From d2f0e7e6158bf0c0995ebe09c4d95ee1b24c5607 Mon Sep 17 00:00:00 2001 From: Isotr0py Date: Sat, 7 Jun 2025 17:23:28 +0800 Subject: [PATCH] [CI/Build] Improve Llama GGUF test robustness (#19287) Signed-off-by: Isotr0py <2037008807@qq.com> --- tests/models/quantization/test_gguf.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/models/quantization/test_gguf.py b/tests/models/quantization/test_gguf.py index eafdfd1b09aff..32f9472c12d5e 100644 --- a/tests/models/quantization/test_gguf.py +++ b/tests/models/quantization/test_gguf.py @@ -38,7 +38,7 @@ class GGUFTestConfig(NamedTuple): LLAMA_CONFIG = GGUFTestConfig( original_model="meta-llama/Llama-3.2-1B-Instruct", gguf_repo="bartowski/Llama-3.2-1B-Instruct-GGUF", - gguf_filename="Llama-3.2-1B-Instruct-IQ4_XS.gguf", + gguf_filename="Llama-3.2-1B-Instruct-Q6_K.gguf", ) QWEN2_CONFIG = GGUFTestConfig(