--- tags: - sentence-transformers - sentence-similarity - feature-extraction - dense - generated_from_trainer - dataset_size:359 - loss:CosineSimilarityLoss base_model: thenlper/gte-small widget: - source_sentence: Using this advanced technology, we will be able to gain transparency in our elections, without compromising the privacy of voters, and we have a way to accurately demonstrate the mathematical results of elections. Also, at the request of the voter, there will be a way to allow the voter to vote online in the election and follow his vote in the ballot box to ensure that his vote is stored safely and safely without changing or changing it in any way. sentences: - Using this advanced technology, we will be able to gain transparency in our elections, without compromising the privacy of voters, and we have a way to accurately demonstrate the mathematical results of elections. Also, at the request of the voter, there will be a way to allow the voter to vote online in the election and follow his vote in the ballot box to ensure that his vote is stored safely and safely without changing or changing it in any way. - we decided to make a platform, Pharmacies can be far away from your place. After noticing all these problems we made a survey to found a solution for this problem, Health is considering as the important thing in our lives, we find the solution must be the processions of the technology era, like some is not always available, can solve these problems in the side of, we found most of people suffer from a large number of problem include problems that presented previously, we have noticed that there are many problems in medicine field, the prices change from place to another - determine the type of project as it was a construction project or an architectural project or sewage project After specifying the name, Enter the name of the project, The platform helps the user to find the appropriate map that he is looking for, type of project He will show him the map of the building as he wants to see it. - source_sentence: 'Stroke (Brain Attack): is one of the biggest dangers, occurs when something blocks blood supply to part of the brain or when a blood vessel in the brain bursts. There are 2 types from stroke Ischemic stroke: occurs when blood clots or other particles block the blood vessels to the brain. Hemorrhagic stroke: happens when an artery in the brain leaks blood or ruptures (breaks open). The leaked blood puts too much pressure on brain cells, which damages them. Stroke is the second leading causes of death, responsible for approximately 11% of the world wide death, Annually 15 million people worldwide suffer a stroke, Of these, 5 million die and another 10 million are left permanently disabled .We can avoid this danger if we know the factors that affect stroke. Our application is trained with machine learning model that can predict if you have a probability to have a stroke or not by entering data like age, gender, hypertension, heart diseases, and average glucose level, Based on the data you entered the application will predict if you have a probability of stroke or not. If you have a probability of stroke the application will also display the main reason of this danger(like hypertension or glucose) and recommend diet plan for your lifestyle to have a control in this danger.' sentences: - 'Of these, another 10 million are left permanently disabled .We can avoid this danger if we know the factors that affect stroke. Our, responsible for approximately 11% of the world wide death, damages them. Stroke is the second leading causes of death, Stroke (Brain Attack): is one of the biggest dangers, Annually 15 million people worldwide suffer a stroke, 5 million die, occurs when something blocks blood supply to part of the brain or when a blood vessel in the brain bursts. There are 2 types from stroke Ischemic stroke: occurs when blood clots or other particles block the blood vessels to the brain. Hemorrhagic stroke: happens when an artery in the brain leaks blood or ruptures (breaks open). The leaked blood puts too much pressure on brain cells' - Automation is one of our life requirements which simplifies our daily routines and ensures safety and accuracy. One of these routine processes that people need to automate is the distribution of catering subsidized products in Egypt. This problem has caught the attention of all people from different living standards because of what they face when they need subsidized products. Our problem spotlights cheat catering products and hide products from the customers and forcing them to buy specific products or make customers waste their time waiting for their products. Finally, they don't have their products except with higher prices not specified by the ministry to solve the aforementioned problems, we suggest making the product distribution done by the customer themselves like vending machine that makes the customer decide what he wants with the specific price that the ministry of Supply decided and announced to their customers through a mobile application give them full details of available products, prices, and receipts. - disability, can cause damage to the surrounding tissue, breast cancer. The accuracy of diagnosis, benign tumor lesions, control the harmful effects of skin cancer. Due to the similar shape of the lesion between skin cancer, benign tumor lesions automatically with the Convolutional Neural Network, Skin cancer is a type of cancer that grows in the skin tissue, the early proper treatment can minimize, even death. skin cancer is the third leading for most cancer cases after cervical, physicians consuming much more time in diagnosing these lesions. The platform was developed in this study could identify skin cancer - source_sentence: Today, Mobile technology is a field of rapid development. Especially over the past few years, the improvements in mobile technology has been tremendous. The increase in performance of these devices, as well as the additional hardware in form of GPS, sensors, etc., make them powerful devices which can develop comprehensive services sentences: - uploaded to the site from here, selling their food, neighborhoods. Food is prepared at home, the client requests ready-made food. Then the food is sent with the delivery agent This will help create job opportunities for housewives, after people who have a hobby of cooking in spreading, Baladi Food Project(Sofra) the main idea Given that the project is being applied to popular areas such as villages - Therefore, in addition to these medical tests it is good to aid computer technology like Artificial Intelligence, as it can play a vital role. Artificial Intelligence (AI) is used in cameras to track infected patients with travel history using facial recognition so that we can easily identify other people who are in physical contact with corona-effected - children will believe that they deserve the insult, Parenting is not an easy task. Good parenting requires the parent to quickly respond to the needs of their child. Constant monitoring of the child also becomes a necessity, Children not only imitate their parents or repeat the words, expect it, behavior of their teachers, but also believe what they say about them. When parents insult or treat them poorly - source_sentence: This project proposes a system that is based on a QR code, which is being displayed for students during or at the beginning of each lecture. The students will need to scan the code in order to confirm their attendance. The project explains analysis and implementation details of the proposed system. It also discusses how the system verifies student identity to eliminate false registrations. sentences: - is being displayed for students during or at the beginning of each lecture. The students will need to scan the code in order to confirm, This project proposes a platform that is using a QR code - 'Stroke (Brain Attack): is one of the biggest dangers, occurs when something blocks blood supply to part of the brain or when a blood vessel in the brain bursts. There are 2 types from stroke Ischemic stroke: occurs when blood clots or other particles block the blood vessels to the brain. Hemorrhagic stroke: happens when an artery in the brain leaks blood or ruptures (breaks open). The leaked blood puts too much pressure on brain cells, which damages them. Stroke is the second leading causes of death, responsible for approximately 11% of the world wide death, Annually 15 million people worldwide suffer a stroke, Of these, 5 million die and another 10 million are left permanently disabled .We can avoid this danger if we know the factors that affect stroke. Our application is trained with machine learning model that can predict if you have a probability to have a stroke or not by entering data like age, gender, hypertension, heart diseases, and average glucose level, Based on the data you entered the application will predict if you have a probability of stroke or not. If you have a probability of stroke the application will also display the main reason of this danger(like hypertension or glucose) and recommend diet plan for your lifestyle to have a control in this danger.' - doctors There, pharmacists to know the interactions happens learn between drugs, also allows patients to know the nearest yours pharmacy to him to meets his needs, It's an application that offers to patients - source_sentence: Medical Plus application is an web based application that provides the patients with speed time to find the best clinics and doctors, such as find the nearest clinic, search for best doctors, find all specialists, get latest news about new doctors and illness, ticket prices, ask for something you want to know about your illness and find new information from specific doctor. sentences: - he system provides online information of blood bank and administrators can also all information about Blood bank, donor, patient request and blood requirements.The Target of the application is to make the donation process more easily, spread awareness about this process, the way to deal with it. - get latest news about new doctors, such as find the nearest clinic, search for best doctors, ask for something you want to know about your illness, doctors, illness, find new information from specific doctor., ticket prices, find all specialists, Medical Plus application is an web based application that provides the patients with speed time to find the best clinics - database. This project is web site for booking hotels. We will use in this site many programs such as some We will identify the tasks that consist of the project, languages of web create, do it with the language or the pipeline_tag: sentence-similarity library_name: sentence-transformers --- # SentenceTransformer based on thenlper/gte-small This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [thenlper/gte-small](https://huggingface.co/thenlper/gte-small). It maps sentences & paragraphs to a 384-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:** [thenlper/gte-small](https://huggingface.co/thenlper/gte-small) - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 384 dimensions - **Similarity Function:** Cosine Similarity ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/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': 128, 'do_lower_case': False, 'architecture': 'BertModel'}) (1): Pooling({'word_embedding_dimension': 384, '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}) (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 = [ 'Medical Plus application is an web based application that provides the patients with speed time to find the best clinics and doctors, such as find the nearest clinic, search for best doctors, find all specialists, get latest news about new doctors and illness, ticket prices, ask for something you want to know about your illness and find new information from specific doctor.', 'get latest news about new doctors, such as find the nearest clinic, search for best doctors, ask for something you want to know about your illness, doctors, illness, find new information from specific doctor., ticket prices, find all specialists, Medical Plus application is an web based application that provides the patients with speed time to find the best clinics', 'he system provides online information of blood bank and administrators can also all information about Blood bank, donor, patient request and blood requirements.The Target of the application is to make the donation process more easily, spread awareness about this process, the way to deal with it.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 384] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities) # tensor([[1.0000, 0.8653, 0.3511], # [0.8653, 1.0000, 0.2667], # [0.3511, 0.2667, 1.0000]]) ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 359 training samples * Columns: sentence_0, sentence_1, and label * Approximate statistics based on the first 359 samples: | | sentence_0 | sentence_1 | label | |:--------|:-------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | | | | * Samples: | sentence_0 | sentence_1 | label | |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------| | And we dedicated that one of the most dangerous problem, that the patient not get the right Medicine for his conditions because of commercial and capitalism polices of the Medicine industry factories and Supply and demand policy of the doctors.

SO the main problems our team will make (GHC) system to solve it, and increase the performance and integrity of healthcare in Egypt to support Egypt vision 2030. | demand policy of the doctors., that the patient not get the right Medicine for his conditions because of commercial, we dedicated that one of the most dangerous problem, Supply, capitalism polices of the Medicine industry factories | 0.6 | | providing information about companies,chat online,providing different works,payment system | providing information about companies, providing, chat online | 0.6 | | Using this advanced technology, we will be able to gain transparency in our elections, without compromising the privacy of voters, and we have a way to accurately demonstrate the mathematical results of elections. Also, at the request of the voter, there will be a way to allow the voter to vote online in the election and follow his vote in the ballot box to ensure that his vote is stored safely and safely without changing or changing it in any way. | at the request of the voter, with this advanced technology, without compromising the privacy of voters, we have a way to accurately demonstrate the mathematical results of elections. Also, there will be a way to allow the, we will be able to gain transparency in our elections | 0.6 | * Loss: [CosineSimilarityLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "loss_fct": "torch.nn.modules.loss.MSELoss" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `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`: 8 - `per_device_eval_batch_size`: 8 - `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`: 3 - `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`: {}
### Framework Versions - Python: 3.11.9 - Sentence Transformers: 5.1.1 - Transformers: 4.57.1 - PyTorch: 2.9.0+cpu - Accelerate: 1.11.0 - Datasets: 4.3.0 - 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", } ```