Use BioLORD-2023-M config

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "output/dmmc1_FremyCompany-BioLORD-2023-M-2024-06-22_15-35-21/",
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
   "architectures": [
     "XLMRobertaModel"
   ],
@@ -22,7 +22,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.24.0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 128,
+  "max_seq_length": 64,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,25 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -27,25 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
-size 17082987
+oid sha256:64f620ed598f02c6e9ad8bd7c093e0bf1f883f0a113b315e3299ae7d1b85581a
+size 17082912

tokenizer_config.json

@@ -17,4 +17,4 @@
   "special_tokens_map_file": null,
   "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
-}
+}