From 68508e92fbb3e160a01fa100494d0ce8e6152695 Mon Sep 17 00:00:00 2001 From: jhen Date: Sun, 28 Jul 2024 16:27:44 +0800 Subject: [PATCH] docs(readme): update `Obtain the model` section --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index ccf3017a..67ce54a8 100644 --- a/README.md +++ b/README.md @@ -31,6 +31,7 @@ Add proguard rule if it's enabled in project (android/app/proguard-rules.pro): You can search HuggingFace for available models (Keyword: [`GGUF`](https://huggingface.co/search/full-text?q=GGUF&type=model)). +<<<<<<< Updated upstream For create a GGUF model manually, for example in Llama 2: Download the Llama 2 model @@ -61,6 +62,9 @@ make quantize # quantize the model to 4-bits (using q4_0 method) ./quantize ./models/7B/ggml-model-f16.gguf ./models/7B/ggml-model-q4_0.gguf q4_0 ``` +======= +For get a GGUF model or quantize manually, see [`Prepare and Quantize`](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#prepare-and-quantize) section in llama.cpp. +>>>>>>> Stashed changes ## Usage