nreimers commited on
Commit
45a65f3
1 Parent(s): 48a8a8b
CESoftmaxAccuracyEvaluator_AllNLI-dev_results.csv ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,Accuracy
2
+ 0,10000,0.8647301215851859
3
+ 0,20000,0.8722083736073664
4
+ 0,30000,0.8845195095894592
5
+ 0,40000,0.8869105153380475
6
+ 0,50000,0.8886910515338048
7
+ 0,-1,0.8922521239253193
8
+ 1,10000,0.8953553441522104
9
+ 1,20000,0.8956605789286259
10
+ 1,30000,0.898204202065422
11
+ 1,40000,0.9005443353512743
12
+ 1,50000,0.9018670193824083
13
+ 1,-1,0.9018670193824083
README.md ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ The model was trained on the [SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral.
6
+
7
+
8
+ ## Usage
9
+
10
+ Pre-trained models can be used like this:
11
+ ```python
12
+ from sentence_transformers import CrossEncoder
13
+ model = CrossEncoder('model_name')
14
+ scores = model.predict([('A man is eating pizza', 'A man eats something'), ('A black race car starts up in front of a crowd of people.', 'A man is driving down a lonely road.')])
15
+
16
+ #Convert scores to labels
17
+ label_mapping = ['contradiction', 'entailment', 'neutral']
18
+ labels = [label_mapping[score_max] for score_max in scores.argmax(axis=1)]
19
+ ```
20
+
21
+ ## Usage with Transformers AutoModel
22
+ You can use the model also directly with Transformers library (without SentenceTransformers library):
23
+ ```python
24
+ from transformers import AutoTokenizer, AutoModelForSequenceClassification
25
+ import torch
26
+
27
+ model = AutoModelForSequenceClassification.from_pretrained('model_name')
28
+ tokenizer = AutoTokenizer.from_pretrained('model_name')
29
+
30
+ features = tokenizer(['A man is eating pizza', 'A black race car starts up in front of a crowd of people.'], ['A man eats something', 'A man is driving down a lonely road.'], padding=True, truncation=True, return_tensors="pt")
31
+
32
+ model.eval()
33
+ with torch.no_grad():
34
+ scores = model(**features).logits
35
+ label_mapping = ['contradiction', 'entailment', 'neutral']
36
+ labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
37
+ print(labels)
38
+ ```
bpe_encoder.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caff5a98d15fd439255194f3fcfd41a7b276b500cdf69caba890ae242c498797
3
+ size 3918127
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-base",
3
+ "architectures": [
4
+ "DebertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "layer_norm_eps": 1e-07,
23
+ "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_type": "deberta",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "pooler_dropout": 0,
30
+ "pooler_hidden_act": "gelu",
31
+ "pooler_hidden_size": 768,
32
+ "pos_att_type": [
33
+ "c2p",
34
+ "p2c"
35
+ ],
36
+ "position_biased_input": false,
37
+ "relative_attention": true,
38
+ "type_vocab_size": 0,
39
+ "vocab_size": 50265
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ef040f1fba1b3ff1916e2dd02b3d73d161dd085907e5181ef26261d65df69f
3
+ size 556869824
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "model_max_length": 512, "name_or_path": "microsoft/deberta-base"}