answerdotai/ModernBERT-base

#79 opened 5 months ago by

Padajno

Dataset

#78 opened 6 months ago by

hakim1510

fine tune model and convert to onnx

#77 opened 7 months ago by

Gerald001

Embeddings - last_hidden_state vs hidden_state[-1]

#76 opened 7 months ago by

technicalanalyst

Training with transformers API

#75 opened 8 months ago by

Padajno

gpu requirements

#73 opened 8 months ago by

Gerald001

An error occurred (ModelError) when calling the InvokeEndpoint operation load has model type `modernbert`

#70 opened 8 months ago by

devs9

sagemaker not supporting modernBERT trained model with transformers 4.49.0

5

#69 opened 8 months ago by

devs9

Can you add a Tensorflow compatible model?

#68 opened 8 months ago by

kgolden317

multilang support

➕ 7

#67 opened 8 months ago by

ulasarikaya

modernBERT training learning rate=0 and validation_loss=nan

➕ 6

#66 opened 9 months ago by

devs9

LayerNorm.init() got an unexpected keyword argument 'bias'

#65 opened 9 months ago by

clabluo

ModernBert vs Bert for text classification

#64 opened 9 months ago by

Joseph2805

Question about MLDR Evaluation Metrics in ModernBERT Paper

#62 opened 9 months ago by

WoutDeRijck

I have trained a multilingual version of ModernBert

🤗 👍 2

#60 opened 9 months ago by

neavo

nan or 0.0 loss when training with flash attention

16

#59 opened 9 months ago by

roadtoagi

Modernbert with Golang

#58 opened 9 months ago by

Thibault-Requesty

ModernBERT fails to work without FlashAttention !

🔥 1

#56 opened 9 months ago by

benhachem

Import fails on AWS lamba instance.

#55 opened 9 months ago by

obeijbom

Performance vs the original architecture on approximate original data sizes (BooksCorpus/Wikipedia)

#54 opened 10 months ago by

tollefj

Speed Benchmarks with MPS Backend

#47 opened 10 months ago by

mlburnham

Continual pre-training for multilingual support (extend embedding matrix and tokenizer)

➕ 9

#46 opened 10 months ago by

ibotana

Encountering Error: cannot import name 'shard_checkpoint' from 'transformers.modeling_utils'

#44 opened 10 months ago by

rkabir

ModernBertModel works on the CPU but fails on the GPU

#43 opened 10 months ago by

rudigung

ModernBERT-base-chinese

#42 opened 10 months ago by

ZBW

Error: RuntimeError: Failed to import transformers.models.modernbert.modeling_modernbert because of the following error (look up to see its traceback): Windows not yet supported for torch.compile

6

#40 opened 10 months ago by

JoAmps42i

ModernBART wen?

👍 3

6

#38 opened 10 months ago by

Fizzarolli

Pretraining Using HF Tokenizers and Transformers

👍 1

#36 opened 10 months ago by

akhooli

Update README.md

#35 opened 10 months ago by

solankibhargav

Unpadding and Sequence Packing inference example?

#34 opened 10 months ago by

denti

Interview Request: Thoughts on Model Documentation

#33 opened 10 months ago by

evatang

Training Data?

#32 opened 10 months ago by

binarymax

What is the position of this model in MTEB leaderboard?

#31 opened 10 months ago by

deepak-banka

tokenizer

#24 opened 10 months ago by

ulasarikaya

RuntimeError: Failed to import transformers.models.modernbert.modeling_modernbert

➕ 3

#21 opened 10 months ago by

SantoshHF

Pretraining data cutoff?

#17 opened 10 months ago by

ytsaig

How to use ModernBERT with the AutoModelForQuestionAnswering class?

➕ 3

#15 opened 10 months ago by

sraj

Is ModernBERT already fine-tuned for IR tasks?

#13 opened 10 months ago by

belerico

Question about output embedding vector of ModernBERT

#12 opened 10 months ago by

Youm9602

ModernBert for multi-vector embeddings

#11 opened 10 months ago by

admarcosai

How to use ModernBERT as a sentence transformer?

30

#9 opened 10 months ago by

hungrybiker

multilingual

👍 2

#8 opened 10 months ago by

ale-volpe

Is this model meant for full bfloat16, AMP bfloat16 or no bfloat16?

👍 2

#7 opened 10 months ago by

umarbutler

# Fine-tuning ModernBERT on a Large Dataset with Masked Language Modelling

👍 4

#6 opened 10 months ago by

ssmits

Precisions about the config properties wrt the paper