Upload README.md with huggingface_hub

README.md

@@ -1,15 +1,15 @@
 ---
+base_model: microsoft/Phi-3-medium-128k-instruct
 language:
 - multilingual
 license: mit
+license_link: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE
+pipeline_tag: text-generation
 tags:
 - nlp
 - code
 - llama-cpp
 - gguf-my-repo
-base_model: microsoft/Phi-3-medium-128k-instruct
-license_link: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE
-pipeline_tag: text-generation
 inference:
   parameters:
     temperature: 0.7
@@ -34,7 +34,7 @@ Invoke the llama.cpp server or the CLI.
 
 ### CLI:
 ```bash
-llama --hf-repo newsletter/Phi-3-medium-128k-instruct-Q6_K-GGUF --hf-file phi-3-medium-128k-instruct-q6_k.gguf -p "The meaning to life and the universe is"
+llama-cli --hf-repo newsletter/Phi-3-medium-128k-instruct-Q6_K-GGUF --hf-file phi-3-medium-128k-instruct-q6_k.gguf -p "The meaning to life and the universe is"
 ```
 
 ### Server:
@@ -56,9 +56,9 @@ cd llama.cpp && LLAMA_CURL=1 make
 
 Step 3: Run inference through the main binary.
 ```
-./main --hf-repo newsletter/Phi-3-medium-128k-instruct-Q6_K-GGUF --hf-file phi-3-medium-128k-instruct-q6_k.gguf -p "The meaning to life and the universe is"
+./llama-cli --hf-repo newsletter/Phi-3-medium-128k-instruct-Q6_K-GGUF --hf-file phi-3-medium-128k-instruct-q6_k.gguf -p "The meaning to life and the universe is"
 ```
 or 
 ```
-./server --hf-repo newsletter/Phi-3-medium-128k-instruct-Q6_K-GGUF --hf-file phi-3-medium-128k-instruct-q6_k.gguf -c 2048
+./llama-server --hf-repo newsletter/Phi-3-medium-128k-instruct-Q6_K-GGUF --hf-file phi-3-medium-128k-instruct-q6_k.gguf -c 2048
 ```