Downloads · 30 days
48
1% of all-time downloads
mpnet-base-snli-mnli
symanto/mpnet-base-snli-mnli
mpnet-base-snli-mnli is a zero-shot classification model from symanto. Use it when you need labels you did not train the model on. It is set up for transformers.
A cross-attention NLI model trained for zero-shot and few-shot text classification.
All-time downloads
4.3K
Public
Parameters
109M
1.3 GB on disk
Likes
5
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 50%
Parameter types
How the weights are stored.
F32109M · 100%
Try a prompt
Model card
From the Hugging Face model README
A cross-attention NLI model trained for zero-shot and few-shot text classification.
The base model is mpnet-base, trained with the code from here; on SNLI and MNLI.
Usage:
from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch
import numpy as np
model = AutoModelForSequenceClassification.from_pretrained("symanto/mpnet-base-snli-mnli")
tokenizer = AutoTokenizer.from_pretrained("symanto/mpnet-base-snli-mnli")
input_pairs = [("I like this pizza.", "The sentence is positive."), ("I like this pizza.", "The sentence is negative.")]
inputs = tokenizer(["</s></s>".join(input_pair) for input_pair in input_pairs], return_tensors="pt")
logits = model(**inputs).logits
probs = torch.softmax(logits, dim=1).tolist()
print("probs", probs)
np.testing.assert_almost_equal(probs, [[0.86, 0.14, 0.00], [0.16, 0.15, 0.69]], decimal=2)
- Task
- Zero-Shot Classification
- Library
- transformers
- Type
- mpnet
- Languages
- en
- Created
- Mar 2, 2022
- Updated
- Jul 6, 2023