microsoft/Florence-2-large

#94 opened 27 days ago by

tonny123321

Fix: Importing from timm.models.layers is deprecated, now importing via timm.layers

#93 opened 2 months ago by

D4ve-R

Object of type Florence2LanguageConfig is not JSON serializable

#92 opened 2 months ago by

LINXIAO233

Florence-2 for German OCR

#91 opened 3 months ago by

elizanyambu

Multiline text are concated while using it as ocr

#90 opened 3 months ago by

iamvastava

Florence-2 Large Model Struggles with Color Recognition in Phrase Grounding Task

#89 opened 3 months ago by

DecTom

Scores for CAPTION_TO_PHRASE_GROUNDING

#88 opened 3 months ago by

LConstantine

Can I customize prompt for Florence-2 series models

#87 opened 3 months ago by

jinxxxx

Is Florence causal LLM？

#86 opened 4 months ago by

WenyaoZhang

REGION_TO_DESCRIPTION.

#85 opened 4 months ago by

abderrahimwaga

Quenstion about MIT Licence

#83 opened 4 months ago by

Matagi

Has there been some breaking changes ?

#81 opened 4 months ago by

skylord

Clarification on JSON Lines Dataset for Multi-Task Fine-Tuning of Florence-2

#78 opened 5 months ago by

mariaac

ImportError: cannot import name 'Florence2ForConditionalGeneration' from 'transformers' (/home/user/miniconda3/envs/florence_env/lib/python3.9/site-packages/transformers/init.py)

#76 opened 5 months ago by

dutta18

ValueError: If no `decoder_input_ids` or `decoder_inputs_embeds` are passed, `input_ids` cannot be `None`

#75 opened 5 months ago by

dutta18

Bad performance

#74 opened 6 months ago by

JJJYmmm

How to get the last_hidden_state of the florence2 Model , found no reference for the same.

#73 opened 6 months ago by

dutta18

Which torch version and transformer version to run this model?

#72 opened 6 months ago by

guyuchao

Flash_attn not able to build in the Local environment for the Model inference.

#71 opened 6 months ago by

siddharth-magesh

OCR Fine tuning on Florence-2

#70 opened 6 months ago by

ShanenThomas

what is the system requirements of this model like gpu or cpu??

#69 opened 6 months ago by

world-of-ai

Configurable vit parameters

#68 opened 6 months ago by

gmastrapas

Add task_prefix_attention_mask argument to _merge_input_ids_with_image_features for better padding handling

#66 opened 7 months ago by

pawlowskipawel

What does the suffix look like for training task 'REFERRING_EXPRESSION_SEGMENTATION'

#64 opened 7 months ago by

liougehooa

Update configuration_florence2.py

#62 opened 7 months ago by

zbing

Resolving Accuracy Issues in Chinese Output for Florence-2 Fine-Tuned with LoRA

#60 opened 8 months ago by

dqqAAA

Special tokens: purpose

#59 opened 8 months ago by

tdeboissiere

VQA Fine Tuning

#58 opened 8 months ago by

gragrisgrey

Batch vs Single Inference - Speed

#57 opened 8 months ago by

amaye15

How to get last hidden states?

#54 opened 8 months ago by

ZappY-AI

embeddings

#51 opened 8 months ago by

ajpuylea

Batch: inefficient memory

#50 opened 8 months ago by

SinanAkkoyun

Simple web server

#49 opened 8 months ago by

Navot

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

#48 opened 8 months ago by

shifeiwen

Update modeling_florence2.py

#47 opened 8 months ago by

xray1111

How to retrain the model with large max length?

7

#46 opened 8 months ago by

lucasjin

prompt engineering in Florence model

#45 opened 8 months ago by

vishalkatheriya

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

4

#44 opened 8 months ago by

Truc95

LayerNorm missing in Statedict of DatViT L

#43 opened 8 months ago by

Matagi

Running Inference on Video

#41 opened 8 months ago by

Haneesh-007

How to increase max token output ?

#40 opened 8 months ago by

Truc95

TypeError: Object of type Florence2LanguageConfig is not JSON serializable

4

#39 opened 9 months ago by

JiabaoWangTS

Scores with OCR

#38 opened 9 months ago by

matteocacciola

Regarding Confidence Score