Add new SentenceTransformer model

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 512,
+  "word_embedding_dimension": 384,
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,

config.json

@@ -1,36 +1,26 @@
 {
-  "_name_or_path": "jinaai/jina-embeddings-v2-small-en",
+  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
   "architectures": [
-    "JinaBertModel"
+    "BertModel"
   ],
-  "attention_probs_dropout_prob": 0.0,
-  "attn_implementation": null,
-  "auto_map": {
-    "AutoConfig": "jinaai/jina-bert-implementation--configuration_bert.JinaBertConfig",
-    "AutoModel": "jinaai/jina-bert-implementation--modeling_bert.JinaBertModel",
-    "AutoModelForMaskedLM": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForMaskedLM",
-    "AutoModelForSequenceClassification": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForSequenceClassification"
-  },
+  "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "emb_pooler": "mean",
-  "feed_forward_type": "geglu",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
+  "intermediate_size": 1536,
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 8192,
-  "model_max_length": 8192,
+  "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 4,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "alibi",
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.45.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30528
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e787f7cfdca1b5fdba32b7dbebcac86c5095c4f0558bbe2cb75f6d7a6f6d6db1
-size 130769960
+oid sha256:7dd3bf6aafaa845805be2f1c6c1195f7017af7142dea16d703986ef25aa24237
+size 90864192

modules.json

@@ -10,5 +10,11 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
   }
 ]

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 512,
+  "max_seq_length": 256,
   "do_lower_case": false
 }

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
@@ -30678,13 +30678,7 @@
       "##／": 30518,
       "##：": 30519,
       "##？": 30520,
-      "##～": 30521,
-      "bowang": 30522,
-      "georgiosmastrapas": 30523,
-      "jackminong": 30524,
-      "jonathangeuter": 30525,
-      "louismilliken": 30526,
-      "michaelguenther": 30527
+      "##～": 30521
     }
   }
 }

tokenizer_config.json

@@ -41,17 +41,24 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 8192,
+  "max_length": 128,
+  "model_max_length": 256,
   "never_split": null,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

vocab.txt

@@ -30520,9 +30520,3 @@ necessitated
 ##：
 ##？
 ##～
-bowang
-georgiosmastrapas
-jackminong
-jonathangeuter
-louismilliken
-michaelguenther