中文Sign up

second-state/jina-embeddings-v2-base-de-GGUF

🤗 Hugging Face sourceapache-2.01.8 GBGGUF✓ 13 checksumsupdated today
Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo second-state/jina-embeddings-v2-base-de-GGUF ./model-folder
Needs a seeder →

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