Model Distiluse Base Multilingual Cased V1 10 Epochs

🚀 {MODEL_NAME}

This is a sentence-transformers model that maps sentences and paragraphs to a 512-dimensional dense vector space. It can be used for tasks such as clustering or semantic search, providing efficient solutions for text processing.

🚀 Quick Start

Using this model becomes easy when you have sentence-transformers installed. First, install the necessary library:

pip install -U sentence-transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)

✨ Features

• Maps sentences and paragraphs to a 512-dimensional dense vector space.
• Suitable for tasks like clustering and semantic search.

📦 Installation

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)

📚 Documentation

Evaluation Results

For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net

Training

The model was trained with the following parameters: DataLoader: torch.utils.data.dataloader.DataLoader of length 11 with parameters:

{'batch_size': 15, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss: sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss Parameters of the fit()-Method:

{
    "epochs": 10,
    "evaluation_steps": 1,
    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 11,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
  (2): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)

🔧 Technical Details

The model is based on the sentence-transformers framework. It uses a Transformer model (DistilBertModel) for feature extraction, followed by a pooling layer and a dense layer to map the input to a 512-dimensional vector space. The training process uses a cosine similarity loss function and an AdamW optimizer with a warm-up linear scheduler.

📄 License

No license information provided in the original document.