saraleivam/GURU2-paraphrase-multilingual-MiniLM-L12-v2

SentenceTransformer based on saraleivam/GURU-paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from saraleivam/GURU-paraphrase-multilingual-MiniLM-L12-v2. 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: saraleivam/GURU-paraphrase-multilingual-MiniLM-L12-v2
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 384 tokens
• 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': 128, 'do_lower_case': False}) with Transformer model: 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})
)

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("saraleivam/GURU2-paraphrase-multilingual-MiniLM-L12-v2")
# Run inference
sentences = [
    'Servicio consultor SAP MM con experiencia Data Maestra SemiSenior, actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.',
    'Python, Bash and SQL Essentials for Data Engineering.Computer Science.Software Development.Develop data engineering solutions with a minimal and essential subset of the Python language and the Linux environment. Design scripts to connect and query a SQL database using Python. Use a scraping library in Python to read, identify and extract data from websites ',
    'AI-Enhanced Content Creation:Elevate Copywriting with Humata.Data Science.Machine Learning.Use prompts in Humata AI to get the information needed to generate an ad copy from the source files.  . Create engaging ads and blog posts tailored to your audience with the help of Humata AI prompts.  . Create a compelling advertisement for various online platforms using prompt engineering in Humata AI.    ',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

Unnamed Dataset

• Size: 500 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 77 tokens mean: 77.0 tokens max: 77 tokens	min: 14 tokens mean: 64.05 tokens max: 128 tokens	0: ~17.00% 1: ~25.00% 2: ~58.00%

• Samples:

  sentence1	sentence2	label
  Servicio consultor SAP MM con experiencia Data Maestra SemiSenior, actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.	Introduction to Generative AI - 한국어.Information Technology.Cloud Computing.생성형 AI 정의. 생성형 AI의 작동 방식 설명. 생성형 AI 모델 유형 설명. 생성형 AI 애플리케이션 설명	0
  Servicio consultor SAP MM con experiencia Data Maestra SemiSenior, actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.	Mastering Excel Essentials to Enhance Business Value.Business.Business Essentials.Effectively input data and efficiently navigate large spreadsheets.. Employ various "hacks" and expertly apply (the most appropriate) built-in functions in Excel to increase productivity and streamline workflow.. Apply the "what-if" analysis tools in Excel to conduct break-even analysis, conduct sensitivity analysis and support decision-making.	1
  Servicio consultor SAP MM con experiencia Data Maestra SemiSenior, actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.	Exploring Piano Literature: The Piano Sonata.Arts and Humanities.Music and Art.Identify specific historical time periods in which the popularity of sonatas increases or decreases and the reasons behind these trends. . Identify sonata form. Recognize the most influential pieces in the sonata repertoire.	2

• Loss: SoftmaxLoss

Training Hyperparameters

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
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 3.0
• 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: 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}
• 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: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• 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
• dispatch_batches: None
• split_batches: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.3.1+cu121
• Accelerate: 0.31.0
• Datasets: 2.20.0
• Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers and SoftmaxLoss

@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",
}