apepkuss79's picture
Update README.md
3e8b377 verified
metadata
base_model: intfloat/e5-mistral-7b-instruct
license: mit
model_creator: intfloat
quantized_by: Second State Inc.
language: en

E5-Mistral-7B-Instruct-Embedding-GGUF

Original Model

intfloat/e5-mistral-7b-instruct

Run with LlamaEdge

  • LlamaEdge version: v0.8.2 and above

  • Prompt template

    • Prompt type: embedding
  • Context size: 4096

  • Run as LlamaEdge service

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:e5-mistral-7b-instruct-Q5_K_M.gguf \
      llama-api-server.wasm \
      --prompt-template embedding \
      --ctx-size 4096 \
      --model-name e5-mistral-7b-instruct
    

Quantized GGUF Models

Name Quant method Bits Size Use case
e5-mistral-7b-instruct-Q2_K.gguf Q2_K 2 2.72 GB smallest, significant quality loss - not recommended for most purposes
e5-mistral-7b-instruct-Q3_K_L.gguf Q3_K_L 3 3.82 GB small, substantial quality loss
e5-mistral-7b-instruct-Q3_K_M.gguf Q3_K_M 3 3.52 GB very small, high quality loss
e5-mistral-7b-instruct-Q3_K_S.gguf Q3_K_S 3 3.16 GB very small, high quality loss
e5-mistral-7b-instruct-Q4_0.gguf Q4_0 4 4.11 GB legacy; small, very high quality loss - prefer using Q3_K_M
e5-mistral-7b-instruct-Q4_K_M.gguf Q4_K_M 4 4.37 GB medium, balanced quality - recommended
e5-mistral-7b-instruct-Q4_K_S.gguf Q4_K_S 4 4.14 GB small, greater quality loss
e5-mistral-7b-instruct-Q5_0.gguf Q5_0 5 5.00 GB legacy; medium, balanced quality - prefer using Q4_K_M
e5-mistral-7b-instruct-Q5_K_M.gguf Q5_K_M 5 5.13 GB large, very low quality loss - recommended
e5-mistral-7b-instruct-Q5_K_S.gguf Q5_K_S 5 5.00 GB large, low quality loss - recommended
e5-mistral-7b-instruct-Q6_K.gguf Q6_K 6 5.94 GB very large, extremely low quality loss
e5-mistral-7b-instruct-Q8_0.gguf Q8_0 8 7.7 GB very large, extremely low quality loss - not recommended
e5-mistral-7b-instruct-f16.gguf f16 8 14.5 GB very large, extremely low quality loss - not recommended

Quantized with llama.cpp b2334