kweinmeister
/

distilbert-snli

Sentence Similarity

text-classification

Eval Results (legacy)

text-embeddings-inference

Model card Files Files and versions

Model Card for distilbert-snli

Model Details

Model Description

A fine-tuned version of distilbert/distilbert-base-uncased using the stanford-nlp/snli dataset.

Developed by: Karl Weinmeister
Language(s) (NLP): en
License: apache-2.0
Finetuned from model [optional]: distilbert/distilbert-base-uncased

Training Hyperparameters

Training regime: The model was trained for 5 epochs with batch size 128.

Downloads last month: 4

Safetensors

Model size

67M params

Tensor type

F32

·

Model tree for kweinmeister/distilbert-snli

Base model

distilbert/distilbert-base-uncased

Finetuned

this model

Evaluation results

accuracy on stanford-nlp/snli
self-reported

0.898