BAAI/bge-m3 · Discussions

#60 opened 3 days ago by

Juli784

Long context embedding & chunking on same document with bge-m3

#59 opened 5 days ago by

DracoDev

Discussions about aggregate score computing (and question about banchmarks against colbert / splade)

#58 opened 8 days ago by

bobox

Maximum and Optimal Text Size That Can Be Vectror Embedded with bge-m3?

#57 opened 10 days ago by

DracoDev

Does bge-m3 understand html tages <h1>, <h2> , <code> etc?

8

#56 opened 10 days ago by

DracoDev

Issue: Semantic Similarity Score

#55 opened 11 days ago by

linhphanff

不同平台向量化后结果有差异

#54 opened 16 days ago by

compute_score 问题

#53 opened 16 days ago by

How to use the ONNX format of BERT-based model bge-m3, how to load the model and output sentence embeddings.

#52 opened 17 days ago by

panjiayi

生产中使用API问题

#51 opened 19 days ago by

如何运行模型

#49 opened 21 days ago by

how to use trainer 'resume_from_checkpoint'?

#48 opened 24 days ago by

COCO0414

Reduce dimension of colbert vector

#47 opened about 1 month ago by

feliciaAI

Adding `safetensors` variant of this model

#46 opened about 2 months ago by

SFconvertbot

How to enable fp16 option in fintuning?

7

#45 opened about 2 months ago by

comet24082002

Got this error: AttributeError: 'NoneType' object has no attribute 'size'

#43 opened about 2 months ago by

latuan

Is bge-m3 compatible with OpenCLIP?

#42 opened about 2 months ago by

seanchenupland

Colbert Mode Usage

#41 opened about 2 months ago by

pulkitchahar

Cuda out of memory

#40 opened about 2 months ago by

comet24082002

Evaluation for finetuned bge-m3 model

#39 opened about 2 months ago by

comet24082002

Adding `safetensors` variant of this model

#38 opened about 2 months ago by

SFconvertbot

Got this error: TypeError: SafeTensorsInfo.init() got an unexpected keyword argument 'sharded'

10

#37 opened about 2 months ago by

favioespinosav

Any 'small' version for this model with 384 dimensions ?

#36 opened 2 months ago by

zaobao

Do I need to add the prefix "query: " and "passage: " to input texts?

5

#35 opened 2 months ago by

zaobao

Endless loop with multiple GPU ?

#34 opened 2 months ago by

Grosper

Using bge-m3 for clustering and search

#33 opened 2 months ago by

talavivi

Sampling Negative Examples for training bge-m3

#32 opened 2 months ago by

mehti

Will the component models be available separately?

#31 opened 2 months ago by

Alex-Libryo

Reranker

4

#30 opened 2 months ago by

Totole

list of languages supported

#29 opened 2 months ago by

andrew123456789

convert token to the original form

#28 opened 3 months ago by

DAIEF

m3需要和base做merge吗

#27 opened 3 months ago by

biaodiluer

Which matrix did you use for Benchmarks from the open-source community

#26 opened 3 months ago by

DAIEF

支持langchain使用bge-m3模型吗？

7

#25 opened 3 months ago by

Nicole828

This models is also best for Finnish in my comparison

#24 opened 3 months ago by

RASMUS

Code and some results for comparing with other embedding models on multilingual data

#23 opened 3 months ago by

Yannael

入参之间会影响embedding的结果吗

#22 opened 3 months ago by

biaodiluer

关于多阶段训练

#21 opened 3 months ago by

xxxcliu

bge-M3和baai_general_embedding是什么关系

#20 opened 3 months ago by

biaodiluer

How many GPU's are required to fine tuning bge-m3 over 1 million tripplets ?

#18 opened 3 months ago by

wilfoderek

How do you suggest using Colbert vectors ?

#16 opened 3 months ago by

EquinoxElahin

may be little bugs

#14 opened 3 months ago by

prudant

serving the model

#13 opened 3 months ago by

prudant

Datasets

#11 opened 4 months ago by

AbdelkerimDassi

Issue while finetuning embedding model because of use_reentrant = True

#10 opened 4 months ago by

DamianS89

Optimize inference speed

5

#9 opened 4 months ago by

CoolWP

OOM occurs in the process of converting the model to torchscript. I have a question about this issue.

#8 opened 4 months ago by

LeeJungHoon

Add benchmark to MTEB

5

#7 opened 4 months ago by

sam-gab

base model

16

#6 opened 4 months ago by

ambivalent02

It is now working colab..