Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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
+}

README.md

@@ -0,0 +1,352 @@
+---
+base_model: intfloat/multilingual-e5-base
+datasets: []
+language:
+- vi
+- en
+library_name: sentence-transformers
+license: apache-2.0
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Bóng đá có lợi ích gì cho sức khỏe?
+  sentences:
+  - Bóng đá giúp cải thiện sức khỏe tim mạch và tăng cường sức bền.
+  - Bóng đá là môn thể thao phổ biến nhất thế giới.
+  - Bóng đá có thể giúp bạn kết nối với nhiều người hơn.
+
+model-index:
+- name: Halong Embedding
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.8294209702660407
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9233176838810642
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9436619718309859
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9687010954616588
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.8294209702660407
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3145539906103286
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1931142410015649
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09906103286384975
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8145539906103286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9178403755868545
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9389671361502347
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9640062597809077
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8976041381292648
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.879893558884169
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8763179130484675
+      name: Cosine Map@100
+
+---
+
+# Halong Embedding
+
+Halong Embedding is a Vietnamese text embedding focused on RAG and production efficiency:
+- 📚 Trained on a in house dataset consist of approximately 100,000 examples of question and related documents
+- 🪆 Trained with a Matryoshka loss, allowing you to truncate embeddings with minimal performance loss: smaller embeddings are faster to compare.
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base). 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:** [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) <!-- at revision d13f1b27baf31030b7fd040960d60d909913633f -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** vi-focused, multilingual
+- **License:** apache-2.0
+
+### 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': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (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
+import torch
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("hiieu/halong_embedding")
+
+# Define query and documents
+query = "Bóng đá có lợi ích gì cho sức khỏe?"
+docs = [
+    "Bóng đá giúp cải thiện sức khỏe tim mạch và tăng cường sức bền.",
+    "Bóng đá là môn thể thao phổ biến nhất thế giới.",
+    "Chơi bóng đá giúp giảm căng thẳng và cải thiện tâm lý.",
+    "Bóng đá có thể giúp bạn kết nối với nhiều người hơn.",
+    "Bóng đá không chỉ là môn thể thao mà còn là cách để giải trí."
+]
+
+# Encode query and documents
+query_embedding = model.encode([query])
+doc_embeddings = model.encode(docs)
+similarities = model.similarity(query_embedding, doc_embeddings).flatten()
+
+# Sort documents by cosine similarity
+sorted_indices = torch.argsort(similarities, descending=True)
+sorted_docs = [docs[idx] for idx in sorted_indices]
+sorted_scores = [similarities[idx].item() for idx in sorted_indices]
+
+# Print sorted documents with their cosine scores
+for doc, score in zip(sorted_docs, sorted_scores):
+    print(f"Document: {doc} - Cosine Similarity: {score:.4f}")
+
+# Document: Bóng đá giúp cải thiện sức khỏe tim mạch và tăng cường sức bền. - Cosine Similarity: 0.7318
+# Document: Chơi bóng đá giúp giảm căng thẳng và cải thiện tâm lý. - Cosine Similarity: 0.6623
+# Document: Bóng đá không chỉ là môn thể thao mà còn là cách để giải trí. - Cosine Similarity: 0.6102
+# Document: Bóng đá có thể giúp bạn kết nối với nhiều người hơn. - Cosine Similarity: 0.4988
+# Document: Bóng đá là môn thể thao phổ biến nhất thế giới. - Cosine Similarity: 0.4828
+```
+
+### Matryoshka Embeddings Inference
+```python
+from sentence_transformers import SentenceTransformer
+import torch.nn.functional as F
+import torch
+
+matryoshka_dim = 64
+model = SentenceTransformer(
+    "hiieu/halong_embedding",
+    truncate_dim=matryoshka_dim,
+)
+
+# Define query and documents
+query = "Bóng đá có lợi ích gì cho sức khỏe?"
+docs = [
+    "Bóng đá giúp cải thiện sức khỏe tim mạch và tăng cường sức bền.",
+    "Bóng đá là môn thể thao phổ biến nhất thế giới.",
+    "Chơi bóng đá giúp giảm căng thẳng và cải thiện tâm lý.",
+    "Bóng đá có thể giúp bạn kết nối với nhiều người hơn.",
+    "Bóng đá không chỉ là môn thể thao mà còn là cách để giải trí."
+]
+
+# Encode query and documents
+query_embedding = model.encode([query])
+doc_embeddings = model.encode(docs)
+similarities = model.similarity(query_embedding, doc_embeddings).flatten()
+
+# Sort documents by cosine similarity
+sorted_indices = torch.argsort(similarities, descending=True)
+sorted_docs = [docs[idx] for idx in sorted_indices]
+sorted_scores = [similarities[idx].item() for idx in sorted_indices]
+
+# Print sorted documents with their cosine scores
+for doc, score in zip(sorted_docs, sorted_scores):
+    print(f"Document: {doc} - Cosine Similarity: {score:.4f}")
+
+# Document: Bóng đá giúp cải thiện sức khỏe tim mạch và tăng cường sức bền. - Cosine Similarity: 0.8045
+# Document: Chơi bóng đá giúp giảm căng thẳng và cải thiện tâm lý. - Cosine Similarity: 0.7676
+# Document: Bóng đá không chỉ là môn thể thao mà còn là cách để giải trí. - Cosine Similarity: 0.6758
+# Document: Bóng đá có thể giúp bạn kết nối với nhiều người hơn. - Cosine Similarity: 0.5931
+# Document: Bóng đá là môn thể thao phổ biến nhất thế giới. - Cosine Similarity: 0.5105
+```
+<!--
+### 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
+
+#### Information Retrieval
+* Dataset: [Zalo legal retrieval dataet](https://huggingface.co/datasets/hiieu/legal_eval_label)
+* *note*: We sampled 20% of the Zalo Legal train dataset for fast testing; our model did not train on this dataset.
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Model                | Accuracy@1 | Accuracy@3 | Accuracy@5 | Accuracy@10 | Precision@1 | Precision@3 | Precision@5 | Precision@10 | Recall@1 | Recall@3 | Recall@5 | Recall@10 | NDCG@10 | MRR@10 | MAP@100 |
+|----------------------|------------|------------|------------|-------------|-------------|--------------|--------------|---------------|-----------|-----------|-----------|------------|---------|--------|---------|
+| 
+vietnamese-bi-encoder            | 0.8169     | 0.9108     | 0.9437     | 0.9640      | 0.8169      | 0.3099       | 0.1931       | 0.0987        | 0.8020    | 0.9045    | 0.9390    | 0.9601     | 0.8882  | 0.8685 | 0.8652  |
+| sup-SimCSE-VietNamese-phobert-base            | 0.5540     | 0.7308     | 0.7981     | 0.8748      | 0.5540      | 0.2473       | 0.1621       | 0.0892        | 0.5446    | 0.7246    | 0.7903    | 0.8693     | 0.7068  | 0.6587 | 0.6592  |
+| halong_embedding (768)         | 0.8294     | 0.9233     | 0.9437     | 0.9687      | 0.8294      | 0.3146       | 0.1931       | 0.0991        | 0.8146    | 0.9178    | 0.9390    | 0.9640     | 0.8976  | 0.8799 | 0.8763  |
+| halong_embedding (512)         | 0.8138     | 0.9233     | 0.9390     | 0.9703      | 0.8138      | 0.3146       | 0.1922       | 0.0992        | 0.7989    | 0.9178    | 0.9343    | 0.9656     | 0.8917  | 0.8715 | 0.8678  |
+| halong_embedding (256)         | 0.7934     | 0.8967     | 0.9280     | 0.9593      | 0.7934      | 0.3062       | 0.1900       | 0.0981        | 0.7786    | 0.8920    | 0.9233    | 0.9546     | 0.8743  | 0.8520 | 0.8489  |
+| halong_embedding (128)         | 0.7840     | 0.8951     | 0.9264     | 0.9515      | 0.7840      | 0.3046       | 0.1894       | 0.0975        | 0.7707    | 0.8889    | 0.9210    | 0.9476     | 0.8669  | 0.8439 | 0.8412  |
+| halong_embedding (64)          | 0.6980     | 0.8435     | 0.8920     | 0.9358      | 0.6980      | 0.2864       | 0.1815       | 0.0958        | 0.6854    | 0.8365    | 0.8842    | 0.9311     | 0.8145  | 0.7805 | 0.7775  |
+
+
+<!--
+## 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.*
+-->
+
+
+## Citation
+
+You can cite our work as below:
+
+```Plaintext
+@misc{HalongEmbedding,
+  title={HalongEmbedding: A Vietnamese Text Embedding},
+  author={Ngo Hieu},
+  year={2024},
+  publisher={Huggingface},
+}
+```
+
+
+### 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@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}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@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.*
+-->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "hiieu/halong_embedding",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.45.2",
+    "pytorch": "2.3.1+cpu"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fd083778d8b1f54d7ad106d1e279b5e0f6f2f9f71ae095cf91107b6e54131ab
+size 1112197096

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": 512,
+  "do_lower_case": false
+}

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}