Fix Gemma model path

README.md

@@ -68,7 +68,7 @@ Actually all these will be solved with further training. First requires unet tra
 1. Install [custom nodes](https://github.com/NeuroSenko/ComfyUI_LLM_SDXL_Adapter) for Comfy
 2. Make sure you updated Transformers to version that supports gemma-3
 3. Download [adapter](https://huggingface.co/Minthy/RouWei-Gemma/blob/main/rw_gemma_3_1_27k.safetensors) and put it into `/models/llm_adapters`
-4. Download [gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) ([non-gated mirror](https://huggingface.co/unsloth/gemma-3-1b-it)) and put it into `/models/llm_adapters/gemma-3-1b-it`
+4. Download [gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) ([non-gated mirror](https://huggingface.co/unsloth/gemma-3-1b-it)) and put it into `/models/LLM/gemma-3-1b-it`
 5. You need all files from original model, not only .safetensors (the best way to download them is to use HF-HUB)
 6. Download [Rouwei-0.8](https://huggingface.co/Minthy/RouWei-0.8) ([vpred](https://huggingface.co/Minthy/RouWei-0.8/blob/main/rouwei_080_vpred_fp16.safetensors) or [epsilon](https://huggingface.co/Minthy/RouWei-0.8/blob/main/rouwei_080_epsilon_fp16.safetensors) or [base-epsilon](https://huggingface.co/Minthy/RouWei-0.8/blob/main/rouwei_080_base_fp16.safetensors)) checkpoint if you don't have one yet
 7. Use [this workflow](https://huggingface.co/Minthy/RouWei-Gemma/blob/main/workflow.png) as a reference, feel free to experiment