metadata

base_model: saraleivam/GURU2-paraphrase-multilingual-MiniLM-L12-v2
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:100
  - loss:SoftmaxLoss
widget:
  - source_sentence: ilustracion,diseño ux uidiseño ux
    sentences:
      - >-
        Create AI-generated art using NightCafe. Apply styles and techniques to
        customize artwork  .  Produce a digital art portfolio showcasing AI
        creativity
      - >-
        The nature of discrete-time signals. Discrete-time signals are vectors
        in a vector space. Discrete-time signals can be analyzed in the
        frequency domain via the Fourier transform
      - >-
        Describe software engineering, Software Development Lifecycle (SDLC),
        and software development tools, technologies and stacks.  . List
        different types of programming languages and create basic programming
        constructs such as loops and conditions using Python.   . Outline
        approaches to application architecture and design, patterns, and
        deployment architectures.   . Summarize the skills required in software
        engineering and describe the career options it provides.
  - source_sentence: profesional
    sentences:
      - >-
        Create a  Facebook Prophet Machine learning model & Forecast the price
        of Bitcoin for the future 30 days. Learn to Visualize Bitcoin using
        Plotly Express. Learn to Extract Financial Data and Analyze it using
        Google Sheets
      - >-
        What Industry 4.0 is and what factors have enabled the IIoT.. Key skills
        to develop to be employed in the IIoT space.. What platforms are, and
        also market information on Software and Services.. What the top
        application areas are (examples include manufacturing and oil & gas).
      - Writing
  - source_sentence: ilustracion,diseño ux uidiseño ux
    sentences:
      - Creativity, Problem Solving, Writing
      - Anatomy of the Upper and Lower Extremities
      - >-
        Evaluate the performance of a classifier using visual diagnostic tools
        from Yellowbrick. Diagnose and handle class imbalance problems
  - source_sentence: Maestría en educación
    sentences:
      - >-
        Explain the seminal ideas leading to the birth of AI, the major
        difficulties and how the international community overtook them..
        Describe what AI is today in terms of goals, scientific community,
        companies’ interests. Describe the taxonomy of the know-how on AI in
        terms of techniques, software and hardware methodologies. . Explain the
        need for national strategies on AI and identify the major Italian and
        European players on AI
      - >-
        How a hardware component can be adapted at runtime to better respond to
        users/environment needs using FPGAs
      - >-
        A framework to evaluate DeFi risk; Environmental implications of
        cryptocurrency; and winners and losers in the future of finance.
  - source_sentence: ilustracion,diseño ux uidiseño ux
    sentences:
      - Planning
      - >-
        1.     Transform numbers between number bases and perform arithmetic in
        number bases . 2. Identify, describe and compute sequences of numbers
        and their sums. . 3. Represent and describe space numerically using
        coordinates and graphs.. 4. Study, represent and describe variations of
        quantities via functions and their graphs.
      - >-
        Create PivotTables to assess specific relationships within the data..
        Create line, bar, and pie charts to present the information from the
        PivotTables.. Compose a dashboard with the charts and tables created to
        present a global picture of the data.

SentenceTransformer based on saraleivam/GURU2-paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from saraleivam/GURU2-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/GURU2-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/GURU-train-paraphrase-multilingual-MiniLM-L12-v2")
# Run inference
sentences = [
    'ilustracion,diseño ux uidiseño ux',
    'Create PivotTables to assess specific relationships within the data.. Create line, bar, and pie charts to present the information from the PivotTables.. Compose a dashboard with the charts and tables created to present a global picture of the data.',
    '1.     Transform numbers between number bases and perform arithmetic in number bases . 2. Identify, describe and compute sequences of numbers and their sums. . 3. Represent and describe space numerically using coordinates and graphs.. 4. Study, represent and describe variations of quantities via functions and their graphs.',
]
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: 100 training samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 3 tokens
mean: 12.47 tokens
max: 26 tokens

min: 3 tokens
mean: 46.48 tokens
max: 128 tokens

0: ~39.00%
1: ~24.00%
2: ~37.00%
Samples:

sentence1 sentence2 label

ilustracion,diseño ux ui, sdiseño ux The Ancient Greeks 2

Marketing digital, Bachiller The Modern and the Postmodern (Part 1) 2

profesional Writing 1
Loss: SoftmaxLoss

	sentence1	sentence2	label
type	string	string	int
details	min: 3 tokens mean: 12.47 tokens max: 26 tokens	min: 3 tokens mean: 46.48 tokens max: 128 tokens	0: ~39.00% 1: ~24.00% 2: ~37.00%

sentence1	sentence2	label
`ilustracion,diseño ux ui, sdiseño ux`	`The Ancient Greeks`	`2`
`Marketing digital, Bachiller`	`The Modern and the Postmodern (Part 1)`	`2`
`profesional`	`Writing`	`1`

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: 2.3.0+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",
}