Update README.md

README.md

@@ -860,7 +860,7 @@ It was created with group_size none (-1) to reduce VRAM usage, and with --act-or
 * `gptq_model-4bit-128g.safetensors`
   * Works with AutoGPTQ in CUDA or Triton modes.
   * Does NOT work with [ExLlama](https://github.com/turboderp/exllama) as it's not a Llama model.
-  * Works with GPTQ-for-LLaMa in CUDA mode.  May have issues with GPTQ-for-LLaMa Triton mode.
+  * Untested with GPTQ-for-LLaMa.
   * Works with text-generation-webui, including one-click-installers.
   * Parameters: Groupsize = -1. Act Order / desc_act = True.