Revert inadvertent config, tokenizer updates

This reverts commit d6a867ee21ea12c29559eca07bd3c048e0577565.

README.md

@@ -1,33 +1,33 @@
----
-license: apache-2.0
-datasets:
-- sentence-transformers/stsb
-language:
-- en
-base_model:
-- FacebookAI/roberta-large
-pipeline_tag: text-ranking
-library_name: sentence-transformers
-tags:
-- transformers
----
-# Cross-Encoder for Semantic Textual Similarity
-This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class.
-
-## Training Data
-This model was trained on the [STS benchmark dataset](http://ixa2.si.ehu.eus/stswiki/index.php/STSbenchmark). The model will predict a score between 0 and 1 how for the semantic similarity of two sentences. 
-
-
-## Usage and Performance
-
-Pre-trained models can be used like this:
-```python
-from sentence_transformers import CrossEncoder
-
-model = CrossEncoder('cross-encoder/stsb-roberta-large')
-scores = model.predict([('Sentence 1', 'Sentence 2'), ('Sentence 3', 'Sentence 4')])
-```
-
-The model will predict scores for the pairs `('Sentence 1', 'Sentence 2')` and `('Sentence 3', 'Sentence 4')`.
-
+---
+license: apache-2.0
+datasets:
+- sentence-transformers/stsb
+language:
+- en
+base_model:
+- FacebookAI/roberta-large
+pipeline_tag: text-ranking
+library_name: sentence-transformers
+tags:
+- transformers
+---
+# Cross-Encoder for Semantic Textual Similarity
+This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class.
+
+## Training Data
+This model was trained on the [STS benchmark dataset](http://ixa2.si.ehu.eus/stswiki/index.php/STSbenchmark). The model will predict a score between 0 and 1 how for the semantic similarity of two sentences. 
+
+
+## Usage and Performance
+
+Pre-trained models can be used like this:
+```python
+from sentence_transformers import CrossEncoder
+
+model = CrossEncoder('cross-encoder/stsb-roberta-large')
+scores = model.predict([('Sentence 1', 'Sentence 2'), ('Sentence 3', 'Sentence 4')])
+```
+
+The model will predict scores for the pairs `('Sentence 1', 'Sentence 2')` and `('Sentence 3', 'Sentence 4')`.
+
 You can use this model also without sentence_transformers and by just using Transformers ``AutoModel`` class

config.json

@@ -1,37 +1,29 @@
-{
-  "_num_labels": 3,
-  "architectures": [
-    "RobertaForSequenceClassification"
-  ],
-  "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": 1024,
-  "id2label": {
-    "0": "LABEL_0"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "label2id": {
-    "LABEL_0": 0
-  },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "sentence_transformers": {
-    "activation_fn": "torch.nn.modules.activation.Sigmoid",
-    "version": "4.1.0.dev0"
-  },
-  "transformers_version": "4.52.0.dev0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
-}
+{
+  "_num_labels": 3,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}