初始化项目，由ModelHub XC社区提供模型

Model: kinit/slovakbert-sts-stsb
Source: Original Platform

.gitattributes

@@ -0,0 +1,30 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/7b/1c/7b1c3ca65da2275e74cc85ad22e76e66ecc6368914f0e9667029d1af967ad7ee filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/e1/f6/e1f6761555731e9e8e29ec3342163f2bbbbb3edd3395993ff3f57de27d0fa05b filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,79 @@
+---
+language:
+- sk
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- sts
+license: cc-by-4.0
+datasets:
+- glue
+metrics:
+- spearmanr
+widget:
+- source_sentence: Izrael uskutočnil letecké údery v blízkosti Damasku.
+  sentences:
+  - Izrael uskutočnil vzdušný útok na Sýriu.
+  - Pes leží na gauči a má hlavu na bielom vankúši.
+base_model:
+- gerulata/slovakbert
+library_name: sentence-transformers
+---
+
+
+# Sentence similarity model based on SlovakBERT
+
+This is a sentence similarity model based on [SlovakBERT](https://huggingface.co/gerulata/slovakbert). The model was fine-tuned using [STSbenchmark](https://ixa2.si.ehu.eus/stswiki/index.php/STSbenchmark) [Cer et al 2017] translated to Slovak using [M2M100](https://huggingface.co/facebook/m2m100_1.2B). The model can be used as an universal sentence encoder for Slovak sentences.
+
+## Results
+
+The model was evaluated in [our paper](https://arxiv.org/abs/2109.15254) [Pikuliak et al 2021, Section 4.3]. It achieves \\(0.791\\) Spearman correlation on STSbenchmark test set.
+
+
+## Usage
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('kinit/slovakbert-sts-stsb')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+## Cite
+
+```
+@inproceedings{pikuliak-etal-2022-slovakbert,
+    title = "{S}lovak{BERT}: {S}lovak Masked Language Model",
+    author = "Pikuliak, Mat{\'u}{\v{s}}  and
+      Grivalsk{\'y}, {\v{S}}tefan  and
+      Kon{\^o}pka, Martin  and
+      Bl{\v{s}}t{\'a}k, Miroslav  and
+      Tamajka, Martin  and
+      Bachrat{\'y}, Viktor  and
+      Simko, Marian  and
+      Bal{\'a}{\v{z}}ik, Pavol  and
+      Trnka, Michal  and
+      Uhl{\'a}rik, Filip",
+    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
+    month = dec,
+    year = "2022",
+    address = "Abu Dhabi, United Arab Emirates",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2022.findings-emnlp.530",
+    pages = "7156--7168",
+    abstract = "We introduce a new Slovak masked language model called \textit{SlovakBERT}. This is to our best knowledge the first paper discussing Slovak transformers-based language models. We evaluate our model on several NLP tasks and achieve state-of-the-art results. This evaluation is likewise the first attempt to establish a benchmark for Slovak language models. We publish the masked language model, as well as the fine-tuned models for part-of-speech tagging, sentiment analysis and semantic textual similarity.",
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "models/sts/0_Transformer",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50264
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.1.0",
+    "transformers": "4.12.2",
+    "pytorch": "1.8.1+cu111"
+  }
+}

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"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c37550b2742afa71a1d36ec08b8c819f213562b045e25517b83e106f8f8c27f
+size 498660807

sentence_bert_config.json

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

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "model_max_length": 512, "name_or_path": "models/sts/0_Transformer", "tokenizer_class": "RobertaTokenizer"}