Update README.md

README.md

@@ -5,30 +5,35 @@ license: apache-2.0
 
 # Download tiny llama llamafile
 - Go to https://huggingface.co/aviol/TinyLlama1.1-llamafile-bootstraped/blob/main/TinyLlama-1.1B.llamafile
-  - Download using the download button
+  - Download this file using the download button.
 
 # Run the server
 ```shell
-# Make executable after downloading
 chmod +x TinyLlama-1.1B.llamafile
 
-# Run
 ./TinyLlama-1.1B.llamafile --server --host 0.0.0.0 --port 1234
 ```
 
-
-# Use the LLM using OpenAI SDK:
+# Use the LLM with OpenAI SDK:
 ```python
 from openai import OpenAI
 
+
 client = OpenAI(base_url="http://127.0.0.1:1234/v1", api_key="test")
 
+# Prompt
+prompt = "Hi, tell me something new about AppSec"
+
+# Send API request to llamafile server
 stream = client.chat.completions.create(
-    model="chatgpt-4",
+    model="avi-llmsky",
     messages=[{"role": "user", "content": prompt}],
     stream=True,
 )
+
+# Print the responses
 for chunk in stream:
     if chunk.choices[0].delta.content is not None:
         print(chunk.choices[0].delta.content, end="")
+
 ```