Upload folder using huggingface_hub

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 768,
+  "word_embedding_dimension": 256,
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,

README.md

@@ -4,12 +4,13 @@ tags:
 - sentence-transformers
 - feature-extraction
 - sentence-similarity
+- transformers
 
 ---
 
 # {MODEL_NAME}
 
-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.
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 256 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
 <!--- Describe your model here -->
 
@@ -34,6 +35,44 @@ print(embeddings)
 
 
 
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
 ## Evaluation Results
 
 <!--- Describe how your model was evaluated -->
@@ -46,28 +85,28 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 12606 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 788 with parameters:
 ```
-{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+{'batch_size': 256, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
 
 **Loss**:
 
-`__main__.LoggingMNRLoss` with parameters:
+`__main__.LoggingCosineSimLoss` with parameters:
   ```
-  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  {'distance_metric': 'SiameseDistanceMetric.COSINE_DISTANCE', 'margin': 0.5, 'size_average': True}
   ```
 
 Parameters of the fit()-Method:
 ```
 {
-    "epochs": 3,
+    "epochs": 2,
     "evaluation_steps": 0,
     "evaluator": "NoneType",
     "max_grad_norm": 1,
     "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
     "optimizer_params": {
-        "lr": 0.0005
+        "lr": 5e-05
     },
     "scheduler": "WarmupLinear",
     "steps_per_epoch": null,
@@ -80,9 +119,8 @@ Parameters of the fit()-Method:
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 512, '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})
-  (2): Normalize()
+  (0): Transformer({'max_seq_length': 150, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 256, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
 )
 ```
 

config.json

@@ -1,28 +1,149 @@
 {
-  "_name_or_path": "/root/.cache/torch/sentence_transformers/intfloat_multilingual-e5-base/",
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/omarelsayeed_Search_Model_PRECHATS_AUGMENTED/",
+  "_num_labels": 2,
   "architectures": [
-    "XLMRobertaModel"
+    "BertModel"
   ],
   "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,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "\u0627\u0645\u0627\u0643\u0646 \u0641\u0631\u0648\u0639 \u0641\u0648\u0631\u064a",
+    "1": "\u0645\u0648\u0627\u0639\u064a\u062f \u0641\u0631\u0648\u0639 \u0641\u0648\u0631\u064a",
+    "2": "\u0648\u0638\u064a\u0641\u0629",
+    "3": "\u0645\u062e\u0627\u0644\u0641\u0627\u062a \u0627\u0644\u0645\u0631\u0648\u0631",
+    "4": "\u0627\u0633\u062a\u0644\u0627\u0645 \u0627\u0644\u0631\u062e\u0635\u0629",
+    "5": "\u062a\u062c\u062f\u064a\u062f \u0627\u0644\u0631\u062e\u0635\u0629",
+    "6": "\u0627\u0636\u0627\u0641\u0647 \u0643\u0627\u0631\u062a",
+    "7": "\u062d\u0630\u0641 \u0643\u0627\u0631\u062a",
+    "8": "\u062a\u062e\u0637\u0649 \u062d\u062f \u0645\u0633\u0645\u0648\u062d",
+    "9": "\u0628\u0637\u0627\u0642\u0647 \u0645\u0639\u0644\u0642\u0629/\u0627\u0644\u0628\u0637\u0627\u0642\u0629 \u0645\u062d\u0638\u0648\u0631\u0629",
+    "10": "\u062d\u0633\u0627\u0628 \u062c\u062f\u064a\u062f",
+    "11": "\u062a\u0633\u062c\u064a\u0644 \u062f\u062e\u0648\u0644 \u062d\u0633\u0627\u0628",
+    "12": "\u062d\u0630\u0641 \u062d\u0633\u0627\u0628",
+    "13": "\u062d\u0633\u0627\u0628 \u0645\u062d\u0638\u0648\u0631",
+    "14": "\u062a\u062d\u062f\u064a\u062b \u062d\u0633\u0627\u0628",
+    "15": "\u0637\u0628\u0627\u0639\u0647 \u0641\u0627\u062a\u0648\u0631\u0629",
+    "16": "\u0627\u0633\u062a\u0641\u0633\u0627\u0631 \u0639\u0646 \u062d\u0627\u0644\u0629 \u0627\u0644\u0639\u0645\u0644\u064a\u0629/\u0627\u0644\u0639\u0645\u0644\u064a\u0629 \u0627\u062a\u062e\u0635\u0645\u062a",
+    "17": "\u0634\u0631\u0627\u0621 \u0645\u0627\u0643\u064a\u0646\u0647",
+    "18": "\u062a\u062d\u0648\u064a\u0644 \u0645\u0628\u0644\u063a \u0645\u0627\u0644\u064a",
+    "19": "\u062e\u062f\u0645\u0627\u062a \u0627\u0644\u0642\u0648\u0627\u062a \u0627\u0644\u0645\u0633\u0644\u062d\u0629",
+    "20": "\u0634\u062d\u0646 \u0627\u0644\u0645\u0648\u0628\u0627\u064a\u0644",
+    "21": "\u0641\u0627\u062a\u0648\u0631\u0629 \u0627\u0644\u0645\u0648\u0628\u0627\u064a\u0644",
+    "22": "\u0645\u064a\u0627\u0647",
+    "23": "\u063a\u0627\u0632",
+    "24": "\u0627\u0644\u0643\u0647\u0631\u0628\u0627\u0621",
+    "25": "\u0641\u0648\u0631\u064a \u0628\u0627\u064a",
+    "26": "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u0643\u0647\u0631\u0628\u0627\u0621",
+    "27": "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u0645\u064a\u0627\u0647",
+    "28": "\u0645\u0634\u0643\u0644\u0629 \u0641\u064a \u0627\u0644\u062a\u0637\u0628\u064a\u0642",
+    "29": "\u0627\u0633\u062a\u0631\u0627\u062c\u0639 \u0642\u064a\u0645\u0629 \u0645\u0627\u0644\u064a\u0629",
+    "30": "\u0645\u0639\u0627\u0645\u0644\u0627\u062a \u062f\u0648\u0644\u064a\u0629",
+    "31": "\u062a\u0630\u0627\u0643\u0631",
+    "32": "\u0627\u0644\u062a\u0623\u0645\u064a\u0646",
+    "33": "\u0627\u0644\u0646\u0642\u0627\u0628\u0627\u062a",
+    "34": "\u062a\u0639\u0644\u064a\u0645",
+    "35": "\u062e\u062f\u0645\u0629 \u0627\u0644\u0639\u0645\u0644\u0627\u0621",
+    "36": "\u0627\u0644\u0639\u0627\u0628 \u0627\u0648\u0646\u0644\u0627\u064a\u0646",
+    "37": "\u0645\u0639\u0627\u0645\u0644\u0627\u062a \u0645\u0627\u0644\u064a\u0629 \u0648 \u0628\u0646\u0648\u0643",
+    "38": "\u062a\u0645\u0648\u064a\u0644 \u0645\u062a\u0646\u0627\u0647\u064a \u0627\u0644\u0635\u063a\u0631",
+    "39": "\u0645\u062f\u0641\u0648\u0639\u0627\u062a \u0627\u0648\u0646\u0644\u0627\u064a\u0646",
+    "40": "\u062a\u0628\u0631\u0639\u0627\u062a",
+    "41": "\u0627\u0634\u062a\u0631\u0627\u0643 \u0646\u0648\u0627\u062f\u064a",
+    "42": "Yellow Card",
+    "43": "\u062c\u0648\u0627\u0626\u0632",
+    "44": "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u063a\u0627\u0632",
+    "45": "\u0627\u0644\u0627\u0646\u062a\u0631\u0646\u062a \u0627\u0644\u0645\u0646\u0632\u0644\u064a",
+    "46": "\u0627\u0644\u062a\u0644\u064a\u0641\u0648\u0646 \u0627\u0644\u0623\u0631\u0636\u064a",
+    "47": "\u0641\u0648\u0631\u064a \u062a\u0642\u0633\u064a\u0637",
+    "48": "\u0641\u0648\u0631\u064a \u064a\u0648\u0645\u064a",
+    "49": "\u062a\u0642\u062f\u064a\u0645 \u0634\u0643\u0648\u064a",
+    "50": "\u0633\u0643\u0646 \u0648\u0639\u0642\u0627\u0631\u0627\u062a",
+    "51": "\u0641\u0648\u0631\u064a \u0644\u0644\u0648\u0633\u0627\u0637\u0629 \u0627\u0644\u062a\u0623\u0645\u064a\u0646\u064a\u0629",
+    "52": "\u062a\u0623\u0645\u064a\u0646 \u0627\u062c\u062a\u0645\u0627\u0639\u064a",
+    "53": "\u0627\u064a\u062f\u0627\u0639",
+    "54": "Consumer Finance",
+    "55": "\u062a\u0633\u062c\u064a\u0644 \u0627\u0644\u0648\u062d\u062f\u0627\u062a \u0627\u0644\u0639\u0642\u0627\u0631\u064a\u0629",
+    "56": "\u0633\u062d\u0628",
+    "57": "\u0634\u0631\u0627\u0621 \u0645\u0646 \u0645\u062d\u0644"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "intermediate_size": 1024,
+  "label2id": {
+    "Consumer Finance": 54,
+    "Yellow Card": 42,
+    "\u0627\u0633\u062a\u0631\u0627\u062c\u0639 \u0642\u064a\u0645\u0629 \u0645\u0627\u0644\u064a\u0629": 29,
+    "\u0627\u0633\u062a\u0641\u0633\u0627\u0631 \u0639\u0646 \u062d\u0627\u0644\u0629 \u0627\u0644\u0639\u0645\u0644\u064a\u0629/\u0627\u0644\u0639\u0645\u0644\u064a\u0629 \u0627\u062a\u062e\u0635\u0645\u062a": 16,
+    "\u0627\u0633\u062a\u0644\u0627\u0645 \u0627\u0644\u0631\u062e\u0635\u0629": 4,
+    "\u0627\u0634\u062a\u0631\u0627\u0643 \u0646\u0648\u0627\u062f\u064a": 41,
+    "\u0627\u0636\u0627\u0641\u0647 \u0643\u0627\u0631\u062a": 6,
+    "\u0627\u0644\u0627\u0646\u062a\u0631\u0646\u062a \u0627\u0644\u0645\u0646\u0632\u0644\u064a": 45,
+    "\u0627\u0644\u062a\u0623\u0645\u064a\u0646": 32,
+    "\u0627\u0644\u062a\u0644\u064a\u0641\u0648\u0646 \u0627\u0644\u0623\u0631\u0636\u064a": 46,
+    "\u0627\u0644\u0639\u0627\u0628 \u0627\u0648\u0646\u0644\u0627\u064a\u0646": 36,
+    "\u0627\u0644\u0643\u0647\u0631\u0628\u0627\u0621": 24,
+    "\u0627\u0644\u0646\u0642\u0627\u0628\u0627\u062a": 33,
+    "\u0627\u0645\u0627\u0643\u0646 \u0641\u0631\u0648\u0639 \u0641\u0648\u0631\u064a": 0,
+    "\u0627\u064a\u062f\u0627\u0639": 53,
+    "\u0628\u0637\u0627\u0642\u0647 \u0645\u0639\u0644\u0642\u0629/\u0627\u0644\u0628\u0637\u0627\u0642\u0629 \u0645\u062d\u0638\u0648\u0631\u0629": 9,
+    "\u062a\u0623\u0645\u064a\u0646 \u0627\u062c\u062a\u0645\u0627\u0639\u064a": 52,
+    "\u062a\u0628\u0631\u0639\u0627\u062a": 40,
+    "\u062a\u062c\u062f\u064a\u062f \u0627\u0644\u0631\u062e\u0635\u0629": 5,
+    "\u062a\u062d\u062f\u064a\u062b \u062d\u0633\u0627\u0628": 14,
+    "\u062a\u062d\u0648\u064a\u0644 \u0645\u0628\u0644\u063a \u0645\u0627\u0644\u064a": 18,
+    "\u062a\u062e\u0637\u0649 \u062d\u062f \u0645\u0633\u0645\u0648\u062d": 8,
+    "\u062a\u0630\u0627\u0643\u0631": 31,
+    "\u062a\u0633\u062c\u064a\u0644 \u0627\u0644\u0648\u062d\u062f\u0627\u062a \u0627\u0644\u0639\u0642\u0627\u0631\u064a\u0629": 55,
+    "\u062a\u0633\u062c\u064a\u0644 \u062f\u062e\u0648\u0644 \u062d\u0633\u0627\u0628": 11,
+    "\u062a\u0639\u0644\u064a\u0645": 34,
+    "\u062a\u0642\u062f\u064a\u0645 \u0634\u0643\u0648\u064a": 49,
+    "\u062a\u0645\u0648\u064a\u0644 \u0645\u062a\u0646\u0627\u0647\u064a \u0627\u0644\u0635\u063a\u0631": 38,
+    "\u062c\u0648\u0627\u0626\u0632": 43,
+    "\u062d\u0630\u0641 \u062d\u0633\u0627\u0628": 12,
+    "\u062d\u0630\u0641 \u0643\u0627\u0631\u062a": 7,
+    "\u062d\u0633\u0627\u0628 \u062c\u062f\u064a\u062f": 10,
+    "\u062d\u0633\u0627\u0628 \u0645\u062d\u0638\u0648\u0631": 13,
+    "\u062e\u062f\u0645\u0627\u062a \u0627\u0644\u0642\u0648\u0627\u062a \u0627\u0644\u0645\u0633\u0644\u062d\u0629": 19,
+    "\u062e\u062f\u0645\u0629 \u0627\u0644\u0639\u0645\u0644\u0627\u0621": 35,
+    "\u0633\u062d\u0628": 56,
+    "\u0633\u0643\u0646 \u0648\u0639\u0642\u0627\u0631\u0627\u062a": 50,
+    "\u0634\u062d\u0646 \u0627\u0644\u0645\u0648\u0628\u0627\u064a\u0644": 20,
+    "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u063a\u0627\u0632": 44,
+    "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u0643\u0647\u0631\u0628\u0627\u0621": 26,
+    "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u0645\u064a\u0627\u0647": 27,
+    "\u0634\u0631\u0627\u0621 \u0645\u0627\u0643\u064a\u0646\u0647": 17,
+    "\u0634\u0631\u0627\u0621 \u0645\u0646 \u0645\u062d\u0644": 57,
+    "\u0637\u0628\u0627\u0639\u0647 \u0641\u0627\u062a\u0648\u0631\u0629": 15,
+    "\u063a\u0627\u0632": 23,
+    "\u0641\u0627\u062a\u0648\u0631\u0629 \u0627\u0644\u0645\u0648\u0628\u0627\u064a\u0644": 21,
+    "\u0641\u0648\u0631\u064a \u0628\u0627\u064a": 25,
+    "\u0641\u0648\u0631\u064a \u062a\u0642\u0633\u064a\u0637": 47,
+    "\u0641\u0648\u0631\u064a \u0644\u0644\u0648\u0633\u0627\u0637\u0629 \u0627\u0644\u062a\u0623\u0645\u064a\u0646\u064a\u0629": 51,
+    "\u0641\u0648\u0631\u064a \u064a\u0648\u0645\u064a": 48,
+    "\u0645\u062e\u0627\u0644\u0641\u0627\u062a \u0627\u0644\u0645\u0631\u0648\u0631": 3,
+    "\u0645\u062f\u0641\u0648\u0639\u0627\u062a \u0627\u0648\u0646\u0644\u0627\u064a\u0646": 39,
+    "\u0645\u0634\u0643\u0644\u0629 \u0641\u064a \u0627\u0644\u062a\u0637\u0628\u064a\u0642": 28,
+    "\u0645\u0639\u0627\u0645\u0644\u0627\u062a \u062f\u0648\u0644\u064a\u0629": 30,
+    "\u0645\u0639\u0627\u0645\u0644\u0627\u062a \u0645\u0627\u0644\u064a\u0629 \u0648 \u0628\u0646\u0648\u0643": 37,
+    "\u0645\u0648\u0627\u0639\u064a\u062f \u0641\u0631\u0648\u0639 \u0641\u0648\u0631\u064a": 1,
+    "\u0645\u064a\u0627\u0647": 22,
+    "\u0648\u0638\u064a\u0641\u0629": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
   "output_past": true,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 32000
 }

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
     "sentence_transformers": "2.2.2",
-    "transformers": "4.30.2",
+    "transformers": "4.33.0",
     "pytorch": "2.0.0"
   }
 }

modules.json

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

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f9c6aa8970951cfcaa3ec982d2dfa3e43020bfd8f8bfcd7cdabcb26905c026
-size 1112245805
+oid sha256:dcfff453aa382640b606ce355a3ca4535a0f71ae483d4262d49a317cb47e6cd4
+size 46223689

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 512,
+  "max_seq_length": 150,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46afe88da5fd71bdbab5cfab5e84c1adce59c246ea5f9341bbecef061891d0a7
-size 17082913
+oid sha256:e852f89dc047b37115597d63437977dde03e8e41e6fc8bdbc42901103b63394b
+size 837545

tokenizer_config.json

@@ -1,19 +1,65 @@
 {
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "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]"
 }