Update README.md

README.md

@@ -6,10 +6,12 @@ language:
 
 # On-chain llama.cpp - Internet Computer
 
+You can run any *.gguf file in a llama_cpp_canister, but these are smaller models you can use for testing [onicai/llama_cpp_canister](https://github.com/onicai/llama_cpp_canister)
 
-- Run on-chain (Internet Computer) with [onicai/llama_cpp_canister](https://github.com/onicai/llama_cpp_canister)
-- Run local with [ggerganov/llama.cpp](https://github.com/ggerganov/llama.cpp)
+Notes:
 - Try them out at [ICGPT](https://icgpt.icpp.world/)
+- To use on the Internet Computer, follow instructions of [onicai/llama_cpp_canister](https://github.com/onicai/llama_cpp_canister)
+- Run local with [ggerganov/llama.cpp](https://github.com/ggerganov/llama.cpp)
 - The models were created with the training procedure outlined in [karpathy/llama2.c](https://github.com/karpathy/llama2.c) and then converted into *.gguf format as described below.