Downloads · 30 days
6
11% of all-time downloads
bert-base-uncased-mnli-2-labels
an-eve/bert-base-uncased-mnli-2-labels
bert-base-uncased-mnli-2-labels is a text classification model from an-eve. Use it when you need a label for a piece of text. It is set up for transformers.
The baseline NLI model is a fine-tuned version of bert-base-uncased for Text Classifacation on the MNLI dataset , with entailments as label 0 and all others (neutral or contradiction) as label 1.
All-time downloads
54
Public
Parameters
109M
438 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jan 4, 2024
- Updated
- Jan 4, 2024
- SHA
- 19c0fa5e
Try a prompt
Datasets
Model card
From the Hugging Face model README
Description
The baseline NLI model is a fine-tuned version of bert-base-uncased for Text Classifacation on the MNLI dataset , with entailments as label 0 and all others (neutral or contradiction) as label 1.
Two classes:
-
entailment: 0
-
non-entailment: 1
Results on the validation set
MNLI: 90.07%
MNLI-mm: 90.08%
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- optimizer: "adamw_torch"
- lr_scheduler_type: linear
- num_epochs: 4
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- Languages
- en
- Created
- Jan 4, 2024
- Updated
- Jan 4, 2024