| --- |
| tags: |
| - sentence-transformers |
| - sentence-similarity |
| - feature-extraction |
| - dense |
| - generated_from_trainer |
| - dataset_size:54320 |
| - loss:MultipleNegativesRankingLoss |
| base_model: BAAI/bge-base-en-v1.5 |
| widget: |
| - source_sentence: The ransomware injected malicious.dll into svchost.exe to execute |
| its encryption routines under a trusted process. |
| sentences: |
| - A rootkit modified UEFI runtime services to maintain control over the system. |
| - ZxxZ has relied on victims to open a malicious attachment delivered via email. |
| - FIN7 has used random junk code to obfuscate malware code. |
| - source_sentence: OnionDuke has the capability to use a Denial of Service module. |
| sentences: |
| - The attacker exploited a denial-of-service vulnerability in the WordPress plugin. |
| - Before activating, the ransomware used 'net share' to enumerate shared folders |
| across the corporate network. |
| - Akira engages in double-extortion ransomware, exfiltrating files then encrypting |
| them, in order to prompt victims to pay a ransom. |
| - source_sentence: The threat actor increased the storage quota limit to accommodate |
| large-scale data exfiltration operations. |
| sentences: |
| - The payload of CozyCar is encrypted with simple XOR with a rotating key. The CozyCar |
| configuration file has been encrypted with RC4 keys. |
| - An adversary changed the Google Cloud organization policy constraints to allow |
| unrestricted resource deployment across all projects. |
| - The malware queried professional networking sites to collect branch office physical |
| addresses. |
| - source_sentence: The threat actor altered DNS SRV records to redirect service authentication |
| requests to compromised servers. |
| sentences: |
| - The malware altered local DNS settings to redirect traffic from banking websites |
| to phishing servers. |
| - The compromised system ran 'c2_client.exe' to reconnect to the command and control |
| infrastructure. |
| - The malware leveraged MailSniper to find emails with employee personal identifiable |
| information. |
| - source_sentence: APT28 has exploited open Wi-Fi access points for initial access |
| to target devices using the network. |
| sentences: |
| - The spyware stored collected data in hidden disk areas reserved for firmware updates |
| and system recovery. |
| - DarkComet gathers the username from the victim’s machine. |
| - A script was deployed to search for and connect to unsecured guest Wi-Fi networks |
| in the area. |
| pipeline_tag: sentence-similarity |
| library_name: sentence-transformers |
| --- |
| |
| # SentenceTransformer based on BAAI/bge-base-en-v1.5 |
|
|
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). 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:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a --> |
| - **Maximum Sequence Length:** 512 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/huggingface/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': 512, 'do_lower_case': True, 'architecture': 'BertModel'}) |
| (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}) |
| (2): Normalize() |
| ) |
| ``` |
|
|
| ## 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 = [ |
| 'APT28 has exploited open Wi-Fi access points for initial access to target devices using the network.', |
| 'A script was deployed to search for and connect to unsecured guest Wi-Fi networks in the area.', |
| 'The spyware stored collected data in hidden disk areas reserved for firmware updates and system recovery.', |
| ] |
| 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, 0.9010, -0.0563], |
| # [ 0.9010, 1.0000, 0.0412], |
| # [-0.0563, 0.0412, 1.0000]]) |
| ``` |
|
|
| <!-- |
| ### 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.* |
| --> |
|
|
| <!-- |
| ## 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: 54,320 training samples |
| * Columns: <code>sentence_0</code> and <code>sentence_1</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | sentence_0 | sentence_1 | |
| |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
| | type | string | string | |
| | details | <ul><li>min: 8 tokens</li><li>mean: 23.66 tokens</li><li>max: 95 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 23.49 tokens</li><li>max: 95 tokens</li></ul> | |
| * Samples: |
| | sentence_0 | sentence_1 | |
| |:---------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------| |
| | <code>ICMP timestamp requests were sent to gather information about network device availability.</code> | <code>The malware executed ping commands to map the victim's internal network structure.</code> | |
| | <code>Using Azure Resource Manager API calls, the threat actor listed all virtual machines across multiple subscriptions.</code> | <code>The adversary used a service principal to query the Microsoft Graph API and enumerate all service principals.</code> | |
| | <code>A malicious DLL was written to the Office application's startup folder for persistence.</code> | <code>The persistence mechanism modified Office registry settings to execute malicious code.</code> | |
| * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: |
| ```json |
| { |
| "scale": 20.0, |
| "similarity_fct": "cos_sim", |
| "gather_across_devices": false |
| } |
| ``` |
|
|
| ### Training Hyperparameters |
| #### Non-Default Hyperparameters |
|
|
| - `per_device_train_batch_size`: 16 |
| - `per_device_eval_batch_size`: 16 |
| - `num_train_epochs`: 4 |
| - `multi_dataset_batch_sampler`: round_robin |
| |
| #### All Hyperparameters |
| <details><summary>Click to expand</summary> |
| |
| - `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`: 4 |
| - `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 |
| - `bf16`: False |
| - `fp16`: False |
| - `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} |
| - `parallelism_config`: None |
| - `deepspeed`: None |
| - `label_smoothing_factor`: 0.0 |
| - `optim`: adamw_torch_fused |
| - `optim_args`: None |
| - `adafactor`: False |
| - `group_by_length`: False |
| - `length_column_name`: length |
| - `project`: huggingface |
| - `trackio_space_id`: trackio |
| - `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 |
| - `hub_revision`: None |
| - `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`: no |
| - `neftune_noise_alpha`: None |
| - `optim_target_modules`: None |
| - `batch_eval_metrics`: False |
| - `eval_on_start`: False |
| - `use_liger_kernel`: False |
| - `liger_kernel_config`: None |
| - `eval_use_gather_object`: False |
| - `average_tokens_across_devices`: True |
| - `prompts`: None |
| - `batch_sampler`: batch_sampler |
| - `multi_dataset_batch_sampler`: round_robin |
| - `router_mapping`: {} |
| - `learning_rate_mapping`: {} |
|
|
| </details> |
|
|
| ### Training Logs |
| | Epoch | Step | Training Loss | |
| |:------:|:-----:|:-------------:| |
| | 0.1473 | 500 | 0.7961 | |
| | 0.2946 | 1000 | 0.4543 | |
| | 0.4418 | 1500 | 0.3414 | |
| | 0.5891 | 2000 | 0.2844 | |
| | 0.7364 | 2500 | 0.2156 | |
| | 0.8837 | 3000 | 0.1984 | |
| | 1.0309 | 3500 | 0.1555 | |
| | 1.1782 | 4000 | 0.1195 | |
| | 1.3255 | 4500 | 0.1039 | |
| | 1.4728 | 5000 | 0.1007 | |
| | 1.6200 | 5500 | 0.1023 | |
| | 1.7673 | 6000 | 0.0975 | |
| | 1.9146 | 6500 | 0.0855 | |
| | 2.0619 | 7000 | 0.0889 | |
| | 2.2091 | 7500 | 0.069 | |
| | 2.3564 | 8000 | 0.07 | |
| | 2.5037 | 8500 | 0.0633 | |
| | 2.6510 | 9000 | 0.0593 | |
| | 2.7982 | 9500 | 0.0624 | |
| | 2.9455 | 10000 | 0.0574 | |
| | 3.0928 | 10500 | 0.0599 | |
| | 3.2401 | 11000 | 0.0484 | |
| | 3.3873 | 11500 | 0.0544 | |
| | 3.5346 | 12000 | 0.0596 | |
| | 3.6819 | 12500 | 0.0536 | |
| | 3.8292 | 13000 | 0.0517 | |
| | 3.9764 | 13500 | 0.0464 | |
|
|
|
|
| ### Framework Versions |
| - Python: 3.10.19 |
| - Sentence Transformers: 5.2.0 |
| - Transformers: 4.57.3 |
| - PyTorch: 2.9.1 |
| - Accelerate: 1.12.0 |
| - Datasets: 4.4.2 |
| - Tokenizers: 0.22.1 |
|
|
| ## 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", |
| } |
| ``` |
|
|
| #### MultipleNegativesRankingLoss |
| ```bibtex |
| @misc{henderson2017efficient, |
| title={Efficient Natural Language Response Suggestion for Smart Reply}, |
| author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, |
| year={2017}, |
| eprint={1705.00652}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CL} |
| } |
| ``` |
|
|
| <!-- |
| ## 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.* |
| --> |
