diff --git a/README.md b/README.md
index fd0adbc..b7385b6 100644
--- a/README.md
+++ b/README.md
@@ -10,20 +10,6 @@ ReZero trains a small language model to develop effective search behaviors inste
 
 </div>
 
-## Quick Demo 🚀
-
-<div align="center">
-  <img src="assets/demo.gif" alt="ReZero Demo" width="1000px">
-</div>
-
-Run the interactive web interface to see ReZero in action:
-
-```bash
-python app.py
-```
-
-This will launch a Gradio interface where you can interact with the model and test different search behaviors.
-
 ## Setup 🛠️
 
 ```bash
@@ -46,6 +32,20 @@ cp .env.example .env
 # Edit .env and add your Tavily API key if you want to use the websearch demo
 ```
 
+## Quick Demo 🚀
+
+<div align="center">
+  <img src="assets/demo.gif" alt="ReZero Demo" width="1000px">
+</div>
+
+Run the interactive web interface to see ReZero in action:
+
+```bash
+python app.py
+```
+
+This will launch a Gradio interface where you can interact with the model and test different search behaviors.
+
 ## Data and Training 🧠
 
 All necessary training data is included in the `data/` folder. To train:
diff --git a/pyproject.toml b/pyproject.toml
index 3af8445..5df00c6 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -5,9 +5,9 @@ build-backend = "flit_core.buildapi"
 [project]
 name = "src"
 version = "0.0.1"
-description = "A short description of the project."
+description = "ReZero: Enhancing LLM search ability by trying one-more-time"
 authors = [
-  { name = "Your name (or your organization/company/team)" },
+  { name = "Menlo Research" },
 ]
 readme = "README.md"
 classifiers = [
@@ -38,6 +38,5 @@ dependencies = [
     "requests>=2.31.0",
     "tqdm>=4.66.1",
     "tavily-python",
-    "sglang[all]>=0.4.5",
     "gdown",
 ]
\ No newline at end of file