jina-embeddings-v3-Embedding-GGUF

Original Model

Run with LlamaEdge

LlamaEdge version: coming soon

Prompt template
- Prompt type: embedding
Embedding size: 32, 64, 128, 256, 512, 768, 1024

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:jina-embeddings-v3-f16.gguf \
  llama-api-server.wasm \
  --prompt-template embedding \
  --ctx-size 768 \
  --model-name jina-embeddings-v3

Quantized with llama.cpp b6311

Downloads last month: 723

GGUF

Model size

558M params

Architecture

jina-bert-v3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for second-state/jina-embeddings-v3-GGUF

Base model

jinaai/jina-embeddings-v3

Quantized

(4)

this model