Zero-Shot Classification
Transformers
PyTorch
Safetensors
English
deberta-v2
text-classification
deberta-v3-base
deberta-v3
deberta
nli
natural-language-inference
multitask
multi-task
pipeline
extreme-multi-task
extreme-mtl
tasksource
zero-shot
rlhf
Eval Results
Inference Endpoints
sileod commited on
Commit
1b90d50
1 Parent(s): e50d067

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -318,9 +318,9 @@ pipeline_tag: zero-shot-classification
318
 
319
  This is [DeBERTa-v3-base](https://hf.co/microsoft/deberta-v3-base) fine-tuned with multi-task learning on 600 tasks of the [tasksource collection](https://github.com/sileod/tasksource/).
320
  This checkpoint has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI), and can be used for:
321
- - Zero-shot entailment-based classification pipeline (similar to bart-mnli), see [ZS].
322
  - Natural language inference [NLI]
323
- - Hundreds of other tasks with tasksource-adapters, see [TA].
324
  - Further fine-tuning with a new task or tasksource task (classification, token classification or multiple-choice) [FT].
325
 
326
  # [ZS] Zero-shot classification pipeline
 
318
 
319
  This is [DeBERTa-v3-base](https://hf.co/microsoft/deberta-v3-base) fine-tuned with multi-task learning on 600 tasks of the [tasksource collection](https://github.com/sileod/tasksource/).
320
  This checkpoint has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI), and can be used for:
321
+ - Zero-shot entailment-based classification pipeline (similar to bart-mnli) [ZS].
322
  - Natural language inference [NLI]
323
+ - Hundreds of other tasks with tasksource-adapters [TA].
324
  - Further fine-tuning with a new task or tasksource task (classification, token classification or multiple-choice) [FT].
325
 
326
  # [ZS] Zero-shot classification pipeline