microsoft/Florence-2-large

#50 opened over 1 year ago by

SinanAkkoyun

Simple web server

🔥 2

#49 opened almost 2 years ago by

Navot

What is the impact of reducing the size of the input image of the Davit image part

#48 opened almost 2 years ago by

shifeiwen

Update modeling_florence2.py

#47 opened almost 2 years ago by

xray1111

How to retrain the model with large max length?

➕🔥 3

7

#46 opened almost 2 years ago by

lucasjin

prompt engineering in Florence model

👍➕ 10

#45 opened almost 2 years ago by

vishalkatheriya

Assert config.vision_config.model_type == 'davit', 'only DaViT is supported for now'

#44 opened almost 2 years ago by

Glider95

LayerNorm missing in Statedict of DatViT L

#43 opened almost 2 years ago by

Matagi

Running Inference on Video

#41 opened almost 2 years ago by

Haneesh-007

How to increase max token output ?

➕ 1

#40 opened almost 2 years ago by

Glider95

TypeError: Object of type Florence2LanguageConfig is not JSON serializable

#39 opened almost 2 years ago by

JiabaoWangTS

Scores with OCR

➕🔥 5

#38 opened almost 2 years ago by

matteocacciola

Regarding Confidence Score

👀👍 33

#36 opened almost 2 years ago by

Haneesh-007

ValueError: Could not load model microsoft/Florence-2-large with any of the following classes.

➕ 2

#35 opened almost 2 years ago by

Dhruv

hey, im new to huggingface,

#34 opened almost 2 years ago by

coolkid891273

Multimodal Tokenizer Question

#33 opened almost 2 years ago by

Nano1337

Fine-tuning for multiple tasks strategy

👍👀 6

#32 opened almost 2 years ago by

gennarino80

Swift now supports inference, training, and deployment of the Florence models.

❤️ 1

#31 opened almost 2 years ago by

hu5enpai

Question about continue pretrain on Florence large base model with more data

#30 opened almost 2 years ago by

lucasjin

Update README.md

#29 opened almost 2 years ago by

huggingface369

TypeError: Object of type Florence2LanguageConfig is not JSON serializable

7

#28 opened almost 2 years ago by

ShravanP

unexpected keyword argument 'loss' - Fine tuning for CAPTIONS

#27 opened almost 2 years ago by

ksooklall

Which image format is preferred? Error during inference

#26 opened almost 2 years ago by

skye0402

Not passing attention_mask in model.generate

#25 opened almost 2 years ago by

hcy511

Release Dataset

👍🤗 78

#24 opened almost 2 years ago by

SinanAkkoyun

CPU inference

#22 opened almost 2 years ago by

KeilahElla

Please add to llama.cpp and ollama

👍🤝 18

#21 opened almost 2 years ago by

KeilahElla

Few shot prompting for object detection

🤝👀 7

#20 opened almost 2 years ago by

aswanthkrshna

How to Finetune?

👍👀 18

#19 opened almost 2 years ago by

vody-am

Segment multiple same objects in the Image

➕👀 9

#18 opened almost 2 years ago by

moaabid

load model from local files, disabling flash_attn, OSError: We couldn't connect to 'https://huggingface.co'

#15 opened almost 2 years ago by

wa99

Safetensors weights?

#14 opened almost 2 years ago by

nizar-naitlho

Wrong bounding boxes

👀🔥 3

#13 opened almost 2 years ago by

aleablu

dynamic module utils error -- requires flash_attn

#11 opened almost 2 years ago by

sidward

Segmentation Issue with identifying multiples, or contiguous objects

#10 opened almost 2 years ago by

EnragedAntelope

What does the output coordinate format?

6

#9 opened almost 2 years ago by

lucasjin

Running on macOS with Metal

#7 opened almost 2 years ago by

christianweyer

How does this version compare with Paligemma

👀 4