llm-embed-jina

llm-embed-jina copied to clipboard

jina-embeddings-v2-large-en: release?

1

Thank you for your work in building these models. Do you have a timeline for the release of [jina-embeddings-v2-large-en](https://huggingface.co/jinaai/jina-embeddings-v2-large-en). It has been pending since v2 was announced last year.

dwlmt

Support CUDA gpus

1

Hi Simon, I was just looking at https://huggingface.co/datasets/SciPhi/AgentSearch-V1 1 Billion passages and 50 Million documents with jina embeddings. So it motivated me to add cuda support to your jina plugin....

irthomasthomas

Add: jina-embeddingts-v2-base-de

1

Jina just released jina-embeddings-v2-base-de. Adding support to this plugin might be as easy as adding it to the list of available list of models. Dimensions vary from en versions, though....

minthemiddle

Question: Memory consumption

4

When running the `embed-multi` command below in my home directory for the test, the `llm` process periodically consumes large amounts of RAM, up to 27GB. Is this expected? These models...

daddy32

Dependency conflict installing (using brew-installed LLM)

4

Hi! I have problems installing version 0.1.2. I am using macOS 14.0 on Apple Silicon. LLM is installed with Brew and works for chatting with default models. ``` ~ llm...

kamidev