From fa384cbfe38a5925878b13f2e848fd3983d860f6 Mon Sep 17 00:00:00 2001
From: metascroy <161522778+metascroy@users.noreply.github.com>
Date: Mon, 15 Apr 2024 17:43:19 -0700
Subject: [PATCH] switch to smaller model to speed up CI test (#210)

---
 .github/workflows/compile-gguf.yml | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/compile-gguf.yml b/.github/workflows/compile-gguf.yml
index 07abe2d95..651a87e97 100644
--- a/.github/workflows/compile-gguf.yml
+++ b/.github/workflows/compile-gguf.yml
@@ -35,15 +35,16 @@ jobs:
       - name: Download GGUF
         run: |
           mkdir gguf_files
-          export GGUF_PATH=gguf_files/llama-2-7b.Q4_0.gguf
+          export GGUF_PATH=gguf_files/TinyLlama-1.1B-openorca.Q4_0.gguf
           export TOKENIZER_PATH=gguf_files/tokenizer.model
-          wget -O ${GGUF_PATH} "https://huggingface.co/TheBloke/Llama-2-7B-GGUF/resolve/main/llama-2-7b.Q4_0.gguf?download=true"
+
+          wget -O ${GGUF_PATH} "https://huggingface.co/TheBloke/TinyLlama-1.1B-1T-OpenOrca-GGUF/resolve/main/tinyllama-1.1b-1t-openorca.Q4_0.gguf?download=true"
           wget -O ${TOKENIZER_PATH} https://github.com/karpathy/llama2.c/raw/master/tokenizer.model
       - name: Run inference
         run: |
-          export GGUF_PATH=gguf_files/llama-2-7b.Q4_0.gguf
+          export GGUF_PATH=gguf_files/TinyLlama-1.1B-openorca.Q4_0.gguf
           export TOKENIZER_PATH=gguf_files/tokenizer.model
-          export MODEL_NAME=llama-2-7b.Q4_0.gguf
+          export MODEL_NAME=TinyLlama-1.1B-openorca.Q4_0.gguf
           export MODEL_DIR=/tmp
 
           echo "******************************************"