nreimers commited on
Commit
6ed5194
1 Parent(s): 2c71c6f
CECorrelationEvaluator_sts-dev_results.csv ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ epoch,steps,Pearson_Correlation,Spearman_Correlation
2
+ 0,-1,0.9169803189330423,0.914689659080599
3
+ 1,-1,0.9184629642176918,0.9145474423018756
4
+ 2,-1,0.9140695557809773,0.911543895130673
5
+ 3,-1,0.9156662483528688,0.9134139344421147
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 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 514,
23
+ "model_type": "roberta",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "pad_token_id": 1,
27
+ "type_vocab_size": 1,
28
+ "vocab_size": 50265
29
+ }
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 sha256:03023f7dcd714c15ff27d534432a80d3bff78c9b50778a44b10585ef5fa7fd25
3
+ size 1421616585
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": "input-model/roberta-large-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