Microsoft LLM Models

There are 127 Open Source LLM Models by Microsoft

phi 4

Text Generation

Phi 3.5 mini instruct

Text Generation

resnet 50

Image Classification

Florence 2 large

Image Text To Text

mattergen

phi 2

Text Generation

Phi 3 mini 4k instruct

Text Generation

Phi 3.5 vision instruct

Image Text To Text

Phi 3 mini 128k instruct

Text Generation

Phi 3 vision 128k instruct

Text Generation

Florence 2 base

Image Text To Text

Florence 2 large ft

Image Text To Text

Omni Parser

Image Text To Text

phi 4 gguf

Text Generation

speecht5_tts

Text To Speech

maira 2

Text Generation

Dialo G P T medium

Text Generation

deberta v3 base

Fill Mask

trocr base handwritten

Image To Text

trocr large handwritten

Image To Text

wavlm large

Feature Extraction

phi 1_5

Text Generation

phi 1

Text Generation

llava med v1.5 mistral 7b

Image Text To Text

Biomed N L P Biomed B E R T base uncased abstract fulltext

Fill Mask

Biomed N L P Biomed B E R T base uncased abstract

Fill Mask

Dialo G P T large

Text Generation

Dialo G P T small

Text Generation

Multilingual Mini L M L12 H384

Text Classification

beit large patch16 224 pt22k

Image Classification

codebert base mlm

Fill Mask

deberta base

Fill Mask

deberta v2 xlarge mnli

Text Classification

deberta v2 xlarge

Fill Mask

deberta v2 xxlarge

Fill Mask

deberta v3 large

Fill Mask

infoxlm large

Fill Mask

layoutlm base uncased

layoutlmv2 base uncased

layoutxlm base

mdeberta v3 base

Fill Mask

mpnet base

Fill Mask

swin tiny patch4 window7 224

Image Classification

trocr base printed

Image To Text

trocr large printed

Image To Text

trocr small handwritten

Image To Text

wavlm base plus

Feature Extraction

dit base

dit base finetuned rvlcdip

Image Classification

tapex large finetuned wtq

Table Question Answering

resnet 152

Image Classification

unixcoder base

Feature Extraction

layoutlmv3 base

layoutlmv3 large

Biomed V L P C X R B E R T general

Fill Mask

Biomed V L P C X R B E R T specialized

Fill Mask

swinv2 tiny patch4 window16 256

Image Classification

swinv2 base patch4 window16 256

Image Classification

layoutlmv3 base chinese

xclip base patch32

Video Classification

xclip base patch16

Video Classification

xclip large patch14

Video Classification

xclip base patch16 zero shot

Video Classification

conditional detr resnet 50

Object Detection

table transformer detection

Object Detection

table transformer structure recognition

Object Detection

biogpt

Text Generation

git base coco

Image To Text

Promptist

Text Generation

git large coco

Image To Text

speecht5_asr

Automatic Speech Recognition

speecht5_vc

Audio To Audio

speecht5_hifigan

Bio G P T Large

Text Generation

Bio G P T Large Pub Med Q A

Text Generation

Biomed C L I P Pub Med B E R T_256 vit_base_patch16_224

Zero Shot Image Classification

rad dino

Image Feature Extraction

graphcodebert base

Fill Mask

aurora

Biomed Parse

Phi 3.5 vision instruct onnx

codebert base

Feature Extraction

table transformer structure recognition v1.1 all

Object Detection

kosmos 2.5

Text2text Generation

Phi 3.5 Mo E instruct

Text Generation

L L M2 C L I P E V A02 L 14 336

Zero Shot Image Classification

Orca 2 13b

Text Generation

Phi 3 vision 128k instruct onnx

Vid Tok

beit base patch16 224 pt22k ft22k

Image Classification

deberta v3 xsmall

Fill Mask

swin base patch4 window7 224 in22k

Image Classification

tapex base finetuned wikisql

Table Question Answering

tapex base

Table Question Answering

tapex large finetuned tabfact

Table Question Answering

trocr small printed

Image To Text

unispeech sat base 100h libri ft

Automatic Speech Recognition

wavlm base plus sd

tapex base finetuned wtq

Table Question Answering

swinv2 tiny patch4 window8 256

Image Classification

markuplm base finetuned websrc

Question Answering

codereviewer

Text2text Generation

G O D E L v1_1 large seq2seq

Text2text Generation

git base

Image To Text

git base vqav2

Visual Question Answering

Phi 3 medium 128k instruct

Text Generation

xclip large patch14 16 frames

Video Classification

Biomed V L P Bio Vi L T

Feature Extraction

Phi 3 medium 4k instruct

Text Generation

Sports B E R T

Fill Mask

deberta base mnli

Text Classification

layoutlmv2 large uncased

trocr base stage1

Image To Text

trocr large stage1

Image To Text

unihanlm base

Feature Extraction

xtremedistil l12 h384 uncased

Text Classification

xtremedistil l6 h256 uncased

Text Classification

Biomed N L P K R I S S B E R T Pub Med U M L S E L

Feature Extraction

swinv2 large patch4 window12to24 192to384 22kto1k ft

Image Classification

bloom deepspeed inference fp16

Feature Extraction

xclip base patch32 16 frames

Video Classification

trocr large str

Image To Text

Phi 3 mini 4k instruct onnx

Text Generation

kosmos 2 patch14 224

Image To Text

kosmos 2.5 chat

L L M2 C L I P Openai L 14 336

Zero Shot Classification

L L M2 C L I P Llama 3 8 B Instruct C C Finetuned

Zero Shot Classification