metadata

base_model: jinaai/jina-embeddings-v2-base-de
license: apache-2.0
model_creator: jinaai
quantized_by: Second State Inc.
language:
  - de
  - en
inference: false

jina-embeddings-v2-base-de-GGUF

Original Model

jinaai/jina-embeddings-v2-base-de

Run with LlamaEdge

LlamaEdge version: v0.14.17
Prompt template
- Prompt type: embedding
Context size: 8192
Embedding dim: 768

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:jina-embeddings-v2-base-de-f16.gguf \
  llama-api-server.wasm \
  --prompt-template embedding \
  --ctx-size 8192 \
  --model-name jina-embeddings-v2-base-de

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
jina-embeddings-v2-base-de-Q2_K.gguf	Q2_K	2	82.5 MB	smallest, significant quality loss - not recommended for most purposes
jina-embeddings-v2-base-de-Q3_K_L.gguf	Q3_K_L	3	101 MB	small, substantial quality loss
jina-embeddings-v2-base-de-Q3_K_M.gguf	Q3_K_M	3	95.5 MB	very small, high quality loss
jina-embeddings-v2-base-de-Q3_K_S.gguf	Q3_K_S	3	89.7 MB	very small, high quality loss
jina-embeddings-v2-base-de-Q4_0.gguf	Q4_0	4	105 MB	legacy; small, very high quality loss - prefer using Q3_K_M
jina-embeddings-v2-base-de-Q4_K_M.gguf	Q4_K_M	4	109 MB	medium, balanced quality - recommended
jina-embeddings-v2-base-de-Q4_K_S.gguf	Q4_K_S	4	105 MB	small, greater quality loss
jina-embeddings-v2-base-de-Q5_0.gguf	Q5_0	5	119 MB	legacy; medium, balanced quality - prefer using Q4_K_M
jina-embeddings-v2-base-de-Q5_K_M.gguf	Q5_K_M	5	121 MB	large, very low quality loss - recommended
jina-embeddings-v2-base-de-Q5_K_S.gguf	Q5_K_S	5	119 MB	large, low quality loss - recommended
jina-embeddings-v2-base-de-Q6_K.gguf	Q6_K	6	134 MB	very large, extremely low quality loss
jina-embeddings-v2-base-de-Q8_0.gguf	Q8_0	8	173 MB	very large, extremely low quality loss - not recommended
jina-embeddings-v2-base-de-f16.gguf	f16	16	323 MB	very large, extremely low quality loss - not recommended

Quantized with llama.cpp b4273