Resources

View closed (45)

Repeated "Internal Server Error" Response In API test page

#78 opened 4 days ago by

cr3306

国内调用经常会因网络问题，报错

#76 opened about 1 month ago by

zyw0605688

Cannot use apply_chat_template because this processor does not have a chat template.

👀 1

#75 opened about 2 months ago by

zhusl-cpu

Don't treat a string starting by http as an image link if there is a space in it

#74 opened about 2 months ago by

LPN64

[Bug] Getting repeated [RID: ] Internal server error during encoding in add. errors

#73 opened about 2 months ago by

Publishing

Preferred dtype: bfloat16 or float16?

#72 opened about 2 months ago by

mihaidusmanu

Does the encode method in sentence_transformers support base64-encoded image input?

👀 1

#71 opened about 2 months ago by

zhangxiangchn

store embedding token into Ventor DB

👍 1

#69 opened 2 months ago by

theeranop

How do I increase the output dimension when using Late Chunking ?

#68 opened 3 months ago by

EthanPhelps

Encoding Image and Text Together

👍 1

#66 opened 3 months ago by

dawn17

How to perform retrieval using fused [image, text] as the input query?

#65 opened 3 months ago by

ququwowo

no apply_rotary_emb function

#64 opened 3 months ago by

galazzo

How to save image embeddings in vector DB?

#63 opened 3 months ago by

Day1Kim

A toy example to use the model with hf transformers

#62 opened 3 months ago by

AliKhajegiliM

'MultiAdapterLinear' object has no attribute '_cast_input_dtype'

#61 opened 3 months ago by

shkwon12

Database

#60 opened 3 months ago by

nPeppon

RAG system configuration question

#57 opened 3 months ago by

Day1Kim

Is there a size limit for the input image?

#55 opened 4 months ago by

frankfan1979

How can I resolve a 'No embeddings were generated' error during fine-tuning with SentenceTransformer?

#54 opened 4 months ago by

delojmkt

How do I quantize jina-embeddings-v4?

❤️ 1

#53 opened 4 months ago by

Kong-Mei

using Jina models in a RAG stack

#52 opened 4 months ago by

giovanni-elcam

GGUF version

🚀 👍 4

#50 opened 4 months ago by

alainlizotte

Apple silicon / Non-CUDA support (flash_attn)

#49 opened 4 months ago by

simonsv

how do i adjust the output dimension when using vllm ?

#48 opened 4 months ago by

vikyw89

How to fine tune this model?

#47 opened 4 months ago by

ququwowo

I am curious how you got around qwens non-comercial license for Qwen2.5-VL-3B-Instruct?

#44 opened 4 months ago by

amazingvince

Results on MMEB(V1/V2)?

#43 opened 4 months ago by

TMRBMWK

How to generate embedding of a document like PDF?

#42 opened 4 months ago by

long124

jina-embeddings-v4 vs clip-v2

#41 opened 4 months ago by

Waln

Congrats on the release of V4! your model is currently the SOTA on The Arabic RAG Leaderboard

❤️ 4

#39 opened 4 months ago by

MohamedRashad

onnx export

👍 1

#37 opened 4 months ago by

25pwn

load model failed: Exception: expected value at line 1 column 1

#36 opened 4 months ago by

vivian345

Runtimerror: "You are attempting to use Flash Attention 2.0 with a model not initialized on GPU."

#35 opened 4 months ago by

dophys