vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

common: llama_load_model_from_url using --model-url (#6098)

Browse source 
* common: llama_load_model_from_url with libcurl dependency

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Pierrick Hymbert 2024-03-17 19:12:37 +01:00 • committed by GitHub
parent cd776c37c9
commit d01b3c4c32
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
16 changed files with 397 additions and 55 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/server/README.md
View file

@ -20,6 +20,7 @@ The project is under active development, and we are [looking for feedback and co
- `-tb N, --threads-batch N`: Set the number of threads to use during batch and prompt processing. If not specified, the number of threads will be set to the number of threads used for generation.
- `--threads-http N`: number of threads in the http server pool to process requests (default: `max(std::thread::hardware_concurrency() - 1, --parallel N + 2)`)
- `-m FNAME`, `--model FNAME`: Specify the path to the LLaMA model file (e.g., `models/7B/ggml-model.gguf`).
- `-mu MODEL_URL --model-url MODEL_URL`: Specify a remote http url to download the file (e.g https://huggingface.co/ggml-org/models/resolve/main/phi-2/ggml-model-q4_0.gguf).
- `-a ALIAS`, `--alias ALIAS`: Set an alias for the model. The alias will be returned in API responses.
- `-c N`, `--ctx-size N`: Set the size of the prompt context. The default is 512, but LLaMA models were built with a context of 2048, which will provide better results for longer input/inference. The size may differ in other models, for example, baichuan models were build with a context of 4096.
- `-ngl N`, `--n-gpu-layers N`: When compiled with appropriate support (currently CLBlast or cuBLAS), this option allows offloading some layers to the GPU for computation. Generally results in increased performance.