KBaba7/llama.cpp

1# llama.cpp/example/embedding2 3This example demonstrates generate high-dimensional embedding vector of a given text with llama.cpp.4 5## Quick Start6 7To get started right away, run the following command, making sure to use the correct path for the model you have:8 9### Unix-based systems (Linux, macOS, etc.):10 11```bash12./llama-embedding -m ./path/to/model --pooling mean --log-disable -p "Hello World!" 2>/dev/null13```14 15### Windows:16 17```powershell18llama-embedding.exe -m ./path/to/model --pooling mean --log-disable -p "Hello World!" 2>$null19```20 21The above command will output space-separated float values.22 23## extra parameters24### --embd-normalize $integer$25| $integer$ | description         | formula |26|-----------|---------------------|---------|27| $-1$      | none                |28| $0$       | max absolute int16  | $\Large{{32760 * x_i} \over\max \lvert x_i\rvert}$29| $1$       | taxicab             | $\Large{x_i \over\sum \lvert x_i\rvert}$30| $2$       | euclidean (default) | $\Large{x_i \over\sqrt{\sum x_i^2}}$31| $>2$      | p-norm              | $\Large{x_i \over\sqrt[p]{\sum \lvert x_i\rvert^p}}$32 33### --embd-output-format $'string'$34| $'string'$ | description                  |  |35|------------|------------------------------|--|36| ''         | same as before               | (default)37| 'array'    | single embeddings            | $[[x_1,...,x_n]]$38|            | multiple embeddings          | $[[x_1,...,x_n],[x_1,...,x_n],...,[x_1,...,x_n]]$39| 'json'     | openai style                 |40| 'json+'    | add cosine similarity matrix |41 42### --embd-separator $"string"$43| $"string"$   | |44|--------------|-|45| "\n"         | (default)46| "<#embSep#>" | for exemple47| "<#sep#>"    | other exemple48 49## examples50### Unix-based systems (Linux, macOS, etc.):51 52```bash53./llama-embedding -p 'Castle<#sep#>Stronghold<#sep#>Dog<#sep#>Cat' --pooling mean --embd-separator '<#sep#>' --embd-normalize 2  --embd-output-format '' -m './path/to/model.gguf' --n-gpu-layers 99 --log-disable 2>/dev/null54```55 56### Windows:57 58```powershell59llama-embedding.exe -p 'Castle<#sep#>Stronghold<#sep#>Dog<#sep#>Cat' --pooling mean --embd-separator '<#sep#>' --embd-normalize 2  --embd-output-format '' -m './path/to/model.gguf' --n-gpu-layers 99 --log-disable 2>/dev/null60```61