REDSOULTM / baxy-router-encoder-ft

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/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: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 384 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': 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("sentence_transformers_model_id")
# Run inference
sentences = [
    'andá a la página de YouTube',
    'open a website, URL or web address in a browser; abrir una pagina web, abrir github o un sitio, abrir una direccion como python.org o localhost, navegar a un enlace, open a link in the browser. TAMBIEN: buscar o comprar un producto o juego en una TIENDA WEB (Instant Gaming, Steam store online, Epic Games, GOG, Amazon): ir al sitio de la tienda y buscar ahi el juego; find or buy a game on an online store website, go to the store site and search for the product',
    'Steam game library, Steam store, launch installed Steam games',
]
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: 11,808 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 3 tokens mean: 10.0 tokens max: 46 tokens	min: 9 tokens mean: 71.13 tokens max: 128 tokens

• Samples:

  sentence_0	sentence_1
  abre Notepad y escribe hola con GUI	screenshot, click, type text, hotkeys, scroll, drag with mouse
  schließ den Editor	abrir, cerrar o encontrar un programa o juego ya instalado en esta computadora, desde el menú de inicio; open, close or find an installed desktop application on this PC by name
  Mets le volume à 25 pour cent	audio volume, raise or lower the sound volume, turn it up or down (subir/bajar el volumen, lauter/leiser machen, alza/abbassa il volume, aumenta/diminui o volume, monter/baisser le volume); mute and unmute the sound (silenciar, desmutear, stummschalten, ton an, couper/rétablir le son, silenciar/reativar o som), system sound, media keys, audio devices listing

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size : 64
• per_device_eval_batch_size : 64
• num_train_epochs : 2
• multi_dataset_batch_sampler : round_robin

All Hyperparameters

Framework Versions

• Python: 3.11.15
• Sentence Transformers: 3.3.1
• Transformers: 4.44.2
• PyTorch: 2.6.0+cu124
• Accelerate: 1.13.0
• Datasets: 2.21.0
• Tokenizers: 0.19.1

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",
}

MultipleNegativesRankingLoss

@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}
}