Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,36 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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": 1024,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
+    "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/config.json

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

LICENSE

@@ -0,0 +1,59 @@
+Creative Commons Attribution-NonCommercial 4.0 International License
+
+Copyright (c) 2025
+
+This work is licensed under the Creative Commons Attribution-NonCommercial 4.0
+International License. To view a copy of this license, visit
+http://creativecommons.org/licenses/by-nc/4.0/ or send a letter to
+Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.
+
+You are free to:
+- Share — copy and redistribute the material in any medium or format
+- Adapt — remix, transform, and build upon the material
+
+Under the following terms:
+- Attribution — You must give appropriate credit, provide a link to the license,
+  and indicate if changes were made. You may do so in any reasonable manner, but
+  not in any way that suggests the licensor endorses you or your use.
+- NonCommercial — You may not use the material for commercial purposes.
+- No additional restrictions — You may not apply legal terms or technological
+  measures that legally restrict others from doing anything the license permits.
+
+---
+
+## Acknowledgments
+
+This model builds upon several foundational works and contributions:
+
+### Base Architecture
+- **XLM-RoBERTa**: This model uses XLM-RoBERTa as its base architecture
+- Original paper: "Unsupervised Cross-lingual Representation Learning at Scale"
+- Authors: Conneau et al.
+- License: MIT License
+
+### Training Methodology
+We are grateful to the Beijing Academy of Artificial Intelligence (BAAI) for their
+contributions to embedding research:
+
+- **RetroMAE**: Self-supervised pre-training methodology
+  - Paper: "RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder"
+  - Authors: BAAI
+  - arXiv: https://arxiv.org/abs/2205.12035
+
+- **BGE-M3**: Multi-lingual embedding research
+  - Paper: "BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings"
+  - Authors: BAAI
+  - arXiv: https://arxiv.org/abs/2402.03216
+
+### Matryoshka Representation Learning
+- Paper: "Matryoshka Representation Learning"
+- Authors: Kusupati et al.
+- Year: 2022
+- arXiv: https://arxiv.org/abs/2205.13147
+
+### Training Framework
+- Sentence Transformers: https://www.sbert.net
+- License: Apache 2.0
+
+Users are encouraged to cite this model and the foundational works when using
+it in research or applications.

README.md

@@ -1,3 +1,439 @@
 ---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- matryoshka
+- multilingual
+- embeddings
+- xlm-roberta
+language:
+- multilingual
+- en
+- ar
+- de
+- es
+- fr
+- zh
+- ru
+- tr
+- ko
+- ja
+- it
+- pt
+- nl
 license: cc-by-nc-4.0
+base_model: xlm-roberta-base
+metrics:
+- cosine_accuracy
+- cosine_precision
+- cosine_recall
+- cosine_f1
+- cosine_ap
+- dot_accuracy
+- dot_precision
+- dot_recall
+- dot_f1
+- dot_ap
+- manhattan_accuracy
+- manhattan_precision
+- manhattan_recall
+- manhattan_f1
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_precision
+- euclidean_recall
+- euclidean_f1
+- euclidean_ap
+model-index:
+- name: Matryoshka Text Embedding v1
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: SciFact
+      type: scifact
+      config: default
+      split: test
+      revision: d56462d0e63a25450459c4f213e49ffdb866f7f9
+    metrics:
+    - type: ndcg_at_10
+      value: 0.63084
+      name: NDCG@10
+    - type: ndcg_at_1
+      value: 0.51
+      name: NDCG@1
+    - type: ndcg_at_3
+      value: 0.578
+      name: NDCG@3
+    - type: ndcg_at_5
+      value: 0.60648
+      name: NDCG@5
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STSBenchmark
+      type: stsbenchmark
+      config: default
+      split: test
+      revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
+    metrics:
+    - type: spearman
+      value: 0.850616
+      name: Spearman
+    - type: pearson
+      value: 0.838067
+      name: Pearson
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STS17
+      type: sts17-crosslingual-sts
+      config: en-en
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: spearman
+      value: 0.873981
+      name: Spearman (en-en)
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STS17
+      type: sts17-crosslingual-sts
+      config: es-es
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: spearman
+      value: 0.88079
+      name: Spearman (es-es)
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STS17
+      type: sts17-crosslingual-sts
+      config: ko-ko
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: spearman
+      value: 0.821019
+      name: Spearman (ko-ko)
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STS17
+      type: sts17-crosslingual-sts
+      config: ar-ar
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: spearman
+      value: 0.805643
+      name: Spearman (ar-ar)
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STS17
+      type: sts17-crosslingual-sts
+      config: en-de
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: spearman
+      value: 0.824516
+      name: Spearman (en-de)
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STS17
+      type: sts17-crosslingual-sts
+      config: nl-en
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: spearman
+      value: 0.819011
+      name: Spearman (nl-en)
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STS17
+      type: sts17-crosslingual-sts
+      config: it-en
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: spearman
+      value: 0.815176
+      name: Spearman (it-en)
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STS17
+      type: sts17-crosslingual-sts
+      config: fr-en
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: spearman
+      value: 0.815679
+      name: Spearman (fr-en)
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STS17
+      type: sts17-crosslingual-sts
+      config: en-tr
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: spearman
+      value: 0.748444
+      name: Spearman (en-tr)
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STS17
+      type: sts17-crosslingual-sts
+      config: es-en
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: spearman
+      value: 0.766019
+      name: Spearman (es-en)
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: STS17
+      type: sts17-crosslingual-sts
+      config: en-ar
+      split: test
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+    metrics:
+    - type: spearman
+      value: 0.71912
+      name: Spearman (en-ar)
 ---
+
+# Matryoshka Text Embedding v1
+
+A multilingual text embedding model with Matryoshka Representation Learning, allowing flexible embedding dimensions from 64D to 1024D.
+
+## Model Overview
+
+This model implements Matryoshka Representation Learning, enabling you to truncate embeddings to different dimensions while maintaining good performance. This allows you to balance accuracy, speed, and storage based on your specific needs.
+
+### Key Features
+
+- **Flexible Dimensions**: Choose from 7 different embedding sizes (64D, 128D, 256D, 384D, 512D, 768D, 1024D)
+- **Multilingual Support**: Trained on 100+ languages
+- **Base Architecture**: XLM-RoBERTa
+- **Max Sequence Length**: 8192 tokens
+
+## Quick Start
+
+### Installation
+
+```python
+pip install sentence-transformers
+```
+
+### Basic Usage
+
+```python
+from sentence_transformers import SentenceTransformer
+
+# Load model
+model = SentenceTransformer('matryoshka-text-embedding-v1')
+
+# Full precision (1024D)
+embeddings = model.encode(["Your text here"])
+
+# Balanced mode (512D) - Recommended for most use cases
+embeddings = model.encode(["Your text here"], truncate_dim=512)
+
+# Fast mode (256D) - For high-throughput applications
+embeddings = model.encode(["Your text here"], truncate_dim=256)
+
+# Ultra-fast mode (128D) - For real-time applications
+embeddings = model.encode(["Your text here"], truncate_dim=128)
+```
+
+## Performance Benchmarks
+
+### SciFact (Scientific Document Retrieval)
+
+| Dimension | NDCG@10 | Relative Performance |
+|-----------|---------|---------------------|
+| **1024D** | 0.6308 | 100.0% |
+| **768D** | 0.6277 | 99.5% |
+| **512D** | 0.6114 | 96.9% |
+| **384D** | 0.6035 | 95.7% |
+| **256D** | 0.5614 | 89.0% |
+| **128D** | 0.4732 | 75.0% |
+| **64D** | 0.3317 | 52.6% |
+
+### STSBenchmark (English Semantic Similarity)
+
+- **Spearman**: 0.8506 (1024D)
+- **Pearson**: 0.8381 (1024D)
+
+### STS17 (Multilingual Semantic Similarity)
+
+**Average Spearman Correlation across languages: 0.8096**
+
+Performance by language pair (1024D):
+- Spanish (es-es): 0.8808
+- English (en-en): 0.8740
+- German (en-de): 0.8245
+- Korean (ko-ko): 0.8210
+- French (fr-en): 0.8157
+- Italian (it-en): 0.8152
+- Dutch (nl-en): 0.8190
+- Arabic (ar-ar): 0.8056
+- Turkish (en-tr): 0.7484
+- Spanish-English (es-en): 0.7660
+- English-Arabic (en-ar): 0.7191
+
+## Use Cases
+
+### High Accuracy Applications (768D-1024D)
+- Scientific literature search
+- Legal document retrieval
+- Medical information systems
+
+### Balanced Production (512D) - Recommended
+- General web search
+- E-commerce product search
+- Content recommendation engines
+- Knowledge base retrieval
+
+### High-Throughput Systems (256D-384D)
+- Real-time search APIs
+- Large-scale document indexing
+- Social media search
+
+### Mobile & Edge Devices (64D-128D)
+- Mobile applications
+- IoT devices
+- Browser-based search
+- Resource-constrained environments
+
+## Advanced Usage
+
+### Semantic Search
+
+```python
+import numpy as np
+from sentence_transformers import util
+
+# Index documents with 512D (optimal balance)
+documents = [
+    "Artificial intelligence is transforming healthcare.",
+    "Machine learning models require large datasets.",
+    "Quantum computing promises exponential speedups."
+]
+
+doc_embeddings = model.encode(documents, truncate_dim=512)
+
+# Search with same dimension
+query = "How is AI used in medicine?"
+query_embedding = model.encode(query, truncate_dim=512)
+
+# Compute similarities
+similarities = util.cos_sim(query_embedding, doc_embeddings)
+top_result = np.argmax(similarities)
+
+print(f"Most relevant: {documents[top_result]}")
+```
+
+### Integration with FAISS
+
+```python
+import faiss
+import numpy as np
+
+# Create embeddings with 512D
+embeddings = model.encode(documents, truncate_dim=512)
+embeddings = embeddings.astype('float32')
+
+# Build FAISS index
+dimension = 512
+index = faiss.IndexFlatIP(dimension)
+faiss.normalize_L2(embeddings)
+index.add(embeddings)
+
+# Search
+query_embedding = model.encode(query, truncate_dim=512).astype('float32')
+faiss.normalize_L2(query_embedding.reshape(1, -1))
+distances, indices = index.search(query_embedding.reshape(1, -1), k=10)
+```
+
+## Technical Details
+
+### Architecture
+- **Base**: XLM-RoBERTa transformer encoder
+- **Embedding Dimensions**: 1024 (full) with 7 supported truncation levels
+- **Max Sequence Length**: 8192 tokens
+- **Vocabulary Size**: 250,002 tokens
+- **Parameters**: ~568M
+
+### Training
+- **Technique**: Matryoshka Representation Learning
+- **Languages**: 100+ languages
+- **Max Input Length**: 8192 tokens
+
+## Model Files
+
+- `pytorch_model.bin` - Model weights
+- `config.json` - Model configuration
+- `tokenizer.json` - Tokenizer configuration
+- `lumees_config.json` - Matryoshka-specific configuration
+
+## License
+
+This model is released under the **CC-BY-NC-4.0** (Creative Commons Attribution-NonCommercial 4.0 International) license.
+
+See the [LICENSE](LICENSE) file for full details and acknowledgments.
+
+## Acknowledgments
+
+This model builds upon important foundational work:
+
+- **XLM-RoBERTa**: Base architecture for multilingual representations
+- **BAAI**: For their contributions through RetroMAE and BGE-M3 papers
+- **Matryoshka Representation Learning**: Training methodology (Kusupati et al., 2022)
+
+## Citation
+
+If you use this model in your research or application, please cite:
+
+```bibtex
+@misc{matryoshka-text-embedding-v1,
+  title={Matryoshka Text Embedding v1},
+  author={Hasan Kurşun and Kerem Berkay Yanık},
+  year={2025},
+  url={https://huggingface.co/matryoshka-text-embedding-v1},
+  organization={Lumees},
+  contact={[email protected]},
+  website={https://lumees.io}
+}
+```

README_HF.md

@@ -0,0 +1,89 @@
+---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- matryoshka
+- multilingual
+- embeddings
+language:
+- multilingual
+- en
+- ar
+- de
+- es
+- fr
+- zh
+- ru
+- tr
+- ko
+- ja
+license: cc-by-nc-4.0
+base_model: xlm-roberta-base
+---
+
+# Matryoshka Text Embedding v1
+
+**Matryoshka Embedding Model with Flexible Dimensions**
+
+This is a [sentence-transformers](https://www.SBERT.net) model with Matryoshka Representation Learning,
+allowing flexible dimension truncation from 64D to 1024D.
+
+## Model Details
+
+- **Model Type**: Sentence Transformer with Matryoshka Representation Learning
+- **Base Architecture**: XLM-RoBERTa
+- **Dimensions**: 64, 128, 256, 384, 512, 768, 1024
+- **Max Sequence Length**: 8192 tokens
+- **Languages**: 100+ languages
+- **Output Dimensionality**: 1024 (with 7 truncation options)
+
+## Usage
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer('matryoshka-text-embedding-v1')
+
+# Full precision
+embeddings = model.encode(["Hello World"])
+
+# Optimized for production (recommended)
+embeddings = model.encode(["Hello World"], truncate_dim=512)
+```
+
+See [README.md](README.md) for detailed documentation.
+
+## Performance (Self-Reported)
+
+| Task | Metric | Score |
+|------|--------|-------|
+| SciFact | NDCG@10 | 0.6308 |
+| STS17 | Spearman | 0.8096 |
+| STSBenchmark | Spearman | 0.8506 |
+
+## License
+
+CC-BY-NC-4.0 - See LICENSE file for details and acknowledgments.
+
+## Acknowledgments
+
+This model builds upon:
+- **XLM-RoBERTa**: Base architecture
+- **BAAI**: RetroMAE and BGE-M3 research contributions
+- **Matryoshka Representation Learning**: Training methodology
+
+## Citation
+
+```bibtex
+@misc{matryoshka-text-embedding-v1,
+  title={Matryoshka Text Embedding v1},
+  author={Hasan Kurşun and Kerem Berkay Yanık},
+  year={2025},
+  url={https://huggingface.co/matryoshka-text-embedding-v1},
+  organization={Lumees},
+  contact={[email protected]},
+  website={https://lumees.io}
+}
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.57.1",
+    "pytorch": "2.6.0+cu124"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

lumees_config.json

@@ -0,0 +1,18 @@
+{
+  "model_name": "matryoshka-text-embedding-v1",
+  "model_type": "matryoshka",
+  "version": "1.0.0",
+  "matryoshka_dimensions": [
+    64,
+    128,
+    256,
+    384,
+    512,
+    768,
+    1024
+  ],
+  "default_dimension": 1024,
+  "embedding_dimension": 1024,
+  "max_sequence_length": 8192,
+  "is_matryoshka": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58aa06c15337c73f189f161594b536c74a4be096df6143864e09c9e853676bb0
+size 2271064456

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": 8192,
+    "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:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
+size 17083053

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 8192,
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}