jupyterjazz (Saba Sturua) – Community Activity

New activity in jinaai/jina-embeddings-v4 2 months ago

#73 opened 2 months ago by

New activity in jinaai/jina-embeddings-v4 3 months ago

#72 opened 3 months ago by

#65 opened 3 months ago by

New activity in jinaai/jina-embeddings-v4 4 months ago

#61 opened 4 months ago by

#63 opened 4 months ago by

#62 opened 4 months ago by

#60 opened 4 months ago by

#1 opened 4 months ago by

New activity in jinaai/jina-embeddings-v4 4 months ago

#57 opened 4 months ago by

#55 opened 4 months ago by

#53 opened 4 months ago by

New activity in jinaai/jina-embeddings-v4 5 months ago

#45 opened 5 months ago by

#52 opened 5 months ago by

#50 opened 5 months ago by

#49 opened 5 months ago by

#35 opened 5 months ago by

#51 opened 5 months ago by

#48 opened 5 months ago by

#47 opened 5 months ago by

#46 opened 5 months ago by

Saba Sturua

Saba Sturua

AI & ML interests

Organizations

jupyterjazz's activity

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

Preferred dtype: bfloat16 or float16?

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

'MultiAdapterLinear' object has no attribute '_cast_input_dtype'

How to save image embeddings in vector DB?

A toy example to use the model with hf transformers

Database

compatible with Transformers？

RAG system configuration question

Is there a size limit for the input image?

How do I quantize jina-embeddings-v4?

Reduce Console Logging

using Jina models in a RAG stack

GGUF version

Apple silicon / Non-CUDA support (flash_attn)

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

fix-disabling-flash-attn

how do i adjust the output dimension when using vllm ?

How to fine tune this model?

fix-task-setting-and-st-load