Downloads · 30 days
9K
1% of all-time downloads
MoritzLaurer/DeBERTa-v3-xsmall-mnli-fever-anli-ling-binary
DeBERTa-v3-xsmall-mnli-fever-anli-ling-binary is a zero-shot classification model from MoritzLaurer. Use it when you need labels you did not train the model on. It is set up for transformers. The card lists the license as mit.
This model was trained on 782 357 hypothesis-premise pairs from 4 NLI datasets: MultiNLI, Fever-NLI, LingNLI and ANLI.
Downloads · 30 days
9K
1% of all-time downloads
All-time downloads
1.2M
Public
Parameters
70.8M
941 MB on disk
Likes
7
Public
Click a slice to open those files.
.onnx371 MB · 39%
How the weights are stored.
F3270.8M · 100%
From the Hugging Face model README
This model was trained on 782 357 hypothesis-premise pairs from 4 NLI datasets: MultiNLI, Fever-NLI, LingNLI and ANLI.
Note that the model was trained on binary NLI to predict either "entailment" or "not-entailment". This is specifically designed for zero-shot classification, where the difference between "neutral" and "contradiction" is irrelevant.
The base model is DeBERTa-v3-xsmall from Microsoft. The v3 variant of DeBERTa substantially outperforms previous versions of the model by including a different pre-training objective, see the DeBERTa-V3 paper.
For highest performance (but less speed), I recommend using https://huggingface.co/MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli.
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
model_name = "MoritzLaurer/DeBERTa-v3-xsmall-mnli-fever-anli-ling-binary"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
premise = "I first thought that I liked the movie, but upon second thought it was actually disappointing."
hypothesis = "The movie was good."
input = tokenizer(premise, hypothesis, truncation=True, return_tensors="pt")
output = model(input["input_ids"].to(device)) # device = "cuda:0" or "cpu"
prediction = torch.softmax(output["logits"][0], -1).tolist()
label_names = ["entailment", "not_entailment"]
prediction = {name: round(float(pred) * 100, 1) for pred, name in zip(prediction, label_names)}
print(prediction)
This model was trained on 782 357 hypothesis-premise pairs from 4 NLI datasets: MultiNLI, Fever-NLI, LingNLI and ANLI.
DeBERTa-v3-xsmall-mnli-fever-anli-ling-binary was trained using the Hugging Face trainer with the following hyperparameters.
training_args = TrainingArguments(
num_train_epochs=5, # total number of training epochs
learning_rate=2e-05,
per_device_train_batch_size=32, # batch size per device during training
per_device_eval_batch_size=32, # batch size for evaluation
warmup_ratio=0.1, # number of warmup steps for learning rate scheduler
weight_decay=0.06, # strength of weight decay
fp16=True # mixed precision training
)
The model was evaluated using the binary test sets for MultiNLI, ANLI, LingNLI and the binary dev set for Fever-NLI (two classes instead of three). The metric used is accuracy.
| dataset | mnli-m-2c | mnli-mm-2c | fever-nli-2c | anli-all-2c | anli-r3-2c | lingnli-2c |
|---|---|---|---|---|---|---|
| accuracy | 0.925 | 0.922 | 0.892 | 0.676 | 0.665 | 0.888 |
| speed (text/sec, CPU, 128 batch) | 6.0 | 6.3 | 3.0 | 5.8 | 5.0 | 7.6 |
| speed (text/sec, GPU Tesla P100, 128 batch) | 473 | 487 | 230 | 390 | 340 | 586 |
Please consult the original DeBERTa paper and literature on different NLI datasets for potential biases.
If you use this model, please cite: Laurer, Moritz, Wouter van Atteveldt, Andreu Salleras Casas, and Kasper Welbers. 2022. ‘Less Annotating, More Classifying – Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT - NLI’. Preprint, June. Open Science Framework. https://osf.io/74b8k.
If you have questions or ideas for cooperation, contact me at m{dot}laurer{at}vu{dot}nl or LinkedIn
Note that DeBERTa-v3 was released on 06.12.21 and older versions of HF Transformers seem to have issues running the model (e.g. resulting in an issue with the tokenizer). Using Transformers>=4.13 might solve some issues.