Instructions to use buelfhood/SOCO-Java-CodeBERTa-MNRL-Triplets with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use buelfhood/SOCO-Java-CodeBERTa-MNRL-Triplets with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("buelfhood/SOCO-Java-CodeBERTa-MNRL-Triplets")

sentences = [
    "\n\nimport java.net.*;\nimport java.io.*;\n\npublic class sendMail {\n\npublic void sendMail(String mailServer, String recipient, String result) {\n   try {\n      Socket s = new Socket(mailServer, 25);\n      BufferedReader in = new BufferedReader\n          (new InputStreamReader(s.getInputStream(), \"8859_1\"));\n      BufferedWriter out = new BufferedWriter\n          (new OutputStreamWriter(s.getOutputStream(), \"8859_1\"));\n\n      send(in, out, \"HELO client\");\n\n      send(in, out, \"MAIL FROM: <WatchDog@SecureECommerce.>\");\n      send(in, out, \"RCPT : \" + recipient);\n      send(in, out, \"DATA\");\n      send(out, \"Subject: \");\n      send(out, \"From: Admin <WatchDog@SecureECommerce.>\");\n      send (out, \"\\n\");\n      \n      send(out, result);\n      send(out, \"\\n.\\n\");\n      send(in, out, \"QUIT\");\n\n      }\n   catch (Exception e) {\n      e.printStackTrace();\n      }\n   }\n\n public void send(BufferedReader in, BufferedWriter out, String s) {\n   try {\n      out.write(s + \"\\n\");\n      out.flush();\n      System.out.println(s);\n      s = in.readLine();\n      System.out.println(s);\n      }\n   catch (Exception e) {\n      e.printStackTrace();\n      }\n   }\n\n public void send(BufferedWriter out, String s) {\n   try {\n      out.write(s + \"\\n\");\n      out.flush();\n      System.out.println(s);\n      }\n   catch (Exception e) {\n      e.printStackTrace();\n      }\n   }\n}",
    "import java.net.*;\nimport java.io.*;\nimport java.*;\n\n public class BruteForce {\n\n   URLConnection conn = null;\n   private static boolean status = false;\n\n   public static void main (String args[]){\n     BruteForce a = new BruteForce();\n     String[] inp = {\"http://sec-crack.cs.rmit.edu./SEC/2/index.php\",\n     \t\t\t\t \"\",\n     \t\t\t\t \"\"};\n     int attempts = 0;\n     exit:\n     for (int i=0;i<pwdArray.length;i++) {\n\t\t for (int j=0;j<pwdArray.length;j++) {\n\t\t\t for (int k=0;k<pwdArray.length;k++) {\n\t\t\t\t if (pwdArray[i] == ' ' && pwdArray[j] != ' ') continue;\n\t\t\t\t if (pwdArray[j] == ' ' && pwdArray[k] != ' ') continue;\n\t\t\t\t inp[2] = inp[2] + pwdArray[i] + pwdArray[j] + pwdArray[k];\n\t\t\t\t attempts++;\n     \t\t\t a.doit(inp);\n  \n  \t\t\t\t if (status) {\n\t\t\t\t\t System.out.println(\"Crrect password is: \" + inp[2]);\n\t\t\t\t\t System.out.println(\"Number of attempts = \" + attempts);\n\t\t\t\t\t break exit;\n\t\t\t \t }\n     \t\t\t inp[2] = \"\";\n\t\t \t }\n\t \t }\n      }\n     }\n\n   public void doit(String args[]) {\n     \n     try {\n       BufferedReader in = new BufferedReader(\n           new InputStreamReader\n              (connectURL(new URL(args[0]), args[1], args[2])));\n       String line;\n       while ((line = in.readLine()) != null) {\n           System.out.println(line);\n           status = true;\n           }\n       }\n     catch (IOException e) {\n   \n       }\n     }\n\n   public InputStream connectURL (URL url, String uname, String pword)\n        throws IOException  {\n     conn = url.openConnection();\n     conn.setRequestProperty (\"Authorization\",\n     userNamePasswordBase64(uname,pword));\n     conn.connect ();\n     return conn.getInputStream();\n     }\n\n   public String userNamePasswordBase64(String username, String password) {\n     return \" \" + base64Encode (username + \":\" + password);\n     }\n\n   private final static char pwdArray [] = {\n\t        'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h',\n\t        'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p',\n\t        'q', 'r', 's', 't', 'u', 'v', 'w', 'x',\n\t        'y', 'z', 'A', 'B', 'C', 'D', 'E', 'F',\n\t        'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N',\n\t        'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V',\n\t        'W', 'X', 'Y', 'Z', ' '\n  };\n\n   private final static char base64Array [] = {\n       'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H',\n       'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P',\n       'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X',\n       'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f',\n       'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n',\n       'o', 'p', 'q', 'r', 's', 't', 'u', 'v',\n       'w', 'x', 'y', 'z', '0', '1', '2', '3',\n       '4', '5', '6', '7', '8', '9', '+', '/'\n  };\n\n   private static String base64Encode (String string)    {\n     String encodedString = \"\";\n     byte bytes [] = string.getBytes ();\n     int i = 0;\n     int pad = 0;\n     while (i < bytes.length) {\n       byte b1 = bytes [i++];\n       byte b2;\n       byte b3;\n       if (i >= bytes.length) {\n          b2 = 0;\n          b3 = 0;\n          pad = 2;\n          }\n       else {\n          b2 = bytes [i++];\n          if (i >= bytes.length) {\n             b3 = 0;\n             pad = 1;\n             }\n          else\n             b3 = bytes [i++];\n          }\n       byte c1 = (byte)(b1 >> 2);\n       byte c2 = (byte)(((b1 & 0x3) << 4) | (b2 >> 4));\n       byte c3 = (byte)(((b2 & 0xf) << 2) | (b3 >> 6));\n       byte c4 = (byte)(b3 & 0x3f);\n       encodedString += base64Array [c1];\n       encodedString += base64Array [c2];\n       switch (pad) {\n        case 0:\n          encodedString += base64Array [c3];\n          encodedString += base64Array [c4];\n          break;\n         case 1:\n          encodedString += base64Array [c3];\n          encodedString += \"=\";\n          break;\n        case 2:\n          encodedString += \"==\";\n          break;\n        }\n       }\n       return encodedString;\n   }\n }\n\n",
    "\nimport java.io.*;\n\npublic class PasswordFile {\n    \n    private String strFilepath;\n    private String strCurrWord;\n    private File fWordFile;\n    private BufferedReader in;\n    \n    \n    public PasswordFile(String filepath) {\n        strFilepath = filepath;\n        try {\n            fWordFile = new File(strFilepath);\n            in = new BufferedReader(new FileReader(fWordFile));\n        }\n        catch(Exception e)\n        {\n            System.out.println(\"Could not open file \" + strFilepath);\n        }\n    }\n    \n    String getPassword() {\n        return strCurrWord;\n    }\n    \n    String getNextPassword() {\n        try {\n            strCurrWord = in.readLine();\n            \n            \n            \n        }\n        catch (Exception e)\n        {\n            \n            return null;\n        }\n                \n        return strCurrWord;\n    }\n    \n}\n",
    "\n\nimport java.net.*;\nimport java.io.*;\n\npublic class SendEMail {\n\n public void SendEMail(){}\n\npublic void sendMail(String recipient,String c, String subject){\n   try {\n\n      Socket s = new Socket(\"yallara.cs.rmit.edu.\", 25);\n      BufferedReader in = new BufferedReader\n          (new InputStreamReader(s.getInputStream(), \"8859_1\"));\n      BufferedWriter out = new BufferedWriter\n          (new OutputStreamWriter(s.getOutputStream(), \"8859_1\"));\n\n      send(in, out, \"HELO theWorld\");\n      \n      \n      send(in, out, \"MAIL FROM: <watch@dog.>\");\n      send(in, out, \"RCPT : \"+recipient);\n      send(in, out, \"DATA\");\n      send(out, \"Subject: \"+ subject);\n      send(out, \"From: WatchDog.java\");\n      send (out, \"\\n\");\n      \n      BufferedReader reader;\n      String line;\n      reader = new BufferedReader(new InputStreamReader(new FileInputStream()));\n      line = reader.readLine();\n      while (line != null){\n          send(out, line);\n         line = reader.readLine();\n      }\n      send(out, \"\\n.\\n\");\n      send(in, out, \"QUIT\");\n      s.print();\n      }\n   catch (Exception e) {\n      e.printStackTrace();\n      }\n   }\n\n public void send(BufferedReader in, BufferedWriter out, String s) {\n   try {\n      out.write(s + \"\\n\");\n      out.flush();\n      System.out.println(s);\n      s = in.readLine();\n      System.out.println(s);\n      }\n   catch (Exception e) {\n      e.printStackTrace();\n      }\n   }\n\n public void send(BufferedWriter out, String s) {\n   try {\n      out.write(s + \"\\n\");\n      out.flush();\n      System.out.println(s);\n      }\n   catch (Exception e) {\n      e.printStackTrace();\n      }\n   }\n}"
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4]

Notebooks
Google Colab
Kaggle

buelfhood commited on Jun 10, 2025

Commit

c817296

verified ·

1 Parent(s): fbd44ef

Add new SentenceTransformer model

Browse files

Files changed (12) hide show

1_Pooling/config.json +10 -0
README.md +0 -0
config.json +26 -0
config_sentence_transformers.json +10 -0
merges.txt +0 -0
model.safetensors +3 -0
modules.json +14 -0
sentence_bert_config.json +4 -0
special_tokens_map.json +51 -0
tokenizer.json +0 -0
tokenizer_config.json +59 -0
vocab.json +0 -0

1_Pooling/config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md ADDED Viewed

The diff for this file is too large to render. See raw diff

config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

config_sentence_transformers.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.4",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:11702a16b0d5e4259ba18f71ddc82212bc5bc27e69d3639e856800420d23f59a
+size 333815048

modules.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,59 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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": 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_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff