nvidia uses the LLaMAForCausalLM string in their config.json, example…

… nvidia/Llama3-ChatQA-2-8B

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