From 66a66a05a8c509e57e170659182f96165d2e8112 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Mon, 21 Aug 2023 22:11:00 +0300 Subject: [PATCH] readme : add notice about new file format ggml-ci --- README.md | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 7b72290e4..82e070ac3 100644 --- a/README.md +++ b/README.md @@ -9,11 +9,17 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++ -### 🚧 Incoming breaking change + refactoring: +### Hot topics -See PR https://github.com/ggerganov/llama.cpp/pull/2398 for more info. +A new file format has been introduced: [GGUF](https://github.com/ggerganov/llama.cpp/pull/2398) -To devs: avoid making big changes to `llama.h` / `llama.cpp` until merged +Last revision compatible with the old format: [dadbed9](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa) + +### Current `master` should be considered in Beta - expect some issues for a few days! + +### Be prepared to re-convert and / or re-quantize your GGUF models while this notice is up! + +### Issues with non-GGUF models will be considered with low priority! ----