile) throws IOException, NoSuchAlgorithmException\
+    \ {\n        ZipFile zip = new ZipFile(mapPackFile);\n        try {\n        \
+    \    Enumeration<? extends ZipEntry> entries = zip.entries();\n            MessageDigest\
+    \ md5Total = MessageDigest.getInstance(\"MD5\");\n            MessageDigest md5\
+    \ = MessageDigest.getInstance(\"MD5\");\n            while (entries.hasMoreElements())\
+    \ {\n                ZipEntry entry = entries.nextElement();\n               \
+    \ if (entry.isDirectory()) continue;\n                String name = entry.getName();\n\
+    \                if (name.toUpperCase().startsWith(\"META-INF\")) continue;\n\
+    \                md5.reset();\n                InputStream in = zip.getInputStream(entry);\n\
+    \                byte[] data = Utilities.getInputBytes(in);\n                in.close();\n\
+    \                byte[] digest = md5.digest(data);\n                log.trace(\"\
+    Hashsum \" + Hex.encodeHexString(digest) + \" includes \\\"\" + name + \"\\\"\"\
+    );\n                md5Total.update(digest);\n                md5Total.update(name.getBytes());\n\
+    \            }\n            String md5sum = Hex.encodeHexString(md5Total.digest());\n\
+    \            log.trace(\"md5sum of \" + mapPackFile.getName() + \": \" + md5sum);\n\
+    \            return md5sum;\n        } finally {\n            zip.close();\n \
+    \       }\n    }\n"
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on Shuu12121/CodeModernBERT-Owl
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: val
+      type: val
+    metrics:
+    - type: pearson_cosine
+      value: 0.9481467499740959
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.5635084463158045
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on Shuu12121/CodeModernBERT-Owl
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Shuu12121/CodeModernBERT-Owl](https://huggingface.co/Shuu12121/CodeModernBERT-Owl). 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.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [Shuu12121/CodeModernBERT-Owl](https://huggingface.co/Shuu12121/CodeModernBERT-Owl) <!-- at revision c6b9f919885bc8b27718df3af11dc0fbed7e2b63 -->
+- **Maximum Sequence Length:** 2048 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 2048, 'do_lower_case': False}) with Transformer model: ModernBertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    '    public static boolean insert(final Cargo cargo) {\n        int result = 0;\n        final Connection c = DBConnection.getConnection();\n        PreparedStatement pst = null;\n        if (c == null) {\n            return false;\n        }\n        try {\n            c.setAutoCommit(false);\n            final String sql = "insert into cargo (nome) values (?)";\n            pst = c.prepareStatement(sql);\n            pst.setString(1, cargo.getNome());\n            result = pst.executeUpdate();\n            c.commit();\n        } catch (final SQLException e) {\n            try {\n                c.rollback();\n            } catch (final SQLException e1) {\n                e1.printStackTrace();\n            }\n            System.out.println("[CargoDAO.insert] Erro ao inserir -> " + e.getMessage());\n        } finally {\n            DBConnection.closePreparedStatement(pst);\n            DBConnection.closeConnection(c);\n        }\n        if (result > 0) {\n            return true;\n        } else {\n            return false;\n        }\n    }\n',
+    '    protected void runTest(URL pBaseURL, String pName, String pHref) throws Exception {\n        URL url = new URL(pBaseURL, pHref);\n        XSParser parser = new XSParser();\n        parser.setValidating(false);\n        InputSource isource = new InputSource(url.openStream());\n        isource.setSystemId(url.toString());\n        String result;\n        try {\n            parser.parse(isource);\n            ++numOk;\n            result = "Ok";\n        } catch (Exception e) {\n            ++numFailed;\n            result = e.getMessage();\n        }\n        log("Running test " + pName + " with URL " + url + ": " + result);\n    }\n',
+    '    public String generateMappackMD5(File mapPackFile) throws IOException, NoSuchAlgorithmException {\n        ZipFile zip = new ZipFile(mapPackFile);\n        try {\n            Enumeration<? extends ZipEntry> entries = zip.entries();\n            MessageDigest md5Total = MessageDigest.getInstance("MD5");\n            MessageDigest md5 = MessageDigest.getInstance("MD5");\n            while (entries.hasMoreElements()) {\n                ZipEntry entry = entries.nextElement();\n                if (entry.isDirectory()) continue;\n                String name = entry.getName();\n                if (name.toUpperCase().startsWith("META-INF")) continue;\n                md5.reset();\n                InputStream in = zip.getInputStream(entry);\n                byte[] data = Utilities.getInputBytes(in);\n                in.close();\n                byte[] digest = md5.digest(data);\n                log.trace("Hashsum " + Hex.encodeHexString(digest) + " includes \\"" + name + "\\"");\n                md5Total.update(digest);\n                md5Total.update(name.getBytes());\n            }\n            String md5sum = Hex.encodeHexString(md5Total.digest());\n            log.trace("md5sum of " + mapPackFile.getName() + ": " + md5sum);\n            return md5sum;\n        } finally {\n            zip.close();\n        }\n    }\n',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Dataset: `val`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.9481     |
+| **spearman_cosine** | **0.5635** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 901,028 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                            | sentence_1                                                                            | label                                                          |
+  |:--------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                                | string                                                                                | float                                                          |
+  | details | <ul><li>min: 52 tokens</li><li>mean: 332.69 tokens</li><li>max: 2048 tokens</li></ul> | <ul><li>min: 54 tokens</li><li>mean: 353.29 tokens</li><li>max: 2048 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.49</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           | label            |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>    public static Image load(final InputStream input, String format, Point dimension) throws CoreException {<br>        MultiStatus status = new MultiStatus(GraphVizActivator.ID, 0, "Errors occurred while running Graphviz", null);<br>        File dotInput = null, dotOutput = null;<br>        ByteArrayOutputStream dotContents = new ByteArrayOutputStream();<br>        try {<br>            dotInput = File.createTempFile(TMP_FILE_PREFIX, DOT_EXTENSION);<br>            dotOutput = File.createTempFile(TMP_FILE_PREFIX, "." + format);<br>            dotOutput.delete();<br>            FileOutputStream tmpDotOutputStream = null;<br>            try {<br>                IOUtils.copy(input, dotContents);<br>                tmpDotOutputStream = new FileOutputStream(dotInput);<br>                IOUtils.copy(new ByteArrayInputStream(dotContents.toByteArray()), tmpDotOutputStream);<br>            } finally {<br>                IOUtils.closeQuietly(tmpDotOutputStream);<br>            }<br>            IStatus result = runDot(format, dimension, dotInp...</code> | <code>    public final Matrix3D<E> read(final URL url) throws IOException {<br>        if (url == null) {<br>            throw new IllegalArgumentException("url must not be null");<br>        }<br>        InputStream inputStream = null;<br>        try {<br>            inputStream = url.openStream();<br>            return read(inputStream);<br>        } catch (IOException e) {<br>            throw e;<br>        } finally {<br>            MatrixIOUtils.closeQuietly(inputStream);<br>        }<br>    }<br></code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | <code>0.0</code> |
+  | <code>    public List<PathObject> fetchPath(BoardObject board) throws NetworkException {<br>        if (boardPathMap.containsKey(board.getId())) {<br>            return boardPathMap.get(board.getId()).getChildren();<br>        }<br>        HttpClient client = HttpConfig.newInstance();<br>        HttpGet get = new HttpGet(HttpConfig.bbsURL() + HttpConfig.BBS_0AN_BOARD + board.getId());<br>        try {<br>            HttpResponse response = client.execute(get);<br>            HttpEntity entity = response.getEntity();<br>            Document doc = XmlOperator.readDocument(entity.getContent());<br>            PathObject parent = new PathObject();<br>            BBSBodyParseHelper.parsePathList(doc, parent);<br>            parent = searchAndCreatePathFromRoot(parent);<br>            boardPathMap.put(board.getId(), parent);<br>            return parent.getChildren();<br>        } catch (Exception e) {<br>            e.printStackTrace();<br>            throw new NetworkException(e);<br>        }<br>    }<br></code>                                         | <code>    public static void readDefault() {<br>        ClassLoader l = Skeleton.class.getClassLoader();<br>        URL url;<br>        if (l != null) {<br>            url = l.getResource(DEFAULT_LOC);<br>        } else {<br>            url = ClassLoader.getSystemResource(DEFAULT_LOC);<br>        }<br>        if (url == null) {<br>            Out.error(ErrorMessages.SKEL_IO_ERROR_DEFAULT);<br>            throw new GeneratorException();<br>        }<br>        try {<br>            InputStreamReader reader = new InputStreamReader(url.openStream());<br>            readSkel(new BufferedReader(reader));<br>        } catch (IOException e) {<br>            Out.error(ErrorMessages.SKEL_IO_ERROR_DEFAULT);<br>            throw new GeneratorException();<br>        }<br>    }<br></code>                                                                                                                                                                                                                                                                                    | <code>0.0</code> |
+  | <code>    public boolean copyFile(File source, File dest) {<br>        try {<br>            FileReader in = new FileReader(source);<br>            FileWriter out = new FileWriter(dest);<br>            int c;<br>            while ((c = in.read()) != -1) out.write(c);<br>            in.close();<br>            out.close();<br>            return true;<br>        } catch (Exception e) {<br>            return false;<br>        }<br>    }<br></code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           | <code>    public static boolean encodeFileToFile(String infile, String outfile) {<br>        boolean success = false;<br>        java.io.InputStream in = null;<br>        java.io.OutputStream out = null;<br>        try {<br>            in = new Base64.InputStream(new java.io.BufferedInputStream(new java.io.FileInputStream(infile)), Base64.ENCODE);<br>            out = new java.io.BufferedOutputStream(new java.io.FileOutputStream(outfile));<br>            byte[] buffer = new byte[65536];<br>            int read = -1;<br>            while ((read = in.read(buffer)) >= 0) {<br>                out.write(buffer, 0, read);<br>            }<br>            success = true;<br>        } catch (java.io.IOException exc) {<br>            exc.printStackTrace();<br>        } finally {<br>            try {<br>                in.close();<br>            } catch (Exception exc) {<br>            }<br>            try {<br>                out.close();<br>            } catch (Exception exc) {<br>            }<br>        }<br>        return success;<br>    }<br></code> | <code>1.0</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `num_train_epochs`: 1
+- `fp16`: True
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `tp_size`: 0
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step  | Training Loss | val_spearman_cosine |
+|:------:|:-----:|:-------------:|:-------------------:|
+| 0.0178 | 500   | 0.1622        | -                   |
+| 0.0355 | 1000  | 0.0124        | 0.5702              |
+| 0.0533 | 1500  | 0.0087        | -                   |
+| 0.0710 | 2000  | 0.0064        | 0.5686              |
+| 0.0888 | 2500  | 0.0048        | -                   |
+| 0.1065 | 3000  | 0.0046        | 0.5753              |
+| 0.1243 | 3500  | 0.0036        | -                   |
+| 0.1421 | 4000  | 0.0039        | 0.5745              |
+| 0.1598 | 4500  | 0.0036        | -                   |
+| 0.1776 | 5000  | 0.0035        | 0.5637              |
+| 0.1953 | 5500  | 0.0036        | -                   |
+| 0.2131 | 6000  | 0.0027        | 0.5615              |
+| 0.2308 | 6500  | 0.002         | -                   |
+| 0.2486 | 7000  | 0.0019        | 0.5660              |
+| 0.2664 | 7500  | 0.0017        | -                   |
+| 0.2841 | 8000  | 0.0017        | 0.5622              |
+| 0.3019 | 8500  | 0.0019        | -                   |
+| 0.3196 | 9000  | 0.0017        | 0.5583              |
+| 0.3374 | 9500  | 0.0012        | -                   |
+| 0.3551 | 10000 | 0.0013        | 0.5547              |
+| 0.3729 | 10500 | 0.0015        | -                   |
+| 0.3907 | 11000 | 0.0011        | 0.5631              |
+| 0.4084 | 11500 | 0.0012        | -                   |
+| 0.4262 | 12000 | 0.0013        | 0.5630              |
+| 0.4439 | 12500 | 0.001         | -                   |
+| 0.4617 | 13000 | 0.0009        | 0.5607              |
+| 0.4794 | 13500 | 0.0007        | -                   |
+| 0.4972 | 14000 | 0.001         | 0.5590              |
+| 0.5150 | 14500 | 0.001         | -                   |
+| 0.5327 | 15000 | 0.0009        | 0.5572              |
+| 0.5505 | 15500 | 0.0007        | -                   |
+| 0.5682 | 16000 | 0.0006        | 0.5607              |
+| 0.5860 | 16500 | 0.0007        | -                   |
+| 0.6037 | 17000 | 0.0006        | 0.5675              |
+| 0.6215 | 17500 | 0.0007        | -                   |
+| 0.6392 | 18000 | 0.0009        | 0.5610              |
+| 0.6570 | 18500 | 0.0008        | -                   |
+| 0.6748 | 19000 | 0.0007        | 0.5583              |
+| 0.6925 | 19500 | 0.0006        | -                   |
+| 0.7103 | 20000 | 0.0006        | 0.5662              |
+| 0.7280 | 20500 | 0.0007        | -                   |
+| 0.7458 | 21000 | 0.0005        | 0.5659              |
+| 0.7635 | 21500 | 0.0004        | -                   |
+| 0.7813 | 22000 | 0.0006        | 0.5667              |
+| 0.7991 | 22500 | 0.0006        | -                   |
+| 0.8168 | 23000 | 0.0006        | 0.5644              |
+| 0.8346 | 23500 | 0.0005        | -                   |
+| 0.8523 | 24000 | 0.0003        | 0.5629              |
+| 0.8701 | 24500 | 0.0005        | -                   |
+| 0.8878 | 25000 | 0.0005        | 0.5642              |
+| 0.9056 | 25500 | 0.0006        | -                   |
+| 0.9234 | 26000 | 0.0006        | 0.5640              |
+| 0.9411 | 26500 | 0.0004        | -                   |
+| 0.9589 | 27000 | 0.0007        | 0.5634              |
+| 0.9766 | 27500 | 0.0004        | -                   |
+| 0.9944 | 28000 | 0.0005        | 0.5635              |
+| 1.0    | 28158 | -             | 0.5635              |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 4.0.1
+- Transformers: 4.50.3
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.5.2
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 50001,
+  "<mask>": 50003,
+  "<s>": 50000,
+  "<unk>": 50002
+}

config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 50000,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50001,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "hidden_activation": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "local_attention": 128,
+  "local_attention_rope_theta": 10000,
+  "local_attention_window": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "reference_compile": true,
+  "repad_logits_with_grad": false,
+  "rope_theta": 160000,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "vocab_size": 50004
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.0.1",
+    "transformers": "4.50.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1f72bbfe8d3f5de1ac4763808bb610c40aaddcc39905532d47928deb1aecfc
+size 606681112

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 2048,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,97 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50000": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50001": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50002": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50003": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}