From 14cd303d9f31a093b58911d9c092642dbcc6f14a Mon Sep 17 00:00:00 2001
From: Philpax <me@philpax.me>
Date: Sat, 6 May 2023 21:01:27 +0200
Subject: [PATCH] fix: default to llm-cli for cargo run

---
 Cargo.toml | 1 +
 README.md  | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/Cargo.toml b/Cargo.toml
index bc3b963a..b8cc993b 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -9,6 +9,7 @@ members = [
     "binaries/*"
 ]
 resolver = "2"
+default-members = ["binaries/llm-cli"]
 
 [workspace.package]
 repository = "https://github.com/rustformers/llm"
diff --git a/README.md b/README.md
index e5299778..48d43556 100644
--- a/README.md
+++ b/README.md
@@ -60,7 +60,7 @@ The resulting binary will be at `target/release/llm[.exe]`.
 It can also be run directly through Cargo, using
 
 ```shell
-cargo run --release --bin llm -- <ARGS>
+cargo run --release -- <ARGS>
 ```
 
 This is useful for development.
@@ -113,7 +113,7 @@ is compatible with ggml. To achieve this, follow the steps outlined below:
 python3 scripts/convert-pth-to-ggml.py /path/to/your/models/7B/ 1
 
 # Quantize the model to 4-bit ggml format
-cargo run --bin llm llama quantize /path/to/your/models/7B/ggml-model-f16.bin /path/to/your/models/7B/ggml-model-q4_0.bin q4_0
+cargo run --release llama quantize /path/to/your/models/7B/ggml-model-f16.bin /path/to/your/models/7B/ggml-model-q4_0.bin q4_0
 ```
 
 > **Note**