nreimers commited on
Commit
ed0a934
1 Parent(s): 1e41a29
CECorrelationEvaluator_sts-dev_results.csv ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ epoch,steps,Pearson_Correlation,Spearman_Correlation
2
+ 0,-1,0.884083449570549,0.8863177324254378
3
+ 1,-1,0.9005634047434494,0.8979486190100184
4
+ 2,-1,0.9025966516139985,0.8991112912317778
5
+ 3,-1,0.9027764763549494,0.8998067524459462
6
+ 4,-1,0.9030718202264396,0.9010020546460012
7
+ 5,-1,0.9041287939833499,0.9017253433578207
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Cross-Encoder for Quora Duplicate Questions Detection
2
+ This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class.
3
+
4
+ ## Training Data
5
+ 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.
6
+
7
+
8
+ ## Usage and Performance
9
+
10
+ Pre-trained models can be used like this:
11
+ ```
12
+ from sentence_transformers import CrossEncoder
13
+ model = CrossEncoder('model_name')
14
+ scores = model.predict([('Sentence 1', 'Sentence 2'), ('Sentence 3', 'Sentence 4')])
15
+ ```
16
+
17
+ The model will predict scores for the pairs `('Sentence 1', 'Sentence 2')` and `('Sentence 3', 'Sentence 4')`.
18
+
19
+ You can use this model also without sentence_transformers and by just using Transformers ``AutoModel`` class
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-05,
21
+ "max_position_embeddings": 514,
22
+ "model_type": "roberta",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 1,
26
+ "type_vocab_size": 1,
27
+ "vocab_size": 50265
28
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd8cddb9f6ddf924f91a1cc3c2bf83973a483a936654259d389ed1e7c56711d2
3
+ size 498676169
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_max_length": 512, "special_tokens_map_file": "final-models/ce-roberta-base-mnli/special_tokens_map.json", "full_tokenizer_file": null}
vocab.json ADDED
The diff for this file is too large to render. See raw diff