Resources

View closed (17)

Maximuim input tokens: 1024 or 8k ?!

#37 opened about 23 hours ago by

Amir313

How to reproduce jina-reranker-v2-base-multilinguale's evaluation results on BEIR or MLDR dataset?

#36 opened 5 days ago by

Nicola007

Update model metadata to set pipeline tag to the new `text-ranking` and tags to `sentence-transformers`

#35 opened 2 months ago by

tomaarsen

position embedding 1026 while sequence length allowed 1024?

#34 opened 2 months ago by

wahaha1987

Finetuning possible?

#33 opened 5 months ago by

Florianoli

ONNX conversion code

#32 opened 6 months ago by

kovcharenko51

Request: DOI

#31 opened 7 months ago by

H-Hosseini

how to create ONNX version of a modified pytorch version of this reranker?

#30 opened 8 months ago by

tiendung

js example cannot be abnormal

#29 opened 8 months ago by

Johnlyon

Supported languages

👍 1

#28 opened 8 months ago by

cahya

Long Context Size Chunk

#27 opened 8 months ago by

CVHvn

HugginFace text-embeddings-inference (TEI) support

#26 opened 9 months ago by

leversberg

Jina rerank api response time suddenly very slow, and on instances not responding at all

#25 opened 9 months ago by

arabikar

vocab.txt missing with jina reranker file

➕ 2

#23 opened 9 months ago by

Anshu

How's the performance when query is english and docs are mainly in Japanese?

#22 opened 10 months ago by

shengluo

OSError: Consistency check failed: file should be of size 561622266 but has size 13542 ((…)ST4gkP16HvQ__&Key-Pair-Id=K34327DB1ZDDBL)

#21 opened 10 months ago by

lww929343413

"_amp_foreach_non_finite_check_and_unscale_cuda" not implemented for 'BFloat16'

#19 opened 11 months ago by

zyzz0625

data did not match any variant of untagged enum PyPreTokenizerTypeWrapper at line 69 column 3

🚀 3

#17 opened 11 months ago by

sigridjineth

Running inference code on README.md has an error

#15 opened 11 months ago by

sigridjineth

How to use sigmoid() to filter irrelevant documents out

#11 opened 11 months ago by

shaunxu