From aaf7f53d46166dabfe4fadb0b4aca73737776627 Mon Sep 17 00:00:00 2001 From: Csaba Kecskemeti Date: Sat, 14 Sep 2024 10:48:09 -0700 Subject: [PATCH] nvidia uses the LLaMAForCausalLM string in their config.json, example nvidia/Llama3-ChatQA-2-8B --- convert_hf_to_gguf.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py index 01a8a50a27cc6..2c6d5d95b8ba3 100755 --- a/convert_hf_to_gguf.py +++ b/convert_hf_to_gguf.py @@ -1487,7 +1487,7 @@ def prepare_tensors(self): raise ValueError(f"Unprocessed norms: {norms}") -@Model.register("LlamaForCausalLM", "MistralForCausalLM", "MixtralForCausalLM") +@Model.register("LLaMAForCausalLM", "LlamaForCausalLM", "MistralForCausalLM", "MixtralForCausalLM") class LlamaModel(Model): model_arch = gguf.MODEL_ARCH.LLAMA