Xiao
Shitao
AI & ML interests
None yet
Organizations
Shitao's activity
which model is used to generate the pos_scores and neg_scores in dataset?
2
#2 opened 2 days ago
by
fengwei
https://huggingface.co/bge-large-zh-v1.5/resolve/main/config.json DO NOT EXIST!
1
#23 opened 2 days ago
by
HuanGong
How did you train m3-retromae?
2
#66 opened 4 days ago
by
hotchpotch
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1661558090027-627c91ff4d0858f003553787.jpeg)
Add TEI support tag
1
#19 opened 5 days ago
by
philschmid
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1624629516652-5ff5d596f244529b3ec0fb89.png)
add text-embeddings-inference tag for easier endpoint deployment
#19 opened 5 days ago
by
MoritzLaurer
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1613511937628-5fb15d1e84389b139cf3b508.jpeg)
finetune bge-reranker-large in huggingface
2
#20 opened 12 days ago
by
ayyalaprem74
小白想问下最大输入长度是多少呢
2
#2 opened 16 days ago
by
19y
I have question on result.
1
#62 opened 25 days ago
by
Methodfunc
BGR-RERANKER-LARGE COMPUTATIONAL TIME
1
#18 opened 26 days ago
by
kazmi09
Cannot use the model following the ReadMe instructions
2
#61 opened 26 days ago
by
Matt2305
Request for Detailed Experimental Procedure For Spanish
1
#15 opened 28 days ago
by
wilfoderek
![](https://cdn-avatars.huggingface.co/v1/production/uploads/60bfa4237f75bb4d92557db9/8Vu3xJkqI59GrtoFrZbwj.jpeg)
NQ数据集上会出现不相关文档的相关性分数明显高于相关文档的情况
2
#17 opened 29 days ago
by
Xvhui
Model size
1
#60 opened about 1 month ago
by
Juli784
Long context embedding & chunking on same document with bge-m3
1
#59 opened about 1 month ago
by
DracoDev
Discussions about aggregate score computing (and question about banchmarks against colbert / splade)
1
#58 opened about 1 month ago
by
bobox
Maximum and Optimal Text Size That Can Be Vectror Embedded with bge-m3?
1
#57 opened about 1 month ago
by
DracoDev
Does bge-m3 understand html tages <h1>, <h2> , <code> etc?
8
#56 opened about 1 month ago
by
DracoDev
Missing Finetuning instruction for bge-reranker-v2-m3 ?
1
#17 opened about 1 month ago
by
jackkwok
文本相似度比较任务,Pooling策略的选择
1
#20 opened about 1 month ago
by
zhihengyu
For text similarity, which pooling strategy is better?
1
#17 opened about 1 month ago
by
zhihengyu
Multi-GPU at FP16? Examples. Large memory allocations.
1
#16 opened about 1 month ago
by
flash9001
Issue: Semantic Similarity Score
2
#55 opened about 1 month ago
by
linhphanff
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6447c3b9a478b20f1755872a/ZRVgZHyvM97QaBnXdOD2U.jpeg)
How to make it run on GPU?
1
#15 opened about 1 month ago
by
HarshalPa
不同平台向量化后结果有差异
1
#54 opened about 1 month ago
by
fffff123
compute_score 问题
1
#53 opened about 1 month ago
by
fffff123
How to use the ONNX format of BERT-based model bge-m3, how to load the model and output sentence embeddings.
1
#52 opened about 2 months ago
by
panjiayi
Optimizing Semantic Queries with bge-small-en Embedding Model: Contextual vs. Term-Based Queries
2
#13 opened about 2 months ago
by
kazmi09
生产中使用API问题
1
#51 opened about 2 months ago
by
fffff123
Adding ONNX file of this model
1
#44 opened 3 months ago
by
yashvardhan7
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65f49a96b97a85ae9d607715/9b1l_EY7pTEcQmMKFvstj.png)
onnx model don't output 'last_hidden_state' field
2
#50 opened about 2 months ago
by
redeve
怎么使用huggingface的inference API?
1
#16 opened about 2 months ago
by
Ethereal-Sakura
Deployment on Inference Endpoints (Dedicated)
5
#17 opened about 2 months ago
by
khalil235
对前后语序十分敏感
1
#15 opened about 2 months ago
by
Tonylin52
bge v1.5 的输出维度有多少
1
#19 opened about 2 months ago
by
dashi6174
支持langchain使用bge-m3模型吗?
7
#25 opened 4 months ago
by
Nicole828
score_ranges 0~1?
1
#14 opened about 2 months ago
by
duzhihua
llama_index 和 transformers 的版本有要求吗,会不会是因为这两个版本不兼容导致我下面的问题
1
#12 opened about 2 months ago
by
liiuiiii
bge-large-zh-v1.5 的输入文本长度
1
#18 opened 2 months ago
by
yy
Adding ONNX file of this model
#6 opened 2 months ago
by
yashvardhan7
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65f49a96b97a85ae9d607715/9b1l_EY7pTEcQmMKFvstj.png)
How to enable fp16 option in fintuning?
9
#45 opened 3 months ago
by
comet24082002
Inference API vs reranker.compute_score
1
#13 opened 4 months ago
by
yitao416
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6492419fa70ea227272c90dd/AdshYPPGfRVhVQC9cddK0.jpeg)
Got this error: AttributeError: 'NoneType' object has no attribute 'size'
3
#43 opened 3 months ago
by
latuan
Document length for v2-m3?
3
#9 opened 3 months ago
by
rag-perplexity
请问该v2-m3最大支持多少token
1
#8 opened 3 months ago
by
devillaws
Cuda out of memory
1
#40 opened 3 months ago
by
comet24082002
Evaluation for finetuned bge-m3 model
2
#39 opened 3 months ago
by
comet24082002
corss-lingual reranking
2
#6 opened 3 months ago
by
victorkeke
what is the difference between "bge-reranker-v2-m3" and "bge-reranker-large"?
2
#5 opened 3 months ago
by
JBW1999
Got this error: TypeError: SafeTensorsInfo.__init__() got an unexpected keyword argument 'sharded'
10
#37 opened 3 months ago
by
favioespinosav
Any 'small' version for this model with 384 dimensions ?
2
#36 opened 3 months ago
by
zaobao
Do I need to add the prefix "query: " and "passage: " to input texts?
5
#35 opened 3 months ago
by
zaobao
Add tags for finding this model more easily
1
#15 opened 3 months ago
by
tomaarsen
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6317233cc92fd6fee317e030/cJHSvvimr1kqgQfHOjO5n.png)
非常好的工作,请问有开源technique report的计划吗
1
#2 opened 3 months ago
by
rangehow
Using bge-m3 for clustering and search
1
#33 opened 3 months ago
by
talavivi
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/0opJtOpWj1-PddvZ68Bqy.jpeg)
Sampling Negative Examples for training bge-m3
3
#32 opened 3 months ago
by
mehti
模型有几个输出?
1
#7 opened 3 months ago
by
Jeromeblue
Will the component models be available separately?
1
#31 opened 3 months ago
by
Alex-Libryo