Update model

.ipynb_checkpoints/tokenizer_config-checkpoint.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "54213": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "BAAI/bge-m3_en_ru",
   "architectures": [
     "XLMRobertaModel"
   ],
@@ -20,8 +21,8 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.46.1",
+  "transformers_version": "4.46.3",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 37367
+  "vocab_size": 54214
 }

config_sentence_transformers.json

@@ -1,10 +1,10 @@
 {
   "__version__": {
-    "sentence_transformers": "3.2.1",
-    "transformers": "4.46.1",
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.46.3",
     "pytorch": "2.2.0"
   },
   "prompts": {},
   "default_prompt_name": null,
-  "similarity_fn_name": null
+  "similarity_fn_name": "cosine"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef9142e240873048deacfbb500046a021105bddca1a2ed1aeedf69f59cf6b26
-size 1400110976
+oid sha256:7926082ed1ac1672d6f5ed7f1192cce1d77b9adf751a9e4b1155c7fb01d9594b
+size 1469116328

sentencepiece.bpe.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684630b85d293bcae6550704da70dc9ae9f76e9b9b5d22580cf6e7baccff1633
-size 825209
+oid sha256:7551423f8ba0399245a6e8b81b20c6938eaa1f9428c014c27f7e7120855914d2
+size 1181314

tokenizer_config.json

@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "37366": {
+    "54213": {
       "content": "<mask>",
       "lstrip": true,
       "normalized": true,