Upload models

README.md

@@ -0,0 +1,28 @@
+# BERT large model multitask (cased) for Sentence Embeddings in Russian language.
+For better quality, use mean token embeddings.
+## Usage (HuggingFace Models Repository)
+You can use the model directly from the model repository to compute sentence embeddings:
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    sum_embeddings = torch.sum(token_embeddings * input_mask_expanded, 1)
+    sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+    return sum_embeddings / sum_mask
+#Sentences we want sentence embeddings for
+sentences = ['Привет! Как твои дела?',
+             'А правда, что 42 твое любимое число?']
+#Load AutoModel from huggingface model repository
+tokenizer = AutoTokenizer.from_pretrained("sberbank-ai/sbert_large_nlu_ru")
+model = AutoModel.from_pretrained("sberbank-ai/sbert_large_nlu_ru")
+#Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=24, return_tensors='pt')
+#Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+#Perform pooling. In this case, mean pooling
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/Users/ibragim/Downloads/sbert_nlu_mltsk",
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "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": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.4.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 120138
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e6a6d0a2d2140ebe7ccda6c907b51ffb9bf47b6d57db57a99e4c0d98a292fa
+size 1712498565

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e4a4603fa5d9df44e5a00c6e8cb0e721c6f92dc784b75b31148f9921bbdb271
+size 1708149528

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/Users/ibragim/Downloads/sbert_nlu_mltsk", "do_basic_tokenize": true, "never_split": null}