kweinmeister
/

distilbert-mnli

Sentence Similarity

text-classification

text-embeddings-inference

Inference Endpoints

Model card Files Files and versions Community

Model Card for distilbert-base-uncased

Model Details

Model Description

A fine-tuned version of distilbert/distilbert-base-uncased using the nyu-mll/multi_nli 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: 208

Safetensors

Model size

67M params

Tensor type

F32

·

Inference Examples

Sentence Similarity

Inference API (serverless) does not yet support transformers models for this pipeline type.

Model tree for kweinmeister/distilbert-mnli

Base model

distilbert/distilbert-base-uncased

Finetuned

(6830)

this model

Merges

Dataset used to train kweinmeister/distilbert-mnli

Evaluation results

accuracy on nyu-mll/multi_nli
self-reported

0.820

View on Papers With Code