ChemMRL: SMILES Matryoshka Representation Learning Embedding Transformer

This is a Chem-MRL (sentence-transformers) model finetuned from Derify/ChemBERTa-druglike on the pubchem_10m_genmol_similarity dataset. It maps SMILES to a 1024-dimensional dense vector space and can be used for molecular similarity, semantic search, database indexing, molecular classification, clustering, and more.

Model Details

Model Description

• Model Type: ChemMRL (Sentence Transformer)
• Base model: Derify/ChemBERTa-druglike
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Tanimoto
• Training Dataset:
  • pubchem_10m_genmol_similarity
• License: apache-2.0

Model Sources

• Repository: Chem-MRL on GitHub
• Demo App Repository: Chem-MRL-demo on GitHub

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'RobertaModel'})
  (1): Pooling({'word_embedding_dimension': 1024, '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): Normalize()
)

Usage

Direct Usage (Chem-MRL)

First install the Chem-MRL library:

pip install -U chem-mrl>=0.7.3

Then you can load this model and run inference.

from chem_mrl import ChemMRL

# Download from the 🤗 Hub
model = ChemMRL("Derify/ChemMRL-beta")
# Run inference
sentences = [
    "Clc1nccc(C#CCCc2nc3ccccc3o2)n1",
    "O=Cc1nc2ccccc2o1",
    "O[C@H]1CN(C(Cc2ccccc2)c2ccccc2)C[C@@H]1Cc1cnc[nH]1",
]
embeddings = model.backbone.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.backbone.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.3200, 0.1209],
#         [0.3200, 1.0000, 0.0950],
#         [0.1209, 0.0950, 1.0000]])

# Load the model with half precision
model = ChemMRL("Derify/ChemMRL-beta", use_half_precision=True)
sentences = [
    "Clc1nccc(C#CCCc2nc3ccccc3o2)n1",
    "O=Cc1nc2ccccc2o1",
    "O[C@H]1CN(C(Cc2ccccc2)c2ccccc2)C[C@@H]1Cc1cnc[nH]1",
]
embeddings = model.embed(sentences)  # Use the embed method for half precision
print(embeddings.shape)
# [3, 1024]

Evaluation

Metrics

Semantic Similarity

• Dataset: pubchem_10m_genmol_similarity
• Evaluated with chem_mrl.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator with these parameters:

  {
      "precision": "float32"
  }
  

Training Details

Training Dataset

pubchem_10m_genmol_similarity

• Dataset: pubchem_10m_genmol_similarity at f68d779

• Size: 19,692,766 training samples

• Columns: smiles_a, smiles_b, and label

• Approximate statistics based on the first 1000 samples:

  	smiles_a	smiles_b	label
  type	string	string	float
  details	min: 17 tokens mean: 39.66 tokens max: 119 tokens	min: 11 tokens mean: 38.29 tokens max: 115 tokens	min: 0.02 mean: 0.57 max: 1.0

• Loss: Matryoshka2dLoss with these parameters:

  Click to expand

  {
      "loss": "TanimotoSentLoss",
      "n_layers_per_step": -1,
      "last_layer_weight": 2.0,
      "prior_layers_weight": 1.0,
      "kl_div_weight": 0.5,
      "kl_temperature": 0.3,
      "matryoshka_dims": [
          1024,
          512,
          256,
          128,
          64,
          32,
          16,
          8
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 128
• learning_rate: 8e-06
• weight_decay: 6.505130550397454e-06
• warmup_ratio: 0.2
• data_seed: 42
• fp16: True
• tf32: True
• load_best_model_at_end: True
• optim: adamw_apex_fused
• dataloader_pin_memory: False

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 128
• 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: 8e-06
• weight_decay: 6.505130550397454e-06
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 3
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.2
• 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: 42
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: True
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: True
• 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: True
• 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}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_apex_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: False
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• 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: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: AMD Ryzen 7 3700X 8-Core Processor
• RAM Size: 62.70 GB

Framework Versions

• Python: 3.12.11
• Sentence Transformers: 5.0.0
• Transformers: 4.53.3
• PyTorch: 2.7.1+cu126
• Accelerate: 1.9.0
• Datasets: 3.6.0
• Tokenizers: 0.21.2

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",
}

Matryoshka2dLoss

@misc{li20242d,
    title={2D Matryoshka Sentence Embeddings},
    author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li},
    year={2024},
    eprint={2402.14776},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}

TanimotoSentLoss

@online{cortes-2025-tanimotosentloss,
    title={TanimotoSentLoss: Tanimoto Loss for SMILES Embeddings},
    author={Emmanuel Cortes},
    year={2025},
    month={Jan},
    url={https://github.com/emapco/chem-mrl},
}

Model Card Authors

@eacortes

Model Card Contact

Manny Cortes (manny@derifyai.com)