cafierom/smiles_embedding_gemma_FT

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 retrieval.

Model Details

Model Description

• —Model Type: Sentence Transformer
• —Base model: google/embeddinggemma-300m <!-- at revision 57c266a740f537b4dc058e1b0cda161fd15afa75 -->
• —Maximum Sequence Length: 128 tokens
• —Output Dimensionality: 768 dimensions
• —Similarity Function: Cosine Similarity
• —Supported Modality: Text <!-- - 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({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'Gemma3TextModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', 'include_prompt': True})
  (2): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
  (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("cafierom/smiles_embedding_gemma_FT")
# Run inference
queries = [
    'CCC(CC)(c1ccccc1)c1ccc(\\C=C\\[C@@H](O)C[C@@H](O)CC([O-])=O)c(c1)-c1ccccc1F',
]
documents = [
    'Cc1ccc(C(=C(\\C=C\\[C@@H](O)C[C@@H](O)CC([O-])=O)c2nnnn2C)c2ccc(C)cc2C)c(C)c1',
    'O[C@H](CCn1c(nc(c1-c1ccc(F)cc1)-c1ccc(F)cc1)C(F)(F)F)C[C@@H](O)CC([O-])=O',
    'CC(C)c1c(c(c(-c2ccc(F)cc2)n1CC[C@@H](O)C[C@@H](O)CC([O-])=O)-c1ccccc1)S(=O)(=O)N(C)C',
]
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([[0.9356, 0.9019, 0.5159]])

<!--

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. -->

<!--

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: 3,396 training samples
• —Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
• —Approximate statistics based on the first 100 samples: | | premise | hypothesis | label | |:---------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | modality | text | text | | | details | <ul><li>min: 18 tokens</li><li>mean: 58.11 tokens</li><li>max: 117 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 54.91 tokens</li><li>max: 119 tokens</li></ul> | <ul><li>0: ~55.77%</li><li>2: ~44.23%</li></ul> |
• —Samples: | premise | hypothesis | label | |:-----------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|:---------------| | <code>CCC@HC(=O)O[C@H]1CC@HC@HCC(=O)O3)[C@@H]12)\C=C\Cc1ccccc1</code> | <code>Cc1cc(-c2ccc(Cl)cc2)c(\C=C\[C@@H]2CC@@HCC(=O)O2)c(C)n1</code> | <code>2</code> | | <code>CC(C)n1c(CCC@@HCC@@HCC([O-])=O)c(c(c1C(=O)Nc1ccccc1)-c1ccccc1)-c1ccc(F)cc1</code> | <code>CC(C)n1c(CCC@@HCC@@HCC([O-])=O)c(c(c1C(=O)NCc1ccccn1)-c1ccccc1)-c1ccc(F)cc1</code> | <code>0</code> | | <code>CC(C)n1c(CCC@@HCC@@HCC([O-])=O)c(c(c1C(=O)N(C)C)-c1ccccc1)-c1ccc(F)cc1</code> | <code>COc1ccc2ccccc2c1-c1ccc(C(C)C)n1CC[C@@H]1CC@@HCC(=O)O1</code> | <code>2</code> |
• —Loss: <code>SoftmaxLoss</code> with these parameters:

  {
      "num_labels": 3,
      "concatenation_sent_rep": true,
      "concatenation_sent_difference": true,
      "concatenation_sent_multiplication": false
  }

Evaluation Dataset

Unnamed Dataset

• —Size: 600 evaluation samples
• —Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
• —Approximate statistics based on the first 100 samples: | | premise | hypothesis | label | |:---------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | modality | text | text | | | details | <ul><li>min: 11 tokens</li><li>mean: 56.06 tokens</li><li>max: 101 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 55.85 tokens</li><li>max: 119 tokens</li></ul> | <ul><li>0: ~41.35%</li><li>2: ~58.65%</li></ul> |
• —Samples: | premise | hypothesis | label | |:--------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------|:---------------| | <code>CNc1cccc(c1)-c1nc(C(C)C)n(\C=C\C@@HCC@@HCC([O-])=O)c1-c1ccc(F)cc1</code> | <code>CC(C)c1c(CCC@@HCC@@HCC([O-])=O)c(cn1-c1ccccc1)-c1ccc(F)cc1</code> | <code>0</code> | | <code>CC(C)c1nc(nc(-c2ccc(F)cc2)c1\C=C\[C@@H]1CC@@HCC(OCC(Cl)(Cl)Cl)O1)N(C)S(C)(=O)=O</code> | <code>CC(C)c1nn(-c2nc3ccccc3s2)c(c1\C=C\C@@HCC@@HCC([O-])=O)-c1ccc(F)cc1</code> | <code>2</code> | | <code>Cc1c(\C=C\C@HCC@@HCC([O-])=O)c(cn1-c1ccccc1)-c1ccc(F)cc1</code> | <code>CC@HC(O)=O)[C@H]1CC(=O)[C@@]2(C)C3=C(C(=O)C[C@]12C)[C@@]1(C)CCC(=O)C@@(COC(=O)CC@@(O)CC(O)=O)[C@@H]1CC3=O</code> | <code>2</code> |
• —Loss: <code>SoftmaxLoss</code> with these parameters:

  {
      "num_labels": 3,
      "concatenation_sent_rep": true,
      "concatenation_sent_difference": true,
      "concatenation_sent_multiplication": false
  }

Training Hyperparameters

Non-Default Hyperparameters

• —warmup_steps: 10
• —optim: adafactor
• —weight_decay: 0.01
• —bf16: True
• —load_best_model_at_end: True
• —dataloader_pin_memory: False

All Hyperparameters

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

• —per_device_train_batch_size: 8
• —num_train_epochs: 3
• —max_steps: -1
• —learning_rate: 5e-05
• —lr_scheduler_type: linear
• —lr_scheduler_kwargs: None
• —warmup_steps: 10
• —optim: adafactor
• —optim_args: None
• —weight_decay: 0.01
• —adam_beta1: 0.9
• —adam_beta2: 0.999
• —adam_epsilon: 1e-08
• —optim_target_modules: None
• —gradient_accumulation_steps: 1
• —average_tokens_across_devices: True
• —max_grad_norm: 1.0
• —label_smoothing_factor: 0.0
• —bf16: True
• —fp16: False
• —bf16_full_eval: False
• —fp16_full_eval: False
• —tf32: None
• —gradient_checkpointing: False
• —gradient_checkpointing_kwargs: None
• —torch_compile: False
• —torch_compile_backend: None
• —torch_compile_mode: None
• —use_liger_kernel: False
• —liger_kernel_config: None
• —use_cache: False
• —neftune_noise_alpha: None
• —torch_empty_cache_steps: None
• —auto_find_batch_size: False
• —log_on_each_node: True
• —logging_nan_inf_filter: True
• —include_num_input_tokens_seen: no
• —log_level: passive
• —log_level_replica: warning
• —disable_tqdm: False
• —project: huggingface
• —trackio_space_id: None
• —trackio_bucket_id: None
• —trackio_static_space_id: None
• —per_device_eval_batch_size: 8
• —prediction_loss_only: True
• —eval_on_start: False
• —eval_do_concat_batches: True
• —eval_use_gather_object: False
• —eval_accumulation_steps: None
• —include_for_metrics: []
• —batch_eval_metrics: False
• —save_only_model: False
• —save_on_each_node: False
• —enable_jit_checkpoint: False
• —push_to_hub: False
• —hub_private_repo: None
• —hub_model_id: None
• —hub_strategy: every_save
• —hub_always_push: False
• —hub_revision: None
• —load_best_model_at_end: True
• —ignore_data_skip: False
• —restore_callback_states_from_checkpoint: False
• —full_determinism: False
• —seed: 42
• —data_seed: None
• —use_cpu: False
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': None}
• —parallelism_config: None
• —dataloader_drop_last: False
• —dataloader_num_workers: 0
• —dataloader_pin_memory: False
• —dataloader_persistent_workers: False
• —dataloader_prefetch_factor: None
• —remove_unused_columns: True
• —label_names: None
• —train_sampling_strategy: random
• —length_column_name: length
• —ddp_find_unused_parameters: None
• —ddp_bucket_cap_mb: None
• —ddp_broadcast_buffers: False
• —ddp_static_graph: None
• —ddp_backend: None
• —ddp_timeout: 1800
• —fsdp: None
• —fsdp_config: None
• —deepspeed: None
• —debug: []
• —skip_memory_metrics: True
• —do_predict: False
• —resume_from_checkpoint: None
• —warmup_ratio: None
• —local_rank: -1
• —prompts: None
• —batch_sampler: batch_sampler
• —multi_dataset_batch_sampler: proportional
• —router_mapping: {}
• —learning_rate_mapping: {}

</details>

Training Logs

• —The bold row denotes the saved checkpoint.

Training Time

• —Training: 31.9 minutes
• —Evaluation: 19.4 minutes
• —Total: 51.3 minutes

Framework Versions

• —Python: 3.12.13
• —Sentence Transformers: 5.6.1
• —Transformers: 5.14.1
• —PyTorch: 2.13.0
• —Accelerate: 1.14.0
• —Datasets: 5.0.1
• —Tokenizers: 0.22.2

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",
}

<!--

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. -->