diff --git a/Cargo.lock b/Cargo.lock
index 48595077..1dcc7c97 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -2516,7 +2516,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-benchmark"
-version = "0.7.0-dev"
+version = "0.7.0"
 dependencies = [
  "average",
  "clap",
@@ -2535,7 +2535,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "0.7.0-dev"
+version = "0.7.0"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -2551,7 +2551,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "0.7.0-dev"
+version = "0.7.0"
 dependencies = [
  "clap",
  "ctrlc",
@@ -2567,7 +2567,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "0.7.0-dev"
+version = "0.7.0"
 dependencies = [
  "async-stream",
  "axum",
diff --git a/Cargo.toml b/Cargo.toml
index d34b10bf..4ed0524e 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -8,7 +8,7 @@ members = [
 ]
 
 [workspace.package]
-version = "0.7.0-dev"
+version = "0.7.0"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"
diff --git a/docs/openapi.json b/docs/openapi.json
index fbac7786..5bccc9fc 100644
--- a/docs/openapi.json
+++ b/docs/openapi.json
@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "0.7.0-dev"
+    "version": "0.7.0"
   },
   "paths": {
     "/": {
diff --git a/server/pyproject.toml b/server/pyproject.toml
index 932a094c..d674172d 100644
--- a/server/pyproject.toml
+++ b/server/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-server"
-version = "0.6.0"
+version = "0.7.0"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]
 
diff --git a/server/text_generation_server/cli.py b/server/text_generation_server/cli.py
index c0e6c2dc..4d8778cb 100644
--- a/server/text_generation_server/cli.py
+++ b/server/text_generation_server/cli.py
@@ -72,7 +72,7 @@ def download_weights(
     model_id: str,
     revision: Optional[str] = None,
     extension: str = ".safetensors",
-    auto_convert: bool = True,
+    auto_convert: bool = False,
     logger_level: str = "INFO",
     json_output: bool = False,
 ):