Update README.md

README.md

@@ -36,7 +36,7 @@ llama-server --hf-repo hellork/deepseek-coder-6.7b-instruct-IQ4_NL-GGUF --hf-fil
 Interact with this model by speaking to it. Lean, fast, & private, networked speech to text, AI images, multi-modal voice chat, control apps, webcam, and sound with less than 4GiB of VRAM.
 [whisper_dictation](https://github.com/themanyone/whisper_dictation)
 
-Quick start
+*Quick start*
 ```bash
 git clone -b main --single-branch https://github.com/themanyone/whisper_dictation.git
 pip install -r whisper_dictation/requirements.txt
@@ -47,13 +47,17 @@ GGML_CUDA=1 make -j # assuming CUDA is available. see docs
 ln -s server ~/.local/bin/whisper_cpp_server # (just put it somewhere in $PATH)
 whisper_cpp_server -l en -m models/ggml-tiny.en.bin --port 7777
 
-# -ngl option assumes CUDA is available. see docs
-llama-server --hf-repo hellork/calme-2.1-qwen2-7b-IQ4_NL-GGUF --hf-file deepseek-coder-6.7b-instruct-iq4_nl-imat.gguf -c 2048 -ngl 17 --port 8888
+# -ngl option assumes CUDA or othr AI acceleration is available. see docs
+llama-server --hf-repo hellork/calme-2.1-qwen2-7b-IQ4_NL-GGUF --hf-file calme-2.1-qwen2-7b-iq4_nl-imat.gguf -c 2048 -ngl 17 --port 8888
 
 cd whisper_dictation
 ./whisper_cpp_client.py
 ```
 
+### Install llama.cpp via git:
+
+Step 1: `git clone https://github.com/ggerganov/llama.cpp`
+
 Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
 ```
 cd llama.cpp && LLAMA_CURL=1 make