Upload 10 files

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -1,3 +1,77 @@
 ---
+language:
+- ru
+- en
+
+pipeline_tag: sentence-similarity
+
+tags:
+- russian
+- pretraining
+- embeddings
+- tiny
+- feature-extraction
+- sentence-similarity
+- retrieval
+- sentence-transformers
+- transformers
+- mteb
+
+datasets:
+- IlyaGusev/gazeta
+- zloelias/lenta-ru
+- HuggingFaceFW/fineweb-2
+- HuggingFaceFW/fineweb
+
 license: mit
+
+base_model: sergeyzh/BERTA
+
 ---
+
+Модель BERT для задач текстового поиска (retrieval). Модель получена дистилляцией эмбеддингов русских и английских текстов [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) в [BERTA](https://huggingface.co/sergeyzh/BERTA).
+
+Основные характеристики модели: 
+ - размер ембеддинга - 768, 
+ - длина контекста - 512, 
+ - слоёв - 12,
+ - префиксы - не требуются. 
+
+
+
+## Использование
+
+```Python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer('sergeyzh/rubert-base-retriever')
+
+sentences = ["привет мир", "hello world", "здравствуй вселенная"]
+embeddings = model.encode(sentences)
+print(model.similarity(embeddings, embeddings))
+```
+
+
+
+## Метрики
+
+Оценки модели на задачах текстового поиска для русского языка:
+
+
+| Model Name | MIRACL Reranking | MIRACL Retrival | RiaNews Retrieval | RuBQ Reranking | RuBQ Retrieval | Average |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: |
+| bge-m3 | 0,654 | 0,702 | 0,830 | 0,740 | 0,712 | 0,728 |
+| BERTA | 0,643 | 0,676 | 0,816 | 0,752 | 0,710 | 0,719 |
+| **rubert-base-retriever** | 0,635 | 0,660 | 0,787 | 0,735 | 0,699 | 0,703 |
+| multilingual-e5-base | 0,605 | 0,616 | 0,702 | 0,720 | 0,696 | 0,668 |
+
+
+Оценки модели на задачах текстового поиска для английского языка:
+
+| Model Name | AILA Statutes | Argu Ana | Legal Bench Corporate Lobbying | SCIDOCS | Stack Overflow QA | Statcan Dialogue Dataset Retrieval | Wikipedia Retrieval Multilingual | Average |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| bge-m3 | 0,298 | 0,539 | 0,904 | 0,164 | 0,806 | 0,284 | 0,924 | 0,560 |
+| **rubert-base-retriever** | 0,249 | 0,528 | 0,912 | 0,154 | 0,703 | 0,346 | 0,928 | 0,546 |
+| multilingual-e5-large | 0,208 | 0,544 | 0,897 | 0,174 | 0,889 | 0,106 | 0,911 | 0,533 |
+| multilingual-e5-base | 0,204 | 0,442 | 0,890 | 0,172 | 0,851 | 0,137 | 0,888 | 0,512 |
+| BERTA | 0,188 | 0,414 | 0,907 | 0,112 | 0,493 | 0,304 | 0,888 | 0,472 |

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "sergeyzh/rubert-base-retriever",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "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 sha256:092860bfec80b25a6bbb3305f6c7b502d4f754cb4690c5eadac1fbb8ec22cbf9
+size 513402728

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 +1,37 @@
+{
+  "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
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "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]"
+}