From: tslmy <redacted>
Date: Thu, 6 Jul 2023 16:17:50 +0000 (-0700)
Subject: alpaca.sh : update model file name (#2074)
X-Git-Tag: gguf-v0.4.0~509
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=a17a2683d8fdb899ba497d0c28ccafb28c62efb6;p=pkg%2Fggml%2Fsources%2Fllama.cpp

alpaca.sh : update model file name (#2074)

The original file name, `ggml-alpaca-7b-q4.bin`, implied the first-generation GGML. After the breaking changes (mentioned in https://github.com/ggerganov/llama.cpp/issues/382), `llama.cpp` requires GGML V3 now. Those model files are named `*ggmlv3*.bin`. We should change the example to an actually working model file, so that this thing is more likely to run out-of-the-box for more people, and less people would waste time downloading the old Alpaca model.
---

diff --git a/examples/alpaca.sh b/examples/alpaca.sh
index aef207f3..8d2bae69 100755
--- a/examples/alpaca.sh
+++ b/examples/alpaca.sh
@@ -7,7 +7,7 @@
 cd `dirname $0`
 cd ..
 
-./main -m ./models/ggml-alpaca-7b-q4.bin \
+./main -m ./models/alpaca.13b.ggmlv3.q8_0.bin \
        --color \
        -f ./prompts/alpaca.txt \
        --ctx_size 2048 \