Upload folder using huggingface_hub

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 384,
+  "word_embedding_dimension": 768,
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,

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 384 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 -->
 
@@ -97,7 +97,7 @@ The model was trained with the parameters:
 Parameters of the fit()-Method:
 ```
 {
-    "epochs": 5,
+    "epochs": 3,
     "evaluation_steps": 0,
     "evaluator": "NoneType",
     "max_grad_norm": 1,
@@ -116,8 +116,8 @@ Parameters of the fit()-Method:
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 50, 'do_lower_case': False}) with Transformer model: BertModel 
-  (1): Pooling({'word_embedding_dimension': 384, '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': 80, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (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

@@ -1,26 +1,29 @@
 {
-  "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2/",
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-mpnet-base-v2/",
   "architectures": [
-    "BertModel"
+    "XLMRobertaModel"
   ],
   "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": 384,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250037
+  "vocab_size": 250002
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06774f97bfe0fa5f87a3f94468d4068403b994cceca36251a580ca9f4f131e50
-size 470686253
+oid sha256:3582c57c542caf1c222073f27a89102a0df6557dc0b458e555c4c087fe140799
+size 1112245805

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 50,
+  "max_seq_length": 80,
   "do_lower_case": false
 }

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0e547aaa62c434b38638d309fd726cafaabff159e25b10afdd819a8595c3dd
+oid sha256:e54a06c2a8b8041b979a9167588cf3adec464fb634ad3b32fbc412c8a4398303
 size 17082912

tokenizer_config.json

@@ -2,7 +2,6 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
-  "do_lower_case": true,
   "eos_token": "</s>",
   "mask_token": {
     "__type": "AddedToken",
@@ -15,8 +14,6 @@
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }