antoinelouis commited on
Commit
ebd6aad
1 Parent(s): 3325e06

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -33,7 +33,7 @@ Then you can use the model like this:
33
  from sentence_transformers import CrossEncoder
34
  pairs = [('Query', 'Paragraph1'), ('Query', 'Paragraph2') , ('Query', 'Paragraph3')]
35
 
36
- model = CrossEncoder('crossencoder-electra-base-french-europeana-cased-discriminator-mmarcoFR')
37
  scores = model.predict(pairs)
38
  print(scores)
39
  ```
@@ -46,8 +46,8 @@ Without [sentence-transformers](https://www.SBERT.net), you can use the model as
46
  from transformers import AutoTokenizer, AutoModelForSequenceClassification
47
  import torch
48
 
49
- model = AutoModelForSequenceClassification.from_pretrained('crossencoder-electra-base-french-europeana-cased-discriminator-mmarcoFR')
50
- tokenizer = AutoTokenizer.from_pretrained('crossencoder-electra-base-french-europeana-cased-discriminator-mmarcoFR')
51
 
52
  pairs = [('Query', 'Paragraph1'), ('Query', 'Paragraph2') , ('Query', 'Paragraph3')]
53
  features = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt')
@@ -69,7 +69,7 @@ Below, we compare the model performance with other cross-encoder models fine-tun
69
  |---:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------:|-------------:|---------:|------------:|------------:|------------:|-------------:|
70
  | 1 | [crossencoder-camembert-base-mmarcoFR](https://huggingface.co/antoinelouis/crossencoder-camembert-base-mmarcoFR) | 443MB | 35.65 | 50.44 | 82.95 | 91.50 | 96.80 | 98.80 |
71
  | 2 | [crossencoder-mMiniLMv2-L12-H384-distilled-from-XLMR-Large-mmarcoFR](https://huggingface.co/antoinelouis/crossencoder-mMiniLMv2-L12-H384-distilled-from-XLMR-Large-mmarcoFR) | 471MB | 34.37 | 51.01 | 82.23 | 90.60 | 96.45 | 98.40 |
72
- | 3 | [crossencoder-mmarcoFR-mMiniLMv2-L12-H384-v1-mmarcoFR](https://huggingface.co/antoinelouis/crossencoder-mmarcoFR-mMiniLMv2-L12-H384-v1-mmarcoFR) | 471MB | 34.22 | 49.20 | 81.70 | 90.90 | 97.10 | 98.90 |
73
  | 4 | [crossencoder-mpnet-base-mmarcoFR](https://huggingface.co/antoinelouis/crossencoder-mpnet-base-mmarcoFR) | 438MB | 29.68 | 46.13 | 80.45 | 87.90 | 93.15 | 96.60 |
74
  | 5 | [crossencoder-distilcamembert-base-mmarcoFR](https://huggingface.co/antoinelouis/crossencoder-distilcamembert-base-mmarcoFR) | 272MB | 27.28 | 43.71 | 80.30 | 89.10 | 95.55 | 98.60 |
75
  | 6 | **crossencoder-electra-base-french-europeana-cased-discriminator-mmarcoFR** | 443MB | 28.32 | 45.28 | 79.22 | 87.15 | 93.15 | 95.75 |
 
33
  from sentence_transformers import CrossEncoder
34
  pairs = [('Query', 'Paragraph1'), ('Query', 'Paragraph2') , ('Query', 'Paragraph3')]
35
 
36
+ model = CrossEncoder('antoinelouis/crossencoder-electra-base-french-europeana-cased-discriminator-mmarcoFR')
37
  scores = model.predict(pairs)
38
  print(scores)
39
  ```
 
46
  from transformers import AutoTokenizer, AutoModelForSequenceClassification
47
  import torch
48
 
49
+ model = AutoModelForSequenceClassification.from_pretrained('antoinelouis/crossencoder-electra-base-french-europeana-cased-discriminator-mmarcoFR')
50
+ tokenizer = AutoTokenizer.from_pretrained('antoinelouis/crossencoder-electra-base-french-europeana-cased-discriminator-mmarcoFR')
51
 
52
  pairs = [('Query', 'Paragraph1'), ('Query', 'Paragraph2') , ('Query', 'Paragraph3')]
53
  features = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt')
 
69
  |---:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------:|-------------:|---------:|------------:|------------:|------------:|-------------:|
70
  | 1 | [crossencoder-camembert-base-mmarcoFR](https://huggingface.co/antoinelouis/crossencoder-camembert-base-mmarcoFR) | 443MB | 35.65 | 50.44 | 82.95 | 91.50 | 96.80 | 98.80 |
71
  | 2 | [crossencoder-mMiniLMv2-L12-H384-distilled-from-XLMR-Large-mmarcoFR](https://huggingface.co/antoinelouis/crossencoder-mMiniLMv2-L12-H384-distilled-from-XLMR-Large-mmarcoFR) | 471MB | 34.37 | 51.01 | 82.23 | 90.60 | 96.45 | 98.40 |
72
+ | 3 | [crossencoder-mMiniLMv2-L12-H384-mmarco-mmarcoFR](https://huggingface.co/antoinelouis/crossencoder-mMiniLMv2-L12-H384-mmarco-mmarcoFR) | 471MB | 34.22 | 49.20 | 81.70 | 90.90 | 97.10 | 98.90 |
73
  | 4 | [crossencoder-mpnet-base-mmarcoFR](https://huggingface.co/antoinelouis/crossencoder-mpnet-base-mmarcoFR) | 438MB | 29.68 | 46.13 | 80.45 | 87.90 | 93.15 | 96.60 |
74
  | 5 | [crossencoder-distilcamembert-base-mmarcoFR](https://huggingface.co/antoinelouis/crossencoder-distilcamembert-base-mmarcoFR) | 272MB | 27.28 | 43.71 | 80.30 | 89.10 | 95.55 | 98.60 |
75
  | 6 | **crossencoder-electra-base-french-europeana-cased-discriminator-mmarcoFR** | 443MB | 28.32 | 45.28 | 79.22 | 87.15 | 93.15 | 95.75 |