MoritzLaurer HF staff commited on
Commit
229ec22
1 Parent(s): 757d9bc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -12,10 +12,10 @@ license: mit
12
  # Model description: deberta-v3-large-zeroshot-v1.1-all-33
13
  The model is designed for zero-shot classification with the Hugging Face pipeline.
14
 
15
- The model can do one universal task: determine whether a hypothesis is `true` or `not_true`
16
- given a text (also called `entailment` vs. `not_entailment`).
17
  This task format is based on the Natural Language Inference task (NLI).
18
- The task is so universal that any classification task can be reformulated into the task.
19
 
20
  A detailed description of how the model was trained and how it can be used is available in this paper: [link to be added]
21
 
@@ -123,8 +123,8 @@ Please consult the original DeBERTa paper and the papers for the different datas
123
  ## License
124
  The base model (DeBERTa-v3) is published under the MIT license.
125
  The datasets the model was fine-tuned on are published under a diverse set of licenses.
126
- The following spreadsheet provides an overview of the non-NLI datasets used for fine-tuning.
127
- The spreadsheets contains information on licenses, the underlying papers etc.: https://github.com/MoritzLaurer/zeroshot-classifier/blob/main/datasets_overview.csv
128
 
129
  ## Citation
130
  If you use this model academically, please cite:
 
12
  # Model description: deberta-v3-large-zeroshot-v1.1-all-33
13
  The model is designed for zero-shot classification with the Hugging Face pipeline.
14
 
15
+ The model can do one universal classification task: determine whether a hypothesis is "true" or "not true" given a text
16
+ (`entailment` vs. `not_entailment`).
17
  This task format is based on the Natural Language Inference task (NLI).
18
+ The task is so universal that any classification task can be reformulated into this task.
19
 
20
  A detailed description of how the model was trained and how it can be used is available in this paper: [link to be added]
21
 
 
123
  ## License
124
  The base model (DeBERTa-v3) is published under the MIT license.
125
  The datasets the model was fine-tuned on are published under a diverse set of licenses.
126
+ The following table provides an overview of the non-NLI datasets used for fine-tuning,
127
+ information on licenses, the underlying papers etc.: https://github.com/MoritzLaurer/zeroshot-classifier/blob/main/datasets_overview.csv
128
 
129
  ## Citation
130
  If you use this model academically, please cite: