Downloads · 30 days
65
0% of all-time downloads
distilbert-base-uncased-mnli
optimum/distilbert-base-uncased-mnli
distilbert-base-uncased-mnli is a zero-shot classification model from optimum. Use it when you need labels you did not train the model on. It is set up for transformers.
This is the uncased DistilBERT model fine-tuned on Multi-Genre Natural Language Inference (MNLI) dataset for the zero-shot classification task. The model is not case-sensitive, i.e., it does not make a difference betw…
All-time downloads
15.6K
Public
Repo size
268 MB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.onnx268 MB · 100%
At a glance
- Task
- Zero-Shot Classification
- Library
- transformers
- Access
- Public
- Created
- Mar 24, 2022
- Updated
- Mar 24, 2022
- SHA
- f2a41159
Try a prompt
Datasets
Model card
From the Hugging Face model README
ONNX convert typeform/distilbert-base-uncased-mnli
Conversion of typeform/distilbert-base-uncased-mnli
This is the uncased DistilBERT model fine-tuned on Multi-Genre Natural Language Inference (MNLI) dataset for the zero-shot classification task. The model is not case-sensitive, i.e., it does not make a difference between "english" and "English".
Training
Training is done on a p3.2xlarge AWS EC2 instance (1 NVIDIA Tesla V100 GPUs), with the following hyperparameters:
$ run_glue.py \
--model_name_or_path distilbert-base-uncased \
--task_name mnli \
--do_train \
--do_eval \
--max_seq_length 128 \
--per_device_train_batch_size 16 \
--learning_rate 2e-5 \
--num_train_epochs 5 \
--output_dir /tmp/distilbert-base-uncased_mnli/
Evaluation results
| Task | MNLI | MNLI-mm |
|---|---|---|
| 82.0 | 82.0 |
- Task
- Zero-Shot Classification
- Library
- transformers
- Languages
- en
- Created
- Mar 24, 2022
- Updated
- Mar 24, 2022