yasserrmd / hindi-gemma-300m-emb

SentenceTransformer based on google/embeddinggemma-300m

This is a sentence-transformers model finetuned from google/embeddinggemma-300m . It maps sentences & paragraphs to a 768-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: google/embeddinggemma-300m
• Maximum Sequence Length: 2048 tokens
• Output Dimensionality: 768 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': 2048, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
  (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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (4): Normalize()
)

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("yasserrmd/hindi-gemma-300m-emb")
# Run inference
queries = [
    "\u0905\u092e\u0943\u0924\u0932\u093e\u0932 \u091a\u0915\u094d\u0930\u0935\u0930\u094d\u0924\u0940 \u0928\u0947 \u0915\u094c\u0928 \u0938\u0947 \u0938\u093e\u092a\u094d\u0924\u093e\u0939\u093f\u0915 \u092a\u0924\u094d\u0930\u093f\u0915\u093e \u0915\u093e \u0938\u0902\u092a\u093e\u0926\u0928 \u0915\u093f\u092f\u093e \u0914\u0930 \u0915\u093f\u0924\u0928\u0947 \u0938\u092e\u092f \u0924\u0915?",
]
documents = [
    "लगभग दस वर्ष तक साप्ताहिक 'हिन्दी बंगवासी' (कलकत्ता)",
    'संख्या में पांच हैं जिनके भीतर 17 मंत्र सम्मिलित माने जाते हैं।',
    'दरभंगा शहर',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.7499, 0.3033, 0.1277]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 5,002 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: 7 tokens mean: 16.51 tokens max: 38 tokens	min: 2 tokens mean: 9.98 tokens max: 263 tokens

• Samples:

  sentence_0	sentence_1
  हरी साड़ी जिसकी किनारी लाल रंग की हो और सफेद ब्लाउज, यह किसकी पोशाक हुआ करती थी?	महिला राष्ट्रीय संघ
  दिल्ली की कितनी जनसंख्या को झुग्गी-झोपड़ियों से स्थानांतरित किया गया है?	लगभग ४००,००० लोग
  मंदिर में किन-किन देवी-देवताओं की मूर्तियां स्थापित हैं?	शिव परिवार राम दरबार दुर्गा जी एवम महाकाली के साथ भैरव

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size : 4
• per_device_eval_batch_size : 4
• num_train_epochs : 7
• multi_dataset_batch_sampler : round_robin

All Hyperparameters

Training Logs

Framework Versions

• Python: 3.12.11
• Sentence Transformers: 5.1.0
• Transformers: 4.56.2
• PyTorch: 2.8.0+cu128
• Accelerate: 1.10.1
• Datasets: 4.0.0
• Tokenizers: 0.22.1

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}
}