gemma-ai-faq-embeddings-v2

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 <!-- at revision 57c266a740f537b4dc058e1b0cda161fd15afa75 -->
• Maximum Sequence Length: 2048 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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("kevinadityai/gemma-ai-faq-embeddings-v2")
# Run inference
queries = [
    "Apa nama lain Siloam Kuta?",
]
documents = [
    'Nama lain Siloam Kuta adalah Siloam Hospitals Denpasar atau SHDP',
    'Saat ini memang hanya ada produk tertentu di website. Untuk mengetahui apakah produk yang Anda cari ada di rumah sakit tertentu, Anda dapat langsung menghubungi contact center 1-500-911.',
    'Saat ini, kami menerima uang tunai dan sebagian besar kartu debit/kredit. ATM tersedia di semua Siloam Hospitals.',
]
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([[0.7178, 0.1271, 0.1815]])

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Triplet

• Datasets: ai-faq-validation and ai-faq-test
• Evaluated with <code>TripletEvaluator</code>

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

Unnamed Dataset

• Size: 304 training samples
• Columns: <code>query</code>, <code>answer_positive</code>, and <code>answer_negative</code>
• Approximate statistics based on the first 304 samples:

  	query	answer_positive	answer_negative
  type	string	string	string
  details	<ul><li>min: 3 tokens</li><li>mean: 12.51 tokens</li><li>max: 44 tokens</li></ul>	<ul><li>min: 9 tokens</li><li>mean: 35.49 tokens</li><li>max: 409 tokens</li></ul>	<ul><li>min: 9 tokens</li><li>mean: 35.49 tokens</li><li>max: 409 tokens</li></ul>

• Samples:

  query	answer_positive	answer_negative
  <code>Apa nama lain Siloam Kuta?</code>	<code>Nama lain Siloam Kuta adalah Siloam Hospitals Denpasar atau SHDP</code>	<code>Saat ini memang hanya ada produk tertentu di website. Untuk mengetahui apakah produk yang Anda cari ada di rumah sakit tertentu, Anda dapat langsung menghubungi contact center 1-500-911.</code>
  <code>Rumah sakit Siloam Hospitals Banjarmasin punya nama lain apa?</code>	<code>Nama lain Siloam Hospitals Banjarmasin adalah SHBJ atau Siloam Banjarmasin Tengah</code>	<code>Anda dapat melakukan cancel appointment dan melakukan booking ulang di tanggal yang diinginkan, atau dapat menghubungi/mendatangi Rumah Sakit yang ingin dituju.</code>
  <code>Apa itu MRCCC?</code>	<code>MRCCC Siloam Hospitals Semanggi adalah kepanjangan dari MRCCC</code>	<code>Lokasinya di Jl. Sultan Hasanuddin No.58, Batulo, Kec. Wolio, Kota Bau-Bau, Sulawesi Tenggara 93716</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 30 evaluation samples
• Columns: <code>query</code>, <code>answer_positive</code>, and <code>answer_negative</code>
• Approximate statistics based on the first 30 samples:

  	query	answer_positive	answer_negative
  type	string	string	string
  details	<ul><li>min: 7 tokens</li><li>mean: 12.5 tokens</li><li>max: 20 tokens</li></ul>	<ul><li>min: 15 tokens</li><li>mean: 31.17 tokens</li><li>max: 82 tokens</li></ul>	<ul><li>min: 13 tokens</li><li>mean: 47.8 tokens</li><li>max: 314 tokens</li></ul>

• Samples:

  query	answer_positive	answer_negative
  <code>Apa nama lain Siloam Kuta?</code>	<code>Nama lain Siloam Kuta adalah Siloam Hospitals Denpasar atau SHDP</code>	<code>Saat ini memang hanya ada produk tertentu di website. Untuk mengetahui apakah produk yang Anda cari ada di rumah sakit tertentu, Anda dapat langsung menghubungi contact center 1-500-911.</code>
  <code>Rumah sakit Siloam Hospitals Banjarmasin punya nama lain apa?</code>	<code>Nama lain Siloam Hospitals Banjarmasin adalah SHBJ atau Siloam Banjarmasin Tengah</code>	<code>Anda dapat melakukan cancel appointment dan melakukan booking ulang di tanggal yang diinginkan, atau dapat menghubungi/mendatangi Rumah Sakit yang ingin dituju.</code>
  <code>Apa itu MRCCC?</code>	<code>MRCCC Siloam Hospitals Semanggi adalah kepanjangan dari MRCCC</code>	<code>Lokasinya di Jl. Sultan Hasanuddin No.58, Batulo, Kec. Wolio, Kota Bau-Bau, Sulawesi Tenggara 93716</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• batch_sampler: no_duplicates

All Hyperparameters

<details><summary>Click to expand</summary>

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• 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
• torch_empty_cache_steps: None
• learning_rate: 2e-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: 1
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• 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}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• 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: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• 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
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

Framework Versions

• Python: 3.12.10
• Sentence Transformers: 5.1.1
• Transformers: 4.56.2
• PyTorch: 2.8.0+cpu
• Accelerate: 1.10.1
• Datasets: 4.1.1
• 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}
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->