improve README

README.md

@@ -2,7 +2,7 @@
 
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 
-A fork of @ggerganov's llama.cpp to use [Facebook's LLaMA](https://github.com/facebookresearch/llama) in Swift.
+A fork of [@ggerganov](https://github.com/ggerganov)'s [llama.cpp](https://github.com/ggerganov/llama.cpp) to use [Facebook's LLaMA](https://github.com/facebookresearch/llama) in Swift.
 
 ## Description
 
@@ -37,14 +37,23 @@ python3 convert-pth-to-ggml.py models/7B/ 1
 
 When running the larger models, make sure you have enough disk space to store all the intermediate files.
 
+## Building
+
+For now, compile from source. Will add other distribution channels shortly.
+
+NB: Ensure to build `llama.framework` for Release for snappiness; Debug builds are super slow. 
+
 ## Usage
 
+In Swift:
+
 ```swift
 let url = ... // URL to the model file, as per llama.cpp
 let llama = LlamaRunner(modelURL: url)
 
 llama.run(
   with: "Building a website can be done in 10 simple steps:",
+  config: LlamaRunner.Config(numThreads: 8, numTokens: 512) // Can also specify `reversePrompt`
   tokenHandler: { token in
     // If printing tokens directly use `terminator: ""` as the tokens include whitespace and newlines.
     print(token, terminator: "")
@@ -71,6 +80,11 @@ llama.run(
 
 ```
 
+Using the `llamaTest` app:
+
+- Set `MODEL_PATH` in `LlamaTest.xcconfig` to point to your `path/to/ggml-model-q4_0.bin`, then build & run for interactive prompt generation.
+- Ensure to build for Release if you want this to be snappy.
+
 ## Misc
 
 - License: MIT