upload
Browse files- CESoftmaxAccuracyEvaluator_AllNLI-dev_results.csv +25 -0
- README.md +69 -0
- added_tokens.json +1 -0
- config.json +45 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spm.model +3 -0
- tokenizer_config.json +1 -0
CESoftmaxAccuracyEvaluator_AllNLI-dev_results.csv
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch,steps,Accuracy
|
2 |
+
0,10000,0.8547082464262095
|
3 |
+
0,20000,0.8703769649488732
|
4 |
+
0,30000,0.8665106577809432
|
5 |
+
0,40000,0.8848756168286107
|
6 |
+
0,50000,0.8881314544437097
|
7 |
+
0,-1,0.8897593732512591
|
8 |
+
1,10000,0.8881314544437097
|
9 |
+
1,20000,0.8849264892913465
|
10 |
+
1,30000,0.8899628631022027
|
11 |
+
1,40000,0.8929643384036221
|
12 |
+
1,50000,0.8939817876583406
|
13 |
+
1,-1,0.8977463499007987
|
14 |
+
2,10000,0.8963727934069289
|
15 |
+
2,20000,0.8975428600498551
|
16 |
+
2,30000,0.89560970646589
|
17 |
+
2,40000,0.8975428600498551
|
18 |
+
2,50000,0.8963727934069289
|
19 |
+
2,-1,0.8986111817673094
|
20 |
+
3,10000,0.8990690339319326
|
21 |
+
3,20000,0.8986111817673094
|
22 |
+
3,30000,0.9000356107239151
|
23 |
+
3,40000,0.898865544080989
|
24 |
+
3,50000,0.8987129266927812
|
25 |
+
3,-1,0.899526886096556
|
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
pipeline_tag: zero-shot-classification
|
4 |
+
tags:
|
5 |
+
- microsoft/deberta-v3-small
|
6 |
+
datasets:
|
7 |
+
- multi_nli
|
8 |
+
- snli
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
license: apache-2.0
|
12 |
+
---
|
13 |
+
|
14 |
+
# Cross-Encoder for Natural Language Inference
|
15 |
+
This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class. This model is based on [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small)
|
16 |
+
|
17 |
+
## Training Data
|
18 |
+
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.
|
19 |
+
|
20 |
+
## Performance
|
21 |
+
- Accuracy on SNLI-test dataset: 91.65
|
22 |
+
- Accuracy on MNLI mismatched set: 87.55
|
23 |
+
|
24 |
+
For futher evaluation results, see [SBERT.net - Pretrained Cross-Encoder](https://www.sbert.net/docs/pretrained_cross-encoders.html#nli).
|
25 |
+
|
26 |
+
## Usage
|
27 |
+
|
28 |
+
Pre-trained models can be used like this:
|
29 |
+
```python
|
30 |
+
from sentence_transformers import CrossEncoder
|
31 |
+
model = CrossEncoder('cross-encoder/nli-deberta-v3-small')
|
32 |
+
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.')])
|
33 |
+
|
34 |
+
#Convert scores to labels
|
35 |
+
label_mapping = ['contradiction', 'entailment', 'neutral']
|
36 |
+
labels = [label_mapping[score_max] for score_max in scores.argmax(axis=1)]
|
37 |
+
```
|
38 |
+
|
39 |
+
## Usage with Transformers AutoModel
|
40 |
+
You can use the model also directly with Transformers library (without SentenceTransformers library):
|
41 |
+
```python
|
42 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
43 |
+
import torch
|
44 |
+
|
45 |
+
model = AutoModelForSequenceClassification.from_pretrained('cross-encoder/nli-deberta-v3-small')
|
46 |
+
tokenizer = AutoTokenizer.from_pretrained('cross-encoder/nli-deberta-v3-small')
|
47 |
+
|
48 |
+
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")
|
49 |
+
|
50 |
+
model.eval()
|
51 |
+
with torch.no_grad():
|
52 |
+
scores = model(**features).logits
|
53 |
+
label_mapping = ['contradiction', 'entailment', 'neutral']
|
54 |
+
labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
|
55 |
+
print(labels)
|
56 |
+
```
|
57 |
+
|
58 |
+
## Zero-Shot Classification
|
59 |
+
This model can also be used for zero-shot-classification:
|
60 |
+
```python
|
61 |
+
from transformers import pipeline
|
62 |
+
|
63 |
+
classifier = pipeline("zero-shot-classification", model='cross-encoder/nli-deberta-v3-small')
|
64 |
+
|
65 |
+
sent = "Apple just announced the newest iPhone X"
|
66 |
+
candidate_labels = ["technology", "sports", "politics"]
|
67 |
+
res = classifier(sent, candidate_labels)
|
68 |
+
print(res)
|
69 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"[MASK]": 128000}
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-small",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForSequenceClassification"
|
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-v2",
|
26 |
+
"norm_rel_ebd": "layer_norm",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 6,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"pooler_dropout": 0,
|
31 |
+
"pooler_hidden_act": "gelu",
|
32 |
+
"pooler_hidden_size": 768,
|
33 |
+
"pos_att_type": [
|
34 |
+
"p2c",
|
35 |
+
"c2p"
|
36 |
+
],
|
37 |
+
"position_biased_input": false,
|
38 |
+
"position_buckets": 256,
|
39 |
+
"relative_attention": true,
|
40 |
+
"share_att_key": true,
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.11.3",
|
43 |
+
"type_vocab_size": 0,
|
44 |
+
"vocab_size": 128100
|
45 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2930841dcaa813d1e04bf0d8bbb4415d795ed6e36719c6fffb613a3fd26faabc
|
3 |
+
size 567639154
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v3-small", "tokenizer_class": "DebertaV2Tokenizer", "model_max_length": 512}
|