Upload folder using huggingface_hub

README.md

@@ -85,7 +85,7 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 125 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 13 with parameters:
 ```
 {'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
@@ -100,7 +100,7 @@ The model was trained with the parameters:
 Parameters of the fit()-Method:
 ```
 {
-    "epochs": 5,
+    "epochs": 30,
     "evaluation_steps": 0,
     "evaluator": "NoneType",
     "max_grad_norm": 1,
@@ -119,7 +119,7 @@ Parameters of the fit()-Method:
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: RobertaModel 
+  (0): Transformer({'max_seq_length': 258, '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})
 )
 ```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/torch/sentence_transformers/VoVanPhuc_sup-SimCSE-VietNamese-phobert-base",
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/vinai_phobert-base-v2",
   "architectures": [
     "RobertaModel"
   ],
@@ -7,7 +7,6 @@
   "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,
@@ -22,7 +21,7 @@
   "position_embedding_type": "absolute",
   "tokenizer_class": "PhobertTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
+  "transformers_version": "4.34.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 64001

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
     "sentence_transformers": "2.2.2",
-    "transformers": "4.33.2",
-    "pytorch": "2.0.1+cu118"
+    "transformers": "4.34.1",
+    "pytorch": "2.1.0+cu118"
   }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbade96fe7eb6c557683bb90a606d9ad80cb59b0f65929a2569e5ddf8df71c87
-size 540059817
+oid sha256:2d68ffd8e2445e7584fed7d6985faa566f5498ea618b2acf1e708e273b541837
+size 540060262

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 256,
+  "max_seq_length": 258,
   "do_lower_case": false
 }

tokenizer_config.json

@@ -1,13 +1,54 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "model_max_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "PhobertTokenizer",
-  "tokenizer_file": null,
   "unk_token": "<unk>"
 }