Upload MiniLM-L12 intertextual embedder

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 384,
+    "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
+}

README.md

@@ -0,0 +1,431 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:275838
+- loss:TripletLoss
+base_model: sentence-transformers/all-MiniLM-L12-v2
+widget:
+- source_sentence: Thus saith the LORD of hosts, the God of Israel; As yet they shall
+    use this speech in the land of Judah and in the cities thereof, when I shall bring
+    again their captivity; The LORD bless thee, O habitation of justice, and mountain
+    of holiness.
+  sentences:
+  - 'The LORD shall bless thee out of Zion: and thou shalt see the good of Jerusalem
+    all the days of thy life.'
+  - And he went out to meet Asa, and said unto him, Hear ye me, Asa, and all Judah
+    and Benjamin; The LORD is with you, while ye be with him; and if ye seek him,
+    he will be found of you; but if ye forsake him, he will forsake you.
+  - And say thou unto them, Thus saith the LORD God of Israel; Cursed be the man that
+    obeyeth not the words of this covenant,
+- source_sentence: Because of their wickedness which they have committed to provoke
+    me to anger, in that they went to burn incense, and to serve other gods, whom
+    they knew not, neither they, ye, nor your fathers.
+  sentences:
+  - 'Woe be unto thee, O Moab! the people of Chemosh perisheth: for thy sons are taken
+    captives, and thy daughters captives.'
+  - 'It repenteth me that I have set up Saul to be king: for he is turned back from
+    following me, and hath not performed my commandments. And it grieved Samuel; and
+    he cried unto the LORD all night.'
+  - If thy brother, the son of thy mother, or thy son, or thy daughter, or the wife
+    of thy bosom, or thy friend, which is as thine own soul, entice thee secretly,
+    saying, Let us go and serve other gods, which thou hast not known, thou, nor thy
+    fathers;
+- source_sentence: As the appearance of the bow that is in the cloud in the day of
+    rain, so was the appearance of the brightness round about. This was the appearance
+    of the likeness of the glory of the LORD. And when I saw it, I fell upon my face,
+    and I heard a voice of one that spake.
+  sentences:
+  - 'A new heart also will I give you, and a new spirit will I put within you: and
+    I will take away the stony heart out of your flesh, and I will give you an heart
+    of flesh.'
+  - Thus saith the Lord GOD; If the prince give a gift unto any of his sons, the inheritance
+    thereof shall be his sons’; it shall be their possession by inheritance.
+  - 'And when I saw him, I fell at his feet as dead. And he laid his right hand upon
+    me, saying unto me, Fear not; I am the first and the last:'
+- source_sentence: Masters, give unto your servants that which is just and equal;
+    knowing that ye also have a Master in heaven.
+  sentences:
+  - And not holding the Head, from which all the body by joints and bands having nourishment
+    ministered, and knit together, increaseth with the increase of God.
+  - And he said also unto his disciples, There was a certain rich man, which had a
+    steward; and the same was accused unto him that he had wasted his goods.
+  - And the keeper of the prison awaking out of his sleep, and seeing the prison doors
+    open, he drew out his sword, and would have killed himself, supposing that the
+    prisoners had been fled.
+- source_sentence: But God shall wound the head of his enemies, and the hairy scalp
+    of such an one as goeth on still in his trespasses.
+  sentences:
+  - 'Then again called they the man that was blind, and said unto him, Give God the
+    praise: we know that this man is a sinner.'
+  - Who can utter the mighty acts of the LORD? who can shew forth all his praise?
+  - Again, when the wicked man turneth away from his wickedness that he hath committed,
+    and doeth that which is lawful and right, he shall save his soul alive.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: intertextual similarity chirho
+      type: intertextual-similarity-chirho
+    metrics:
+    - type: pearson_cosine
+      value: 0.6270927412432303
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6326350413656476
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-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-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) <!-- at revision 936af83a2ecce5fe87a09109ff5cbcefe073173a -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 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/huggingface/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': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
+  (1): Pooling({'word_embedding_dimension': 384, '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 = [
+    'But God shall wound the head of his enemies, and the hairy scalp of such an one as goeth on still in his trespasses.',
+    'Again, when the wicked man turneth away from his wickedness that he hath committed, and doeth that which is lawful and right, he shall save his soul alive.',
+    'Who can utter the mighty acts of the LORD? who can shew forth all his praise?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[ 1.0000, -0.0455, -0.3163],
+#         [-0.0455,  1.0000, -0.0269],
+#         [-0.3163, -0.0269,  1.0000]])
+```
+
+<!--
+### 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
+
+#### Semantic Similarity
+
+* Dataset: `intertextual-similarity-chirho`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6271     |
+| **spearman_cosine** | **0.6326** |
+
+<!--
+## 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: 275,838 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: 12 tokens</li><li>mean: 37.48 tokens</li><li>max: 92 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 36.65 tokens</li><li>max: 83 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 33.52 tokens</li><li>max: 109 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                          | sentence_1                                                                                                                                                                                                                       | sentence_2                                                                                                                                                                                                      |
+  |:------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>And the LORD took me as I followed the flock, and the LORD said unto me, Go, prophesy unto my people Israel.</code>           | <code>And as Jesus passed forth from thence, he saw a man, named Matthew, sitting at the receipt of custom: and he saith unto him, Follow me. And he arose, and followed him.</code>                                             | <code>But, behold, I will raise up against you a nation, O house of Israel, saith the LORD the God of hosts; and they shall afflict you from the entering in of Hemath unto the river of the wilderness.</code> |
+  | <code>Let the elders that rule well be counted worthy of double honour, especially they who labour in the word and doctrine.</code> | <code>We then, as workers together with him, beseech you also that ye receive not the grace of God in vain.</code>                                                                                                               | <code>A bishop then must be blameless, the husband of one wife, vigilant, sober, of good behaviour, given to hospitality, apt to teach;</code>                                                                  |
+  | <code>And the chambers and the entries thereof were by the posts of the gates, where they washed the burnt offering.</code>         | <code>He made also ten lavers, and put five on the right hand, and five on the left, to wash in them: such things as they offered for the burnt offering they washed in them; but the sea was for the priests to wash in.</code> | <code>Hath oppressed the poor and needy, hath spoiled by violence, hath not restored the pledge, and hath lifted up his eyes to the idols, hath committed abomination,</code>                                   |
+* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "TripletDistanceMetric.COSINE",
+      "triplet_margin": 0.5
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `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`: None
+- `warmup_ratio`: None
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `enable_jit_checkpoint`: False
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `use_cpu`: False
+- `seed`: 42
+- `data_seed`: None
+- `bf16`: False
+- `fp16`: False
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: -1
+- `ddp_backend`: None
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `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
+- `group_by_length`: False
+- `length_column_name`: length
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `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
+- `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_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_num_input_tokens_seen`: no
+- `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`: True
+- `use_cache`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step  | Training Loss | intertextual-similarity-chirho_spearman_cosine |
+|:------:|:-----:|:-------------:|:----------------------------------------------:|
+| 0.1160 | 500   | 0.2996        | -                                              |
+| 0.2320 | 1000  | 0.2629        | 0.5336                                         |
+| 0.3480 | 1500  | 0.2529        | -                                              |
+| 0.4640 | 2000  | 0.2434        | 0.5641                                         |
+| 0.5800 | 2500  | 0.2356        | -                                              |
+| 0.6961 | 3000  | 0.2320        | 0.5828                                         |
+| 0.8121 | 3500  | 0.2271        | -                                              |
+| 0.9281 | 4000  | 0.2222        | 0.5963                                         |
+| 1.0    | 4310  | -             | 0.5989                                         |
+| 1.0441 | 4500  | 0.2153        | -                                              |
+| 1.1601 | 5000  | 0.2028        | 0.6041                                         |
+| 1.2761 | 5500  | 0.2025        | -                                              |
+| 1.3921 | 6000  | 0.2006        | 0.6104                                         |
+| 1.5081 | 6500  | 0.1972        | -                                              |
+| 1.6241 | 7000  | 0.1964        | 0.6161                                         |
+| 1.7401 | 7500  | 0.1965        | -                                              |
+| 1.8561 | 8000  | 0.1952        | 0.6213                                         |
+| 1.9722 | 8500  | 0.1935        | -                                              |
+| 2.0    | 8620  | -             | 0.6267                                         |
+| 2.0882 | 9000  | 0.1846        | 0.6282                                         |
+| 2.2042 | 9500  | 0.1783        | -                                              |
+| 2.3202 | 10000 | 0.1797        | 0.6268                                         |
+| 2.4362 | 10500 | 0.1817        | -                                              |
+| 2.5522 | 11000 | 0.1774        | 0.6317                                         |
+| 2.6682 | 11500 | 0.1776        | -                                              |
+| 2.7842 | 12000 | 0.1793        | 0.6325                                         |
+| 2.9002 | 12500 | 0.1758        | -                                              |
+| 3.0    | 12930 | -             | 0.6326                                         |
+
+
+### Framework Versions
+- Python: 3.14.2
+- Sentence Transformers: 5.2.2
+- Transformers: 5.1.0
+- PyTorch: 2.10.0
+- Accelerate: 1.12.0
+- Datasets: 4.5.0
+- Tokenizers: 0.22.2
+
+## 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.*
+-->

config.json

@@ -0,0 +1,30 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.1.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.2.2",
+    "transformers": "5.1.0",
+    "pytorch": "2.10.0"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

eval/similarity_evaluation_intertextual-similarity-chirho_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_pearson,cosine_spearman
+1.0,4310,0.5935413713788631,0.5989102790359944
+2.0,8620,0.6214343499469666,0.6266581668543718
+3.0,12930,0.6270927412432303,0.6326350413656476

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ab5480a3692be4ba43dc7fa5d4be7ffbf9b61a7413d6fe9a7d40ed43a2b2e8
+size 133462104

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"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 128,
+    "do_lower_case": false
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}