diff --git a/modules/models.py b/modules/models.py
index 39a63e1f..94c7df29 100644
--- a/modules/models.py
+++ b/modules/models.py
@@ -249,9 +249,10 @@ def llamacpp_loader(model_name):
 def llamacpp_HF_loader(model_name):
     from modules.llamacpp_hf import LlamacppHF
 
-    for fname in ["oobabooga_llama-tokenizer", "llama-tokenizer"]:
+    for fname in [model_name, "oobabooga_llama-tokenizer", "llama-tokenizer"]:
         path = Path(f'{shared.args.model_dir}/{fname}')
-        if path.exists():
+        if all((path / file).exists() for file in ['tokenizer_config.json', 'special_tokens_map.json', 'tokenizer.model']):
+            logger.info(f'Using tokenizer from: {path}')
             break
     else:
         logger.error("Could not load the model because a tokenizer in transformers format was not found. Please download oobabooga/llama-tokenizer.")
diff --git a/modules/ui_model_menu.py b/modules/ui_model_menu.py
index 6d74f247..0a063c39 100644
--- a/modules/ui_model_menu.py
+++ b/modules/ui_model_menu.py
@@ -119,7 +119,7 @@ def create_ui():
                             shared.gradio['gptq_for_llama_info'] = gr.Markdown('GPTQ-for-LLaMa support is currently only kept for compatibility with older GPUs. AutoGPTQ or ExLlama is preferred when compatible. GPTQ-for-LLaMa is installed by default with the webui on supported systems. Otherwise, it has to be installed manually following the instructions here: [instructions](https://github.com/oobabooga/text-generation-webui/blob/main/docs/GPTQ-models-(4-bit-mode).md#installation-1).')
                             shared.gradio['exllama_info'] = gr.Markdown('For more information, consult the [docs](https://github.com/oobabooga/text-generation-webui/blob/main/docs/ExLlama.md).')
                             shared.gradio['exllama_HF_info'] = gr.Markdown('ExLlama_HF is a wrapper that lets you use ExLlama like a Transformers model, which means it can use the Transformers samplers. It\'s a bit slower than the regular ExLlama.')
-                            shared.gradio['llamacpp_HF_info'] = gr.Markdown('llamacpp_HF is a wrapper that lets you use llama.cpp like a Transformers model, which means it can use the Transformers samplers. To use it, make sure to first download oobabooga/llama-tokenizer under "Download model or LoRA".')
+                            shared.gradio['llamacpp_HF_info'] = gr.Markdown('llamacpp_HF loads llama.cpp as a Transformers model. To use it, you need to download a tokenizer.\n\nOption 1: download `oobabooga/llama-tokenizer` under "Download model or LoRA". That\'s a default Llama tokenizer.\n\nOption 2: place your .gguf in a subfolder of models/ along with these 3 files: tokenizer.model, tokenizer_config.json, and special_tokens_map.json. This takes precedence over Option 1.')
 
             with gr.Column():
                 with gr.Row():