BAAI/bge-m3 · Discussions

#96 opened 4 days ago by

michael-newsrx-com

Add exported onnx model 'model_qint8_avx512_vnni.onnx'

#95 opened 4 days ago by

Add exported onnx model 'model_O4.onnx'

#94 opened 4 days ago by

Add exported openvino model 'openvino_model_qint8_quantized.xml'

#93 opened 4 days ago by

Add exported openvino model 'openvino_model.xml'

#92 opened 4 days ago by

checkpoint saving when fine tune

#91 opened 7 days ago by

NhatNguyen2101

如何下载模型权重到本地

#90 opened 10 days ago by

gintmr

transformers版本冲突问题

#89 opened 10 days ago by

rmqrmqrmq

Semantic for multilingual

#88 opened 16 days ago by

thatpham2k

How to get sparse and cobert from Triton Endpoint?

#87 opened 25 days ago by

snowneji

bge-large-v1.5-zh偶然出现了繁体中文如何解决？

#86 opened 28 days ago by

smartkit

中文文本多标签分类任务推荐使用哪个模型呢

#85 opened about 1 month ago by

OnePlusRay

Update README.md

#84 opened about 2 months ago by

Christianschott99

本地化bge-m3模型

#83 opened 2 months ago by

jy0719

Requesting example for getting multilingual embedding!

#82 opened 2 months ago by

gsvc

Regarding the Retention of Input Information

#81 opened 2 months ago by

aks05410

How can I get dense, colbert embeddings with transformers?

#80 opened 3 months ago by

Calvinnncy97

提示开发环境，生产环境怎么切呢

#79 opened 3 months ago by

vupdate

kNN search with e5-large data

#78 opened 3 months ago by

wshan13

🚩 Report

#76 opened 3 months ago by

ylllllllll

What is the difference between unified fine-tuning and dense fine-tuning?

#75 opened 3 months ago by

HonorOfKing

The GPU memory is not being released after inference?

#74 opened 3 months ago by

chf7410

Multilingual

#73 opened 4 months ago by

Sardar

1_Pooling 这个目录的作用是？

7

#72 opened 4 months ago by

Godsing

Adding `safetensors` variant of this model

#71 opened 4 months ago by

SFconvertbot

Transformers方式调用bge-m3是否有方法返回稀疏向量？

#70 opened 4 months ago by

imdoge

No sentence-transformers model found with name BAAI/bge-m3. Creating a new one with mean pooling.

4

#69 opened 5 months ago by

hhgz

How did you train m3-retromae?

#66 opened 5 months ago by

hotchpotch

If deploy m3 and m3 raranker model on a same gpu service，will it improve the gpu efficiency in the concurrent request environment

#65 opened 5 months ago by

seetimee

[AUTOMATED] Model Memory Requirements

#64 opened 5 months ago by

model-sizer-bot

I have question on result.

#62 opened 6 months ago by

Methodfunc

Model size

#60 opened 6 months ago by

Juli784

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

#59 opened 6 months ago by

DracoDev

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

#58 opened 6 months ago by

bobox

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

#57 opened 6 months ago by

DracoDev

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

8

#56 opened 6 months ago by

DracoDev

Issue: Semantic Similarity Score

#55 opened 6 months ago by

linhphanff

不同平台向量化后结果有差异

#54 opened 6 months ago by

compute_score 问题

#53 opened 6 months 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 6 months ago by

panjiayi

生产中使用API问题

#51 opened 6 months ago by

如何运行模型

#49 opened 6 months ago by

how to use trainer 'resume_from_checkpoint'?

#48 opened 6 months ago by

COCO0414

Reduce dimension of colbert vector

#47 opened 7 months ago by

feliciaAI

Adding `safetensors` variant of this model

#46 opened 7 months ago by

SFconvertbot

How to enable fp16 option in fintuning?

9

#45 opened 7 months ago by

comet24082002

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

#43 opened 7 months ago by

latuan

Is bge-m3 compatible with OpenCLIP?

#42 opened 7 months ago by

seanchenupland

Colbert Mode Usage

#41 opened 7 months ago by

pulkitchahar

Cuda out of memory