Upload README.md

README.md

@@ -119,6 +119,9 @@ Refer to the Provided Files table below to see what files use which methods, and
 | [llama-2-7b.Q8_0.gguf](https://huggingface.co/TheBloke/Llama-2-7B-GGUF/blob/main/llama-2-7b.Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| 9.66 GB | very large, extremely low quality loss - not recommended |
 
 **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
+
+
+
 <!-- README_GGUF.md-provided-files end -->
 
 <!-- README_GGUF.md-how-to-run start -->
@@ -170,7 +173,7 @@ CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
 from ctransformers import AutoModelForCausalLM
 
 # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
-llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-GGML", model_file="llama-2-7b.q4_K_M.gguf", model_type="llama", gpu_layers=50)
+llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-GGUF", model_file="llama-2-7b.q4_K_M.gguf", model_type="llama", gpu_layers=50)
 
 print(llm("AI is going to"))
 ```