Duplicate from slovak-nlp/e5-sk-large

Co-authored-by: Marek Suppa <mrshu@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.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

1_Pooling/config.json

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

README.md

@@ -0,0 +1,424 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:137745
+- loss:CosineSimilarityLoss
+- loss:MultipleNegativesRankingLoss
+base_model:
+- intfloat/multilingual-e5-large
+widget:
+- source_sentence: Mor a epidémia sa očividne vymkli spod kontroly .
+  sentences:
+  - Choroba bola nekontrolovateľná a ohrozovala všetok život .
+  - Tieto vylúčenia sú určené na iné cieľové skupiny ako obchodné štvrte .
+  - >-
+    Autobus National Trust Tour odchádza každý deň o 9:00 z National Trust
+    Information Centre .
+- source_sentence: Bombové útoky v Iraku zabili najmenej 26 ľudí
+  sentences:
+  - Nová sláva pre Čínu v snahe o obnovu
+  - Samovražedný útočník v Iraku zabil najmenej 12 ľudí
+  - Muž lúpe banán.
+- source_sentence: Chlapec a dievča tancujú v daždi.
+  sentences:
+  - Turecko sa snaží premiestniť časť sýrskych utečencov
+  - Záber zblízka na bielu ovcu s čiernou hlavou.
+  - Muž a žena tancujú v daždi.
+- source_sentence: Niekedy fantazírujem o tom, že mám moc.
+  sentences:
+  - Egyptského Mursího čaká súd za útek z väzenia
+  - >-
+    Aj ja niekedy fantazírujem o tom, ako ohýbam ľudí pred svojou dementnou
+    vôľou.
+  - Niekto lúpe banán.
+- source_sentence: >-
+    Vidiecke mydlo „Emmerdale“ vo štvrtok sledovalo 8,3 milióna ľudí, zatiaľ čo
+    živá epizóda „The Bill“ mala 7,9 milióna divákov.
+  sentences:
+  - >-
+    Hodinové špeciálne epizódy seriálov ITV „Emmerdale“ a „The Bill“ boli
+    najlepšie hodnotené britské televízne programy pri príležitosti 50. výročia
+    komerčného kanála.
+  - 4. mája 88 bolo unesených niekoľko honorárnych konzulov.
+  - >-
+    Existujú spoločnosti, ktoré majú rozdelené riadenie procesov výskumu a
+    vývoja.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- cosine_mcc
+- validation_sts_pearson_cosine
+- validation_sts_spearman_cosine
+- validation_nli_cosine_accuracy
+- validation_nli_cosine_accuracy_threshold
+- validation_nli_cosine_f1
+- validation_nli_cosine_f1_threshold
+- validation_nli_cosine_precision
+- validation_nli_cosine_recall
+- validation_nli_cosine_ap
+- validation_nli_cosine_mcc
+- validation_rte_cosine_accuracy
+- validation_rte_cosine_accuracy_threshold
+- validation_rte_cosine_f1
+- validation_rte_cosine_f1_threshold
+- validation_rte_cosine_precision
+- validation_rte_cosine_recall
+- validation_rte_cosine_ap
+- validation_rte_cosine_mcc
+- validation_dev_overall
+model-index:
+- name: E5-sk-large
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: validation sts
+      type: validation_sts
+    metrics:
+    - type: pearson_cosine
+      value: 0.8404018187290129
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8424145819561701
+      name: Spearman Cosine
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: validation nli
+      type: validation_nli
+    metrics:
+    - type: cosine_accuracy
+      value: 0.6662650602409639
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.9897347688674927
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.49969824984912486
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7573917508125305
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.3333333333333333
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9975903614457832
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.2791130922755554
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0
+      name: Cosine Mcc
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: validation rte
+      type: validation_rte
+    metrics:
+    - type: cosine_accuracy
+      value: 0.5234657039711191
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.9790897369384766
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.645320197044335
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7796555757522583
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.4763636363636364
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 1
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.37950776315755064
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.08078074811027249
+      name: Cosine Mcc
+  - task:
+      type: multi-task-dev
+      name: Multi Task Dev
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: validation_sts_pearson_cosine
+      value: 0.8404018187290129
+      name: Validation Sts Pearson Cosine
+    - type: validation_sts_spearman_cosine
+      value: 0.8424145819561701
+      name: Validation Sts Spearman Cosine
+    - type: validation_nli_cosine_accuracy
+      value: 0.6662650602409639
+      name: Validation Nli Cosine Accuracy
+    - type: validation_nli_cosine_accuracy_threshold
+      value: 0.9897347688674927
+      name: Validation Nli Cosine Accuracy Threshold
+    - type: validation_nli_cosine_f1
+      value: 0.49969824984912486
+      name: Validation Nli Cosine F1
+    - type: validation_nli_cosine_f1_threshold
+      value: 0.7573917508125305
+      name: Validation Nli Cosine F1 Threshold
+    - type: validation_nli_cosine_precision
+      value: 0.3333333333333333
+      name: Validation Nli Cosine Precision
+    - type: validation_nli_cosine_recall
+      value: 0.9975903614457832
+      name: Validation Nli Cosine Recall
+    - type: validation_nli_cosine_ap
+      value: 0.2791130922755554
+      name: Validation Nli Cosine Ap
+    - type: validation_nli_cosine_mcc
+      value: 0
+      name: Validation Nli Cosine Mcc
+    - type: validation_rte_cosine_accuracy
+      value: 0.5234657039711191
+      name: Validation Rte Cosine Accuracy
+    - type: validation_rte_cosine_accuracy_threshold
+      value: 0.9790897369384766
+      name: Validation Rte Cosine Accuracy Threshold
+    - type: validation_rte_cosine_f1
+      value: 0.645320197044335
+      name: Validation Rte Cosine F1
+    - type: validation_rte_cosine_f1_threshold
+      value: 0.7796555757522583
+      name: Validation Rte Cosine F1 Threshold
+    - type: validation_rte_cosine_precision
+      value: 0.4763636363636364
+      name: Validation Rte Cosine Precision
+    - type: validation_rte_cosine_recall
+      value: 1
+      name: Validation Rte Cosine Recall
+    - type: validation_rte_cosine_ap
+      value: 0.37950776315755064
+      name: Validation Rte Cosine Ap
+    - type: validation_rte_cosine_mcc
+      value: 0.08078074811027249
+      name: Validation Rte Cosine Mcc
+    - type: validation_dev_overall
+      value: 0.5003451457964254
+      name: Validation Dev Overall
+license: mit
+datasets:
+- slovak-nlp/sklep
+language:
+- sk
+---
+
+# e5-sk-large
+
+**e5-sk-large** is a Slovak text embedding model (365M parameters, 1024-dimensional embeddings) built by applying vocabulary trimming and fine-tuning to [multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large). It achieves competitive performance with proprietary embedding APIs on [SkMTEB](https://huggingface.co/collections/slovak-nlp/skmteb) — the first comprehensive Slovak text embedding benchmark — while being 35% smaller than the original model and fully locally deployable.
+
+Released as part of the **SkMTEB** project ([paper](https://arxiv.org/abs/2606.13647) · [GitHub](https://github.com/slovak-nlp/skmteb) · [collection](https://huggingface.co/collections/slovak-nlp/skmteb)).
+ 
+For a smaller, faster variant, see [e5-sk-small](https://huggingface.co/slovak-nlp/e5-sk-small) (45M parameters).
+
+---
+
+## Model Details
+
+| | |
+|---|---|
+| **Base model** | [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) |
+| **Parameters** | 365M (vs. 560M original — 35% reduction) |
+| **Embedding dimension** | 1024 |
+| **Max sequence length** | 256 tokens |
+| **Pooling** | Mean pooling |
+| **Languages** | Slovak (primary); Slovak–English and Slovak–Czech cross-lingual tasks preserved |
+
+## Usage
+
+This model follows the standard E5 prefix convention: prepend `query:` to queries and `passage:` to documents during retrieval. For symmetric tasks (STS, clustering, classification), no prefix is needed.
+
+### With `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
+ 
+model = SentenceTransformer("slovak-nlp/e5-sk-large")
+ 
+# Retrieval
+query_embedding = model.encode("query: Čo je hlavné mesto Slovenska?")
+passage_embedding = model.encode("passage: Bratislava je hlavné a najväčšie mesto Slovenska.")
+similarity = model.similarity(query_embedding, passage_embedding)
+print(similarity)  # tensor([[0.9269]])
+ 
+# Batch encoding
+sentences = [
+    "query: Aké je počasie v Bratislave?",
+    "passage: V Bratislave je dnes slnečno a teplo.",
+    "passage: Bratislava leží na brehu Dunaja.",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)  # (3, 1024)
+```
+
+### With `transformers` directly
+ 
+```python
+import torch
+import torch.nn.functional as F
+from transformers import AutoTokenizer, AutoModel
+ 
+def average_pool(last_hidden_states, attention_mask):
+    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
+    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
+ 
+tokenizer = AutoTokenizer.from_pretrained("slovak-nlp/e5-sk-large")
+model = AutoModel.from_pretrained("slovak-nlp/e5-sk-large")
+ 
+texts = [
+    "query: Čo je hlavné mesto Slovenska?",
+    "passage: Bratislava je hlavné a najväčšie mesto Slovenska.",
+]
+ 
+batch_dict = tokenizer(texts, max_length=512, padding=True, truncation=True, return_tensors="pt")
+with torch.no_grad():
+    outputs = model(**batch_dict)
+ 
+embeddings = average_pool(outputs.last_hidden_state, batch_dict["attention_mask"])
+embeddings = F.normalize(embeddings, p=2, dim=1)
+print((embeddings[0] @ embeddings[1]).item())
+```
+ 
+### Prefix guide
+ 
+| Task | Input prefix |
+|---|---|
+| Search / retrieval query | `query: ` |
+| Document / passage to index | `passage: ` |
+| STS, clustering, classification | *(no prefix)* |
+
+---
+
+## Training
+ 
+### How it was built
+
+**Step 1 — Vocabulary Trimming.** Before fine-tuning, [Vocabulary Trimming](https://aclanthology.org/2023.findings-emnlp.1029/) (Ushio et al., 2023) was applied to `multilingual-e5-large` to remove tokens irrelevant to Slovak.
+Token frequencies were computed on [FineWeb2-Slovak](https://huggingface.co/datasets/ivykopal/fineweb2-slovak), a quality-filtered Slovak web corpus, and the top 60K tokens (out of 250K) were retained. This reduced the model from 560M to **365M parameters** (35% reduction) without meaningful performance loss.
+  
+**Step 2 — Fine-tuning.** The trimmed model was fine-tuned on curated Slovak datasets from the [skLEP benchmark](https://huggingface.co/slovak-nlp/sklep):
+
+| Dataset | Task | Pairs |
+|---|---|---|
+| SK-SQuAD | Question–context retrieval | ~72K |
+| Slovak NLI (from XNLI) | Entailment | ~393K |
+| Slovak STS (from GLUE STSb) | Similarity scoring | ~6K |
+| Slovak RTE (from GLUE) | Textual entailment | ~2.5K |
+ 
+### Training configuration
+ 
+| Hyperparameter | Value |
+|---|---|
+| Pooling | Mean pooling |
+| Max sequence length | 256 tokens |
+| Batch size | 32 |
+| Learning rate | 2 × 10⁻⁵ |
+| LR scheduler | Linear with 10% warmup |
+| Epochs | 3 |
+| Loss (STS) | Cosine Similarity Loss |
+| Loss (other) | Multiple Negatives Ranking Loss |
+| Hardware | 1× NVIDIA H100 (~50 min) |
+| Seed | 42 |
+ 
+---
+ 
+## Evaluation: SkMTEB Results
+ 
+Evaluated on [SkMTEB](https://huggingface.co/collections/slovak-nlp/skmteb) — 31 datasets across 7 task types. Scores are percentages (higher is better).
+ 
+| Model | Params | **All** | Bitext | Classif. | Clustering | Pair Clf. | Reranking | Retrieval | STS |
+|---|---|---|---|---|---|---|---|---|---|
+| **e5-sk-large** | **365M** | **74.70** | 96.39 | 66.34 | 41.43 | 67.32 | 87.81 | 85.60 | 86.25 |
+| multilingual-e5-large | 560M | 74.25 | 96.29 | 65.34 | 40.35 | 66.78 | 87.96 | 85.80 | 85.90 |
+| text-embedding-3-large (API) | — | 75.07 | 96.79 | 66.91 | 44.22 | 66.58 | 86.96 | 85.55 | 84.21 |
+| multilingual-e5-large-instruct | 560M | 77.49 | 97.09 | 70.28 | 49.69 | 70.55 | 86.49 | 86.08 | 88.86 |
+| e5-sk-small (ours) | 45M | 70.56 | 91.34 | 60.84 | 40.95 | 66.05 | 84.94 | 78.64 | 81.32 |
+ 
+**e5-sk-large is practically equivalent to `text-embedding-3-large`** (TOST equivalence test: 90% CI within ±2 points), while being open-weight, locally deployable, and free to run. Cross-lingual Slovak–English and Slovak–Czech bitext mining performance is preserved within 1 F1 point compared to the original `multilingual-e5-large`.
+
+ <!---
+### Running the full SkMTEB evaluation
+ 
+```bash
+pip install mteb
+mteb run -m slovak-nlp/e5-sk-large -b "MTEB(slk, v1)"
+```
+-->
+---
+ 
+## Intended Uses
+ 
+- Semantic search and retrieval-augmented generation (RAG) over Slovak text
+- Semantic textual similarity (STS)
+- Text clustering and classification via embedding features
+- Cross-lingual retrieval (Slovak–English, Slovak–Czech)
+- Local deployment where API latency or cost is a concern
+
+## Limitations
+ 
+- Optimised for Slovak; cross-lingual transfer to non-Slavic languages is not evaluated.
+- Vocabulary trimming removes non-Slovak tokens; performance on heavily code-mixed text may be reduced.
+- Training data skews toward news, parliamentary, and encyclopedic domains.
+- Max sequence length during fine-tuning is 256 tokens (underlying architecture supports up to 512).
+---
+ 
+## Citation
+ 
+```bibtex
+@inproceedings{suppa2025skmteb,
+  title     = {{SkMTEB}: {Slovak} Massive Text Embedding Benchmark and Model Adaptation},
+  author    = {{\v{S}}uppa, Marek and Ridzik, Andrej and Hl{\'a}dek, Daniel and
+               Kna{\v{z}}ekov{\'a}, Nat{\'a}lia and Ondrejov{\'a}, Vikt{\'o}ria},
+  year      = {2025},
+  eprint    = {2606.13647},
+  archivePrefix = {arXiv},
+  url       = {https://arxiv.org/abs/2606.13647}
+}
+ 
+@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},
+  year      = {2019},
+  publisher = {Association for Computational Linguistics},
+  url       = {https://arxiv.org/abs/1908.10084}
+}
+```
+ 
+---
+ 
+## License
+ 
+MIT

config.json

@@ -0,0 +1,48 @@
+{
+  "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": 514,
+  "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": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 60002,
+  "vocabtrimmer": {
+    "mining_config": {
+      "dataset": "ivykopal/fineweb2-slovak",
+      "dataset_column": "text",
+      "dataset_name": null,
+      "dataset_split": "test",
+      "language": "sk",
+      "min_frequency": 1,
+      "target_vocab_size": 60000
+    },
+    "stats": {
+      "compression_rate_embedding": 24.00060799513604,
+      "compression_rate_full": 65.25034383870307,
+      "parameter_size_embedding/raw": 256002048,
+      "parameter_size_embedding/trimmed": 61442048,
+      "parameter_size_full/raw": 559890432,
+      "parameter_size_full/trimmed": 365330432,
+      "vocab_size/raw": 250002,
+      "vocab_size/trimmed": 60002
+    }
+  }
+}

config_sentence_transformers.json

@@ -0,0 +1,19 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.2.0",
+    "transformers": "4.57.3",
+    "pytorch": "2.9.1+cu128"
+  },
+  "prompts": {
+    "query": "query: ",
+    "document": "passage: ",
+    "passage": "passage: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine",
+  "model_metadata": {
+    "num_parameters": 365330432,
+    "sentence_embedding_dimension": 1024
+  }
+}

eval/binary_classification_evaluation_validation_nli_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
+1.0,60,0.6662650602409639,0.4996986136226642,0.33319935691318325,0.9987951807228915,0.27417349840077787,-0.010024086747057818
+2.0,120,0.6662650602409639,0.4995480566435673,0.33306548814785053,0.9987951807228915,0.2742709130439137,-0.028346702743853168
+3.0,180,0.6662650602409639,0.4995480566435673,0.33306548814785053,0.9987951807228915,0.2727233647368423,-0.028346702743853168

eval/binary_classification_evaluation_validation_rte_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
+1.0,60,0.5234657039711191,0.6437346437346437,0.4746376811594203,1.0,0.36661099711724937,0.05701704150199188
+2.0,120,0.5234657039711191,0.6403940886699507,0.4727272727272727,0.9923664122137404,0.3703334021795854,-0.004624851991046135
+3.0,180,0.5234657039711191,0.6388206388206388,0.47101449275362317,0.9923664122137404,0.37631002414169196,-0.06354571037626576

eval/similarity_evaluation_validation_sts_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_pearson,cosine_spearman
+1.0,60,0.849383323789822,0.8493512123940523
+2.0,120,0.8426812159736894,0.8380053359945728
+3.0,180,0.8557750533894876,0.8517004518675895

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4ac2985f1fba10fb9cfc64e7cba04f046fb7834546cb247010bd6b051dde46
+size 1461366688

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 256,
+    "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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_config.json

@@ -0,0 +1,55 @@
+{
+  "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
+    },
+    "60001": {
+      "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>",
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}