Upload 10 files

README.md

@@ -10,7 +10,7 @@ tags:
 
 # {MODEL_NAME}
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 312 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
 <!--- Describe your model here -->
 
@@ -119,8 +119,8 @@ Parameters of the fit()-Method:
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 2048, 'do_lower_case': False}) with Transformer model: BertModel 
-  (1): Pooling({'word_embedding_dimension': 312, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel 
+  (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})
 )
 ```
 

config.json

@@ -1,27 +1,24 @@
 {
-  "_name_or_path": "/media/denis/d9b5b2ab-3dc3-4627-9f99-1ed59b84b83e/models/ruBert-tiny2/",
+  "_name_or_path": "/media/denis/042CD5B7300C3479/instructor_chatbot/models/embedding_model/",
+  "activation": "gelu",
   "architectures": [
-    "BertModel"
+    "DistilBertModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "emb_size": 312,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 312,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 600,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 2048,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 3,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.29.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 83828
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23779b78540103dbcada3d35abb9ffbb5dd811890c025e10f201a34428c5a8a8
-size 116808857
+oid sha256:b3c2453e24d06b8b580f3f965a56a7f4bd311ca5907bae5211462b404a1a02b6
+size 538969501

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 2048,
+  "max_seq_length": 512,
   "do_lower_case": false
 }

tokenizer_config.json

@@ -4,12 +4,13 @@
   "do_basic_tokenize": true,
   "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 2048,
+  "max_len": 512,
+  "model_max_length": 512,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }