From 1f07fe501fb9483cb4c1dcfadb3b614ee1ca8dbd Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Sun, 31 Mar 2024 12:51:50 +1100
Subject: [PATCH] Updated Home (markdown)

---
 Home.md | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Home.md b/Home.md
index 9cb5164..31b5e39 100644
--- a/Home.md
+++ b/Home.md
@@ -115,6 +115,15 @@ ALLOWED_QUANTS = \
 }
 ```
 
+### Manually saving to GGUF
+Firstly use the terminal and do:
+```bash
+git clone https://github.com/ggerganov/llama.cpp
+cd llama.cpp && make clean && LLAMA_CUBLAS=1 make all -j
+pip install gguf protobuf
+```
+Then follow the steps at https://rentry.org/llama-cpp-conversions#merging-loras-into-a-model
+
 ### Evaluation Loop - also OOM or crashing.
 Set the trainer settings for evaluation to:
 ```python