BAAI/bge-m3 · Discussions

#53 opened 10 months ago by

fffff123

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

#52 opened 10 months ago by

panjiayi

生产中使用API问题

#51 opened 10 months ago by

fffff123

如何运行模型

#49 opened 10 months ago by

fffff123

how to use trainer 'resume_from_checkpoint'?

#48 opened 10 months ago by

COCO0414

Reduce dimension of colbert vector

#47 opened 11 months ago by

feliciaAI

Adding `safetensors` variant of this model

#46 opened 11 months ago by

SFconvertbot

How to enable fp16 option in fintuning?

9

#45 opened 11 months ago by

comet24082002

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

#43 opened 11 months ago by

latuan

Is bge-m3 compatible with OpenCLIP?

#42 opened 11 months ago by

seanchenupland

Colbert Mode Usage

#41 opened 11 months ago by

pulkitchahar

Cuda out of memory

#40 opened 11 months ago by

comet24082002

Evaluation for finetuned bge-m3 model

#39 opened 11 months ago by

comet24082002

Adding `safetensors` variant of this model

#38 opened 11 months ago by

SFconvertbot

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

10

#37 opened 11 months ago by

favioespinosav

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

4

#36 opened 12 months ago by

zaobao

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

5

#35 opened 12 months ago by

zaobao

Endless loop with multiple GPU ?

#34 opened 12 months ago by

Grosper

Using bge-m3 for clustering and search

#33 opened 12 months ago by

talavivi

Will the component models be available separately?

#31 opened 12 months ago by

libryo-ai

Reranker

4

#30 opened 12 months ago by

Totole

list of languages supported

#29 opened 12 months ago by

andrew123456789

convert token to the original form

#28 opened 12 months ago by

DAIEF

m3需要和base做merge吗

#27 opened 12 months ago by

biaodiluer

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

#26 opened about 1 year ago by

DAIEF

支持langchain使用bge-m3模型吗？

8

#25 opened about 1 year ago by

Nicole828

This models is also best for Finnish in my comparison

#24 opened about 1 year ago by

RASMUS

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

#23 opened about 1 year ago by

Yannael

入参之间会影响embedding的结果吗

#22 opened about 1 year ago by

biaodiluer

关于多阶段训练

#21 opened about 1 year ago by

xxxcliu

bge-M3和baai_general_embedding是什么关系

#20 opened about 1 year ago by

biaodiluer

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

#18 opened about 1 year ago by

wilfoderek

How do you suggest using Colbert vectors ?

#16 opened about 1 year ago by

EquinoxElahin

may be little bugs

#14 opened about 1 year ago by

prudant

serving the model

#13 opened about 1 year ago by

prudant

Datasets

#11 opened about 1 year ago by

AbdelkerimDassi

Issue while finetuning embedding model because of use_reentrant = True

#10 opened about 1 year ago by

DamianS89

Optimize inference speed

5

#9 opened about 1 year ago by

CoolWP

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

#8 opened about 1 year ago by

LeeJungHoon

Add benchmark to MTEB

6

#7 opened about 1 year ago by

sam-gab

base model

16

#6 opened about 1 year ago by

ambivalent02

It is now working colab..

#5 opened about 1 year ago by

LeeJungHoon

中文Dense retrieval性能与BGE V1.5相比如何？

#3 opened about 1 year ago by

TianyuLLM

OOMS on 8 GB GPU, is it normal?