Search⌘ K
AI Features

Default Models List

Explore the comprehensive list of default pretrained Hugging Face models used for natural language processing and computer vision tasks. This lesson helps you familiarize yourself with model options available within Hugging Face pipelines, serving as a practical reference for implementing various machine learning workflows in Python.

We'll cover the following...

This lesson now includes all major Hugging Face pipelines, giving you a handy reference for NLP and vision tasks.

Task Type

Model Name

Hugging Face Identifier

Domain

Fill-Mask (MLM)

BERT

bert-base-uncased

General-purpose

DeBERTa v3

microsoft/deberta-v3-base

Outperforms BERT-large on many tasks

RoBERTa

roberta-base

General-purpose

DistilBERT / DistilRoBERTa

distilbert-base-uncased

/

distilroberta-base

Lightweight, faster inference

BioBERT

dmis-lab/biobert-base-cased-v1.1

Biomedical domain

SciBERT

allenai/scibert_scivocab_uncased

Scientific literature

FinBERT

yiyanghkust/finbert-tone

Finance domain

LegalBERT

nlpaueb/legal-bert-base-uncased

Legal documents

XLM-RoBERTa

xlm-roberta-base

Multilingual

LaBSE

sentence-transformers/LaBSE

Cross-lingual embeddings

multilingual-e5

intfloat/multilingual-e5-large

Multilingual text embeddings

Text generation

GPT-2

gpt2

General-purpose generation

GPT-Neo

EleutherAI/gpt-neo-2.7B

Large open-source model

GPT-J

EleutherAI/gpt-j-6B

Higher-capacity open-source model

BLOOM

bigscience/bloom

Multi-lingual, large language model

Text summarization

BART

facebook/bart-large-cnn

General-purpose summarization

T5

t5-base

Multi-task text-to-text model

PEGASUS

google/pegasus-xsum

Summarization-focused, news

Translation

MarianMT

Helsinki-NLP/opus-mt-en-fr

Multilingual translation

M2M100

facebook/m2m100_418M

Multi-language translation

Question answering

BERT QA

bert-large-uncased-whole-word-masking-finetuned-squad

SQuAD fine-tuned

RoBERTa QA

deepset/roberta-base-squad2

SQuAD v2 fine-tuned

Image classification

ViT

google/vit-base-patch16-224

Patch-based transformer

DeiT

facebook/deit-base-patch16-224

Data-efficient ViT

Swin Transformer

microsoft/swin-tiny-patch4-window7-224

Hierarchical windowed attention

ConvNeXt

facebook/convnext-base-224

Next-gen CNN

CLIP

openai/clip-vit-base-patch32

Zero-shot, text-image

Object detection

DETR

facebook/detr-resnet-50

Transformer-based detection

DINO

facebook/dino-detr

Self-distillation improved DETR

Grounding-DINO

GroundingDINO

Text-prompted detection

OWL-ViT

google/owlvit-base-patch32

Open-vocabulary detection

YOLOS

hustvl/yolos-small

Pure transformer detection

DETA

DETA

Efficient transformer detection

Segmentation

SegFormer

nvidia/segformer-b0-finetuned-ade-512-512

Lightweight semantic segmentation

Mask2Former

facebook/mask2former-swin-base

Semantic, instance, panoptic

DETR Panoptic

facebook/detr-resnet-50-panoptic

Panoptic segmentation

UPerNet

open-mmlab/upernet-swin-base

High-quality semantic segmentation