Add new SentenceTransformer model.

README.md

@@ -120,7 +120,7 @@ Parameters of the fit()-Method:
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 100, 'do_lower_case': False}) with Transformer model: AlbertModel 
+  (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: RobertaModel 
   (1): Pooling({'word_embedding_dimension': 768, '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

@@ -1,33 +1,28 @@
 {
   "_name_or_path": "/content/output_train",
   "architectures": [
-    "AlbertModel"
+    "RobertaModel"
   ],
-  "attention_probs_dropout_prob": 0,
-  "bos_token_id": 2,
-  "classifier_dropout_prob": 0.1,
-  "down_scale_factor": 1,
-  "embedding_size": 128,
-  "eos_token_id": 3,
-  "gap_size": 0,
-  "hidden_act": "gelu_new",
-  "hidden_dropout_prob": 0,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
-  "inner_group_num": 1,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "num_attention_heads": 12,
-  "num_hidden_groups": 1,
   "num_hidden_layers": 6,
-  "num_memory_blocks": 0,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.40.2",
-  "type_vocab_size": 2,
-  "vocab_size": 30000
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:946b5b069f6fd0f14632b0e71ee6fcff00ac3c53524a1c8b00f357ee23400c39
-size 46737416
+oid sha256:263a450b4d6ad09e5436839802f842fe0bb296cab15bc7baba255a95272cbdc7
+size 328485128

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 100,
+  "max_seq_length": 75,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,27 +1,27 @@
 {
   "bos_token": {
-    "content": "[CLS]",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "cls_token": {
-    "content": "[CLS]",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "[SEP]",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "mask_token": {
-    "content": "[MASK]",
+    "content": "<mask>",
     "lstrip": true,
     "normalized": false,
     "rstrip": false,
@@ -35,7 +35,7 @@
     "single_word": false
   },
   "sep_token": {
-    "content": "[SEP]",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,7 +1,8 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<pad>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +10,7 @@
       "special": true
     },
     "1": {
-      "content": "<unk>",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +18,7 @@
       "special": true
     },
     "2": {
-      "content": "[CLS]",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,15 +26,15 @@
       "special": true
     },
     "3": {
-      "content": "[SEP]",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "[MASK]",
+    "50264": {
+      "content": "<mask>",
       "lstrip": true,
       "normalized": false,
       "rstrip": false,
@@ -41,23 +42,22 @@
       "special": true
     }
   },
-  "bos_token": "[CLS]",
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "eos_token": "[SEP]",
-  "keep_accents": false,
-  "mask_token": "[MASK]",
-  "max_length": 100,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 75,
   "model_max_length": 512,
   "pad_to_multiple_of": null,
   "pad_token": "<pad>",
   "pad_token_type_id": 0,
   "padding_side": "right",
-  "remove_space": true,
-  "sep_token": "[SEP]",
+  "sep_token": "</s>",
   "stride": 0,
-  "tokenizer_class": "AlbertTokenizer",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "<unk>"