diff --git a/launcher/src/main.rs b/launcher/src/main.rs index b957837a..75762712 100644 --- a/launcher/src/main.rs +++ b/launcher/src/main.rs @@ -124,7 +124,7 @@ struct Args { num_shard: Option, /// Whether you want the model to be quantized. This will use `bitsandbytes` for - /// quantization on the fly, or `gptq`. 4bit quantization is available through + /// quantization on the fly, or `gptq`. 4bit quantization is available through /// `bitsandbytes` by providing the `bitsandbytes-fp4` or `bitsandbytes-nf4` options. #[clap(long, env, value_enum)] quantize: Option,