Upload 11 files (#4)

- Upload 11 files (ff6c2d5a3b8544d75b01c8bcf66eec100be7cedf)
- Delete pytorch_model.bin (f8554054741b1f28af4dc1531832f7e645eeb2db)
- Delete tf_model.h5 (81002e3cbb80a9259679d393af7c2f5b38271561)
- Delete vocab.txt (7650bdeace965517efc5c7573f3760bd6695ec99)
- Delete flax_model.msgpack (c987fcdb31796f6e9d5621d1cea1439683dd0851)
- Upload 10 files (37400f31238f6fd1946020143b62e4a0069d80f1)
- Update tokenizer_config.json (347ec68f3b1bdd2a2d99ee0989d8a6507e93d5f9)

.gitattributes

@@ -15,3 +15,4 @@
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
+model.safetensors 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
+}

config.json

@@ -1,8 +1,10 @@
 {
+  "_name_or_path": "ai-forever/sbert_large_mt_nlu_ru",
   "architectures": [
     "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
   "directionality": "bidi",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
@@ -22,7 +24,8 @@
   "pooler_size_per_head": 128,
   "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
-  "transformers_version": "4.6.0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 120138

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.3.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

flax_model.msgpack → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:874490e6b754858ac826e7d3047a9dfc69fd3334d5949fb2631260f9599dfe30
-size 1707648669
+oid sha256:753539b83bc0ba58ec1606359c6ceb148495512db72f731a5d2af045a4af1c6b
+size 1707679808

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"
+  }
+]

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1e9820b2cd7bbd38f0ea67800eff571d4b0d862b75d93399b98f3e8db84b8e2a
-size 1707796287

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -1 +1,7 @@
-{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tf_model.h5

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

tokenizer_config.json

@@ -1 +1,57 @@
-{"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}
+{
+  "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}