Felipe97/llama-cpp-compiled

1---2base_model:3- {base_model}4---5# {model_name} GGUF6 7Recommended way to run this model:8 9```sh10llama-server -hf {namespace}/{model_name}-GGUF --embeddings11```12 13Then the endpoint can be accessed at http://localhost:8080/embedding, for14example using `curl`:15```console16curl --request POST \17    --url http://localhost:8080/embedding \18    --header "Content-Type: application/json" \19    --data '{{"input": "Hello embeddings"}}' \20    --silent21```22 23Alternatively, the `llama-embedding` command line tool can be used:24```sh25llama-embedding -hf {namespace}/{model_name}-GGUF --verbose-prompt -p "Hello embeddings"26```27 28#### embd_normalize29When a model uses pooling, or the pooling method is specified using `--pooling`,30the normalization can be controlled by the `embd_normalize` parameter.31 32The default value is `2` which means that the embeddings are normalized using33the Euclidean norm (L2). Other options are:34* -1 No normalization35*  0 Max absolute36*  1 Taxicab37*  2 Euclidean/L238* \>2 P-Norm39 40This can be passed in the request body to `llama-server`, for example:41```sh42    --data '{{"input": "Hello embeddings", "embd_normalize": -1}}' \43```44 45And for `llama-embedding`, by passing `--embd-normalize <value>`, for example:46```sh47llama-embedding -hf {namespace}/{model_name}-GGUF  --embd-normalize -1 -p "Hello embeddings"48```49