From 154e0d75fccf1784fe9ff6fd76a630b66563da3d Mon Sep 17 00:00:00 2001 From: Kawrakow <48489457+ikawrakow@users.noreply.github.com> Date: Sat, 27 Jul 2024 07:55:01 +0200 Subject: Merge mainline llama.cpp (#3) * Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow --- examples/infill/README.md | 1 + 1 file changed, 1 insertion(+) (limited to 'examples/infill/README.md') diff --git a/examples/infill/README.md b/examples/infill/README.md index 74f42d2f..810a0c5e 100644 --- a/examples/infill/README.md +++ b/examples/infill/README.md @@ -15,6 +15,7 @@ In this section, we cover the most commonly used options for running the `infill - `-i, --interactive`: Run the program in interactive mode, allowing you to provide input directly and receive real-time responses. - `-n N, --n-predict N`: Set the number of tokens to predict when generating text. Adjusting this value can influence the length of the generated text. - `-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. +- `--spm-infill`: Use Suffix/Prefix/Middle pattern for infill (instead of Prefix/Suffix/Middle) as some models prefer this. ## Input Prompts -- cgit v1.2.3