MoritzLaurer HF staff commited on
Commit
bddf8c5
1 Parent(s): a5d877f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -47,7 +47,7 @@ text = "Angela Merkel is a politician in Germany and leader of the CDU"
47
  hypothesis_template = "This text is about {}"
48
  classes_verbalized = ["politics", "economy", "entertainment", "environment"]
49
  zeroshot_classifier = pipeline("zero-shot-classification", model="MoritzLaurer/deberta-v3-large-zeroshot-v2.0") # change the model identifier here
50
- output = zeroshot_classifier(text, classes_verbalised, hypothesis_template=hypothesis_template, multi_label=False)
51
  print(output)
52
  ```
53
 
@@ -97,7 +97,7 @@ The main reference point is `facebook/bart-large-mnli` which is, at the time of
97
 
98
  These numbers indicate zeroshot performance, as no data from these datasets was added in the training mix.
99
  Note that models without a "`-c`" in the title were evaluated twice: one run without any data from these 28 datasets to test pure zeroshot performance (the first number in the respective column) and
100
- the final run including up to 500 training data points per class from each of the 28 datasets (the second number in brackets in the column). No model was trained on test data.
101
 
102
  Details on the different datasets are available here: https://github.com/MoritzLaurer/zeroshot-classifier/blob/main/v1_human_data/datasets_overview.csv
103
 
 
47
  hypothesis_template = "This text is about {}"
48
  classes_verbalized = ["politics", "economy", "entertainment", "environment"]
49
  zeroshot_classifier = pipeline("zero-shot-classification", model="MoritzLaurer/deberta-v3-large-zeroshot-v2.0") # change the model identifier here
50
+ output = zeroshot_classifier(text, classes_verbalized, hypothesis_template=hypothesis_template, multi_label=False)
51
  print(output)
52
  ```
53
 
 
97
 
98
  These numbers indicate zeroshot performance, as no data from these datasets was added in the training mix.
99
  Note that models without a "`-c`" in the title were evaluated twice: one run without any data from these 28 datasets to test pure zeroshot performance (the first number in the respective column) and
100
+ the final run including up to 500 training data points per class from each of the 28 datasets (the second number in brackets in the column, "fewshot"). No model was trained on test data.
101
 
102
  Details on the different datasets are available here: https://github.com/MoritzLaurer/zeroshot-classifier/blob/main/v1_human_data/datasets_overview.csv
103