初始化项目，由ModelHub XC社区提供模型

Model: sergeyzh/rubert-large-uncased-sts
Source: Original Platform

.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 +1,7 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,81 @@
+---
+language:
+- ru
+- en
+
+pipeline_tag: sentence-similarity
+
+tags:
+- russian
+- pretraining
+- embeddings
+- feature-extraction
+- sentence-similarity
+- sentence-transformers
+- transformers
+- mteb
+
+datasets:
+- IlyaGusev/gazeta
+- zloelias/lenta-ru
+- HuggingFaceFW/fineweb-2
+- HuggingFaceFW/fineweb
+
+license: mit
+
+---
+
+Модель BERT для задач симметричного перефразирования (STS, поиск парафраз, дедупликация) и логического вывода (NLI). Получена дистилляцией эмбеддингов русских и английских текстов [Qwen/Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B).
+
+Модель может использоваться в качестве базовой для дообучения под пользовательские задачи классификации и кластеризации.
+
+Основные характеристики модели: 
+ - размер ембеддинга - 1024, 
+ - длина контекста - 512, 
+ - слоёв - 12,
+ - префиксы - не требуются. 
+
+
+
+## Использование
+
+```Python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer('sergeyzh/rubert-large-uncased-sts')
+
+sentences = ["привет мир", "hello world", "здравствуй вселенная"]
+embeddings = model.encode(sentences)
+print(model.similarity(embeddings, embeddings))
+```
+
+
+
+## Метрики
+
+Оценки модели на задачах для русского языка:
+
+| Model Name | RuSTS Benchmark STS | RU ParaPhraser STS | STS22,v2 | TERRa Classification | Average |
+| :--- | :---: | :---: | :---: | :---: | :---: |
+| Qwen3-Embedding-4B | 0,888 | 0,766 | 0,701 | 0,666 | 0,755 |
+| **rubert-large-uncased-sts** | 0,869 | 0,771 | 0,686 | 0,664 | 0,748 |
+| multilingual-e5-large-instruct | 0,840 | 0,754 | 0,706 | 0,639 | 0,735 |
+| Qwen3-Embedding-0.6B | 0,842 | 0,721 | 0,662 | 0,607 | 0,708 |
+| bge-m3 | 0,797 | 0,749 | 0,663 | 0,607 | 0,704 |
+| multilingual-e5-base | 0,796 | 0,702 | 0,607 | 0,550 | 0,664 |
+
+
+
+
+Оценки модели на задачах для английского языка:
+
+| Model Name | STS12 | STS13 | STS14 | STS15 | STS17 | STS22,v2 | STS Benchmark | Average |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| Qwen3-Embedding-4B | 0,866 | 0,944 | 0,909 | 0,938 | 0,918 | 0,730 | 0,937 | 0,892 |
+| Qwen3-Embedding-0.6B | 0,830 | 0,918 | 0,871 | 0,914 | 0,855 | 0,718 | 0,911 | 0,860 |
+| **rubert-large-uncased-sts** | 0,818 | 0,901 | 0,864 | 0,901 | 0,906 | 0,660 | 0,896 | 0,849 |
+| multilingual-e5-large-instruct | 0,825 | 0,881 | 0,848 | 0,910 | 0,860 | 0,690 | 0,884 | 0,842 |
+| bge-m3 | 0,787 | 0,796 | 0,790 | 0,878 | 0,796 | 0,700 | 0,849 | 0,800 |
+| multilingual-e5-base | 0,767 | 0,780 | 0,766 | 0,882 | 0,783 | 0,646 | 0,856 | 0,783 |
+
+

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sergeyzh/rubert-large-uncased-sts",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 55083
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31faa1bd4694dccc9684e05a6b4f73a29bb3ca6917e6fdb1d1ca92eebf87bc3
+size 836573272

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": true
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "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 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}