Quantized support for f16 and f32 (#457)

* Add f32 as a quantized type.

* Add f16 as a quantized type too.

candle-examples/examples/ggml/main.rs

@@ -8,7 +8,7 @@ use candle::{DType, Device};
 #[derive(Parser, Debug)]
 #[command(author, version, about, long_about = None)]
 struct Args {
-    /// GGML file to load.
+    /// GGML file to load, typically a .bin file generated by the quantize command from llama.cpp
     #[arg(long)]
     model: String,
 }