HF_TOKEN replaces HUGGING_FACE_HUB_TOKEN as it is deprecated (#253)

benchmark/src/main.rs

@@ -147,7 +147,9 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
             tracing::info!("Downloading tokenizer");
 
             // Parse Huggingface hub token
-            let auth_token = std::env::var("HUGGING_FACE_HUB_TOKEN").ok();
+            let auth_token = std::env::var("HF_TOKEN")
+                .or_else(|_| std::env::var("HUGGING_FACE_HUB_TOKEN"))
+                .ok();
 
             // Download and instantiate tokenizer
             // We need to download it outside of the Tokio runtime

docs/source/basic_tutorials/gated_model_access.md

@@ -2,13 +2,13 @@
 
 If the model you wish to serve is behind gated access or the model repository on Hugging Face Hub is private, and you have access to the model, you can provide your Hugging Face Hub access token. You can generate and copy a read token from [Hugging Face Hub tokens page](https://huggingface.co/settings/tokens)
 
-If you're using the CLI, set the `HUGGING_FACE_HUB_TOKEN` environment variable. For example:
+If you're using the CLI, set the `HF_TOKEN` environment variable. For example:
 
 ```
-export HUGGING_FACE_HUB_TOKEN=<YOUR READ TOKEN>
+export HF_TOKEN=<YOUR READ TOKEN>
 ```
 
-If you would like to do it through Docker, you can provide your token by specifying `HUGGING_FACE_HUB_TOKEN` as shown below.
+If you would like to do it through Docker, you can provide your token by specifying `HF_TOKEN` as shown below.
 
 ```bash
 model=meta-llama/Llama-2-7b-chat-hf
@@ -17,7 +17,7 @@ token=<your READ token>
 
 docker run --gpus all \
     --shm-size 1g \
-    -e HUGGING_FACE_HUB_TOKEN=$token \
+    -e HF_TOKEN=$token \
     -p 8080:80 \
     -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.0.3 \
     --model-id $model

examples/README.md

@@ -22,7 +22,7 @@ To run benchmark use below command:
 python run_generation --model_id MODEL_ID
 ```
 where `MODEL_ID` should be set to the same value as in the TGI server instance.
-> For gated models such as [LLama](https://huggingface.co/meta-llama) or [StarCoder](https://huggingface.co/bigcode/starcoder), you will have to set environment variable `HUGGING_FACE_HUB_TOKEN=<token>` with a valid Hugging Face Hub read token.
+> For gated models such as [LLama](https://huggingface.co/meta-llama) or [StarCoder](https://huggingface.co/bigcode/starcoder), you will have to set environment variable `HF_TOKEN=<token>` with a valid Hugging Face Hub read token.
 
 All possible parameters are described in the below table:
 <div align="left">

integration-tests/conftest.py

@@ -31,7 +31,7 @@ from text_generation.types import (
 )
 
 DOCKER_IMAGE = os.getenv("DOCKER_IMAGE", None)
-HUGGING_FACE_HUB_TOKEN = os.getenv("HUGGING_FACE_HUB_TOKEN", None)
+HUGGING_FACE_HUB_TOKEN = os.getenv("HF_TOKEN") or os.getenv("HUGGING_FACE_HUB_TOKEN")
 DOCKER_VOLUME = os.getenv("DOCKER_VOLUME", "/data")
 
 
@@ -427,7 +427,7 @@ def launcher(event_loop):
             env["USE_FLASH_ATTENTION"] = "false"
 
         if HUGGING_FACE_HUB_TOKEN is not None:
-            env["HUGGING_FACE_HUB_TOKEN"] = HUGGING_FACE_HUB_TOKEN
+            env["HF_TOKEN"] = HUGGING_FACE_HUB_TOKEN
 
         volumes = []
         if DOCKER_VOLUME:

launcher/src/main.rs

@@ -578,7 +578,7 @@ fn shard_manager(
 
     // Parse Inference API token
     if let Ok(api_token) = env::var("HF_API_TOKEN") {
-        envs.push(("HUGGING_FACE_HUB_TOKEN".into(), api_token.into()))
+        envs.push(("HF_TOKEN".into(), api_token.into()))
     };
 
     // Detect rope scaling
@@ -912,7 +912,7 @@ fn download_convert_model(args: &Args, running: Arc<AtomicBool>) -> Result<(), L
 
     // Parse Inference API token
     if let Ok(api_token) = env::var("HF_API_TOKEN") {
-        envs.push(("HUGGING_FACE_HUB_TOKEN".into(), api_token.into()))
+        envs.push(("HF_TOKEN".into(), api_token.into()))
     };
 
     // If args.weights_cache_override is some, pass it to the download process
@@ -1212,7 +1212,7 @@ fn spawn_webserver(
 
     // Parse Inference API token
     if let Ok(api_token) = env::var("HF_API_TOKEN") {
-        envs.push(("HUGGING_FACE_HUB_TOKEN".into(), api_token.into()))
+        envs.push(("HF_TOKEN".into(), api_token.into()))
     };
 
     // Parse Compute type

router/src/main.rs

@@ -179,7 +179,9 @@ async fn main() -> Result<(), RouterError> {
     });
 
     // Parse Huggingface hub token
-    let authorization_token = std::env::var("HUGGING_FACE_HUB_TOKEN").ok();
+    let authorization_token = std::env::var("HF_TOKEN")
+        .or_else(|_| std::env::var("HUGGING_FACE_HUB_TOKEN"))
+        .ok();
 
     // Tokenizer instance
     // This will only be used to validate payloads