diff --git a/Cargo.toml b/Cargo.toml
index d6cf18614f..bd6e1a856b 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -46,7 +46,7 @@ criterion = { version = "0.5.1", default-features=false }
 cudarc = { version = "0.12.1", features = ["std", "cublas", "cublaslt", "curand", "driver", "nvrtc", "f16", "cuda-version-from-build-system", "dynamic-linking"], default-features=false }
 fancy-regex = "0.13.0"
 gemm = { version = "0.17.0", features = ["wasm-simd128-enable"] }
-hf-hub = "0.3.0"
+hf-hub = { version = "0.3.3", package = "candle-hf-hub" }
 half = { version = "2.3.1", features = ["num-traits", "use-intrinsics", "rand_distr"] }
 hound = "3.5.1"
 image = { version = "0.25.2", default-features = false, features = ["jpeg", "png"] }
diff --git a/candle-book/src/inference/hub.md b/candle-book/src/inference/hub.md
index e8d8b267db..fb6f9e51f6 100644
--- a/candle-book/src/inference/hub.md
+++ b/candle-book/src/inference/hub.md
@@ -11,8 +11,8 @@ Then let's start by downloading the [model file](https://huggingface.co/bert-bas
 
 ```rust
 # extern crate candle_core;
-# extern crate hf_hub;
-use hf_hub::api::sync::Api;
+# extern crate candle_hf_hub;
+use candle_hf_hub::api::sync::Api;
 use candle_core::Device;
 
 let api = Api::new().unwrap();
@@ -50,8 +50,8 @@ Now that we have our weights, we can use them in our bert architecture:
 ```rust
 # extern crate candle_core;
 # extern crate candle_nn;
-# extern crate hf_hub;
-# use hf_hub::api::sync::Api;
+# extern crate candle_hf_hub;
+# use candle_hf_hub::api::sync::Api;
 # 
 # let api = Api::new().unwrap();
 # let repo = api.model("bert-base-uncased".to_string());
diff --git a/candle-examples/examples/llama/main.rs b/candle-examples/examples/llama/main.rs
index 7a555b00af..cc99b6c191 100644
--- a/candle-examples/examples/llama/main.rs
+++ b/candle-examples/examples/llama/main.rs
@@ -139,8 +139,8 @@ fn main() -> Result<()> {
             Which::V2 => "meta-llama/Llama-2-7b-hf".to_string(),
             Which::V3 => "meta-llama/Meta-Llama-3-8B".to_string(),
             Which::V3Instruct => "meta-llama/Meta-Llama-3-8B-Instruct".to_string(),
-            Which::V31 => "meta-llama/Meta-Llama-3.1-8B".to_string(),
-            Which::V31Instruct => "meta-llama/Meta-Llama-3.1-8B-Instruct".to_string(),
+            Which::V31 => "meta-llama/Llama-3.1-8B".to_string(),
+            Which::V31Instruct => "meta-llama/Llama-3.1-8B-Instruct".to_string(),
             Which::V32_1b => "meta-llama/Llama-3.2-1B".to_string(),
             Which::V32_1bInstruct => "meta-llama/Llama-3.2-1B-Instruct".to_string(),
             Which::V32_3b => "meta-llama/Llama-3.2-3B".to_string(),