Upload 12 files

3_Triplet Contrastive (SmartBatch) (TC-SB)/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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
+}

3_Triplet Contrastive (SmartBatch) (TC-SB)/README.md

@@ -0,0 +1,380 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:10000
+- loss:TripletLoss
+base_model: sentence-transformers/all-mpnet-base-v2
+widget:
+- source_sentence: 'Database: trna-n6-adenosine-threonylcarbamoyltransferase-tsad
+    | Table: trna-n6-adenosine-threonylcarbamoyltransferase-tsad_natural-product |
+    Sample: ...'
+  sentences:
+  - 'Database: trna-n6-adenosine-threonylcarbamoyltransferase-tsad | Table: trna-n6-adenosine-threonylcarbamoyltransferase-tsad_trna-n6-adenosine-threonylcarbamoyltransferase-tsad
+    | Sample: ...'
+  - 'Database: oxidoreductase-alpha-molybdopterin-subunit | Table: oxidoreductase-alpha-molybdopterin-subunit_oxidoreductase-alpha-molybdopterin-subunit
+    | Sample: ...'
+  - 'Database: protein-of-unknown-function-duf3561 | Table: protein-of-unknown-function-duf3561_encoded-by
+    | Sample: ...'
+- source_sentence: 'Database: maastricht-formation | Table: maastricht-formation_eponym
+    | Sample: ...'
+  sentences:
+  - 'Database: maastricht-formation | Table: maastricht-formation_eponym | Sample:
+    ...'
+  - 'Database: uncharacterised-protein-yqey-aim41 | Table: uncharacterised-protein-yqey-aim41_uncharacterised-protein-yqey-aim41
+    | Sample: ...'
+  - 'Database: 3-dehydro-bile-acid-delta46-reductase-like | Table: 3-dehydro-bile-acid-delta46-reductase-like_encoded-by
+    | Sample: ...'
+- source_sentence: 'Database: hexokinase-subgroup | Table: hexokinase-subgroup_encoded-by
+    | Sample: ...'
+  sentences:
+  - 'Database: fictional-energy | Table: fictional-energy_fictional-energy | Sample:
+    ...'
+  - 'Database: co-dehydrogenase-flavoprotein-c-terminal-domain-superfamily | Table:
+    co-dehydrogenase-flavoprotein-c-terminal-domain-superfamily_co-dehydrogenase-flavoprotein-c-terminal-domain-superfamily
+    | Sample: ...'
+  - 'Database: hexokinase-subgroup | Table: hexokinase-subgroup_chromosome | Sample:
+    ...'
+- source_sentence: 'Database: 2010-fifa-world-cup-qualification-uefa-group-1 | Table:
+    2010-fifa-world-cup-qualification-uefa-group-1_occupant | Sample: ...'
+  sentences:
+  - 'Database: 2010-fifa-world-cup-qualification-uefa-group-1 | Table: 2010-fifa-world-cup-qualification-uefa-group-1_occupant
+    | Sample: ...'
+  - 'Database: rna-polymerase-beta-subunit-conserved-site-protein-family | Table:
+    rna-polymerase-beta-subunit-conserved-site-protein-family_rna-polymerase-beta-subunit-conserved-site-protein-family
+    | Sample: ...'
+  - 'Database: anaphase-promoting-complex-subunit-4-wd40-domain-protein-family | Table:
+    anaphase-promoting-complex-subunit-4-wd40-domain-protein-family_natural-product
+    | Sample: ...'
+- source_sentence: 'Database: bothy | Table: bothy_capital-city | Sample: ...'
+  sentences:
+  - 'Database: bothy | Table: bothy_administrative-centre | Sample: ...'
+  - 'Database: provincial-museum-in-finland | Table: provincial-museum-in-finland_jurisdiction
+    | Sample: ...'
+  - 'Database: saicar-synthetase-conserved-site-protein-family | Table: saicar-synthetase-conserved-site-protein-family_encoded-by
+    | Sample: ...'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). 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:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 12e86a3c702fc3c50205a8db88f0ec7c0b6b94a0 -->
+- **Maximum Sequence Length:** 384 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (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): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Database: bothy | Table: bothy_capital-city | Sample: ...',
+    'Database: bothy | Table: bothy_administrative-centre | Sample: ...',
+    'Database: saicar-synthetase-conserved-site-protein-family | Table: saicar-synthetase-conserved-site-protein-family_encoded-by | Sample: ...',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### 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: 10,000 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                          | sentence_1                                                                         | sentence_2                                                                          |
+  |:--------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                             | string                                                                              |
+  | details | <ul><li>min: 17 tokens</li><li>mean: 38.39 tokens</li><li>max: 116 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 38.7 tokens</li><li>max: 107 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 38.53 tokens</li><li>max: 122 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                            | sentence_1                                                                                                                                                                                                                                                | sentence_2                                                                                                                                                           |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Database: protein-of-unknown-function-duf2635 | Table: protein-of-unknown-function-duf2635_encodes | Sample: ...</code>                                                                         | <code>Database: protein-of-unknown-function-duf2635 | Table: protein-of-unknown-function-duf2635_protein-of-unknown-function-duf2635 | Sample: ...</code>                                                                                                 | <code>Database: extinct-volcano | Table: extinct-volcano_country | Sample: ...</code>                                                                                |
+  | <code>Database: tetrapyrrole-biosynthesis-glutamate-1-semialdehyde-aminotransferase | Table: tetrapyrrole-biosynthesis-glutamate-1-semialdehyde-aminotransferase_natural-product | Sample: ...</code> | <code>Database: tetrapyrrole-biosynthesis-glutamate-1-semialdehyde-aminotransferase | Table: tetrapyrrole-biosynthesis-glutamate-1-semialdehyde-aminotransferase_tetrapyrrole-biosynthesis-glutamate-1-semialdehyde-aminotransferase | Sample: ...</code> | <code>Database: pili-assembly-chaperone-conserved-site-protein-family | Table: pili-assembly-chaperone-conserved-site-protein-family_encoded-by | Sample: ...</code> |
+  | <code>Database: series-of-images | Table: series-of-images_series-of-images | Sample: ...</code>                                                                                                      | <code>Database: series-of-images | Table: series-of-images_topic | Sample: ...</code>                                                                                                                                                                     | <code>Database: claretian-martyrs-of-barbastro | Table: claretian-martyrs-of-barbastro_claretian-martyrs-of-barbastro | Sample: ...</code>                           |
+* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
+      "triplet_margin": 5
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `fp16`: True
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `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`: True
+- `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}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `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
+- `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
+- `dispatch_batches`: None
+- `split_batches`: 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
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch | Step | Training Loss |
+|:-----:|:----:|:-------------:|
+| 0.8   | 500  | 4.0418        |
+| 1.6   | 1000 | 3.8665        |
+| 2.4   | 1500 | 3.8205        |
+
+
+### Framework Versions
+- Python: 3.10.15
+- Sentence Transformers: 3.4.1
+- Transformers: 4.49.0
+- PyTorch: 2.6.0+cu118
+- Accelerate: 0.29.3
+- Datasets: 3.4.1
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@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",
+}
+```
+
+#### TripletLoss
+```bibtex
+@misc{hermans2017defense,
+    title={In Defense of the Triplet Loss for Person Re-Identification},
+    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
+    year={2017},
+    eprint={1703.07737},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```
+
+<!--
+## 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.*
+-->

3_Triplet Contrastive (SmartBatch) (TC-SB)/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vocab_size": 30527
+}

3_Triplet Contrastive (SmartBatch) (TC-SB)/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.49.0",
+    "pytorch": "2.6.0+cu118"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

3_Triplet Contrastive (SmartBatch) (TC-SB)/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:166fa679399b8cfe209dfa08d8a500bfe0c0e24ef3c446e7b6c8ac2aaa3f0923
+size 437967672

3_Triplet Contrastive (SmartBatch) (TC-SB)/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

3_Triplet Contrastive (SmartBatch) (TC-SB)/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211f2f46bb9545b19ad02abce0a47037ca4dfabe83984b58024eebdc27bbd64b
+size 438026982

3_Triplet Contrastive (SmartBatch) (TC-SB)/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 384,
+  "do_lower_case": false
+}

3_Triplet Contrastive (SmartBatch) (TC-SB)/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

3_Triplet Contrastive (SmartBatch) (TC-SB)/tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}