[Docs] Rename HUGGING_FACE_HUB_TOKEN to HF_TOKEN (#1871)

[Docs] Rename HUGGING_FACE_HUB_TOKEN to HF_TOKEN #1871
dstackai · Oct 22, 2024 · 4e61acb · 4e61acb
1 parent 185e0df
commit 4e61acb
Show file tree

Hide file tree

Showing 54 changed files with 85 additions and 87 deletions.
diff --git a/docs/blog/posts/amd-on-runpod.md b/docs/blog/posts/amd-on-runpod.md
@@ -50,7 +50,7 @@ you can now specify an AMD GPU under `resources`. Below are a few examples.
 
     image: ghcr.io/huggingface/text-generation-inference:sha-a379d55-rocm
     env:
-      - HUGGING_FACE_HUB_TOKEN
+      - HF_TOKEN
       - MODEL_ID=meta-llama/Meta-Llama-3.1-70B-Instruct
       - TRUST_REMOTE_CODE=true
       - ROCM_USE_FLASH_ATTN_V2_TRITON=true
@@ -83,7 +83,7 @@ you can now specify an AMD GPU under `resources`. Below are a few examples.
 
     image: ghcr.io/huggingface/text-generation-inference:sha-a379d55-rocm
     env:
-      - HUGGING_FACE_HUB_TOKEN
+      - HF_TOKEN
       - ROCM_USE_FLASH_ATTN_V2_TRITON=true
     ide: vscode
 

diff --git a/docs/blog/posts/tpu-on-gcp.md b/docs/blog/posts/tpu-on-gcp.md
@@ -58,7 +58,7 @@ and [vLLM :material-arrow-top-right-thin:{ .external }](https://github.com/vllm-
 
     image: dstackai/optimum-tpu:llama31
     env:
-      - HUGGING_FACE_HUB_TOKEN
+      - HF_TOKEN
       - MODEL_ID=meta-llama/Meta-Llama-3.1-8B-Instruct
       - MAX_TOTAL_TOKENS=4096
       - MAX_BATCH_PREFILL_TOKENS=4095
@@ -89,7 +89,7 @@ and [vLLM :material-arrow-top-right-thin:{ .external }](https://github.com/vllm-
 
     env:
       - MODEL_ID=meta-llama/Meta-Llama-3.1-8B-Instruct
-      - HUGGING_FACE_HUB_TOKEN
+      - HF_TOKEN
       - DATE=20240828
       - TORCH_VERSION=2.5.0
       - VLLM_TARGET_DEVICE=tpu
@@ -167,7 +167,7 @@ name: optimum-tpu-llama-train
 python: "3.11"
 
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
 commands:
   - git clone -b add_llama_31_support https://github.com/dstackai/optimum-tpu.git
   - mkdir -p optimum-tpu/examples/custom/

diff --git a/docs/blog/posts/volumes-on-runpod.md b/docs/blog/posts/volumes-on-runpod.md
@@ -33,7 +33,7 @@ scaling:
 
 image: ghcr.io/huggingface/text-generation-inference:latest
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - MODEL_ID=meta-llama/Meta-Llama-3.1-8B-Instruct
   - MAX_INPUT_LENGTH=4000
   - MAX_TOTAL_TOKENS=4096
@@ -110,7 +110,7 @@ volumes:
   
 image: ghcr.io/huggingface/text-generation-inference:latest
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - MODEL_ID=meta-llama/Meta-Llama-3.1-8B-Instruct
   - MAX_INPUT_LENGTH=4000
   - MAX_TOTAL_TOKENS=4096

diff --git a/docs/docs/guides/protips.md b/docs/docs/guides/protips.md
@@ -181,7 +181,7 @@ name: vscode
 python: "3.10"
 
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
 ide: vscode
 ```
 
@@ -190,20 +190,20 @@ ide: vscode
 Then, you can pass the environment variable either via the shell:
 
 ```shell
-HUGGING_FACE_HUB_TOKEN=... dstack apply -f .dstack.yml
+HF_TOKEN=... dstack apply -f .dstack.yml
 ```
 
 Or via the `-e` option of the `dstack apply` command:
 
 ```shell
-dstack apply -f .dstack.yml -e HUGGING_FACE_HUB_TOKEN=...
+dstack apply -f .dstack.yml -e HF_TOKEN=...
 ```
 
 ??? info ".env"
     A better way to configure environment variables not hardcoded in YAML is by specifying them in a `.env` file:
 
     ```
-    HUGGING_FACE_HUB_TOKEN=...
+    HF_TOKEN=...
     ```
 
     If you install [`direnv` :material-arrow-top-right-thin:{ .external }](https://direnv.net/){:target="_blank"},

diff --git a/docs/docs/reference/dstack.yml/dev-environment.md b/docs/docs/reference/dstack.yml/dev-environment.md
@@ -151,15 +151,15 @@ name: vscode
 
 # Environment variables
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - HF_HUB_ENABLE_HF_TRANSFER=1
 
 ide: vscode
 ```
 
 </div>
 
-> If you don't assign a value to an environment variable (see `HUGGING_FACE_HUB_TOKEN` above), 
+> If you don't assign a value to an environment variable (see `HF_TOKEN` above), 
 `dstack` will require the value to be passed via the CLI or set in the current process.
 
 For instance, you can define environment variables in a `.envrc` file and utilize tools like `direnv`.

diff --git a/docs/docs/reference/dstack.yml/service.md b/docs/docs/reference/dstack.yml/service.md
@@ -312,7 +312,7 @@ python: "3.10"
 
 # Environment variables
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - MODEL=NousResearch/Llama-2-7b-chat-hf
 # Commands of the service
 commands:
@@ -328,7 +328,7 @@ resources:
 
 </div>
 
-If you don't assign a value to an environment variable (see `HUGGING_FACE_HUB_TOKEN` above),
+If you don't assign a value to an environment variable (see `HF_TOKEN` above),
 `dstack` will require the value to be passed via the CLI or set in the current process.
 
 For instance, you can define environment variables in a `.envrc` file and utilize tools like `direnv`.

diff --git a/docs/docs/reference/dstack.yml/task.md b/docs/docs/reference/dstack.yml/task.md
@@ -201,7 +201,7 @@ python: "3.10"
 
 # Environment variables
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - HF_HUB_ENABLE_HF_TRANSFER=1
 
 # Commands of the task
@@ -212,7 +212,7 @@ commands:
 
 </div>
 
-> If you don't assign a value to an environment variable (see `HUGGING_FACE_HUB_TOKEN` above), 
+> If you don't assign a value to an environment variable (see `HF_TOKEN` above), 
 `dstack` will require the value to be passed via the CLI or set in the current process.
 
 For instance, you can define environment variables in a `.envrc` file and utilize tools like `direnv`.

diff --git a/docs/docs/services.md b/docs/docs/services.md
@@ -30,7 +30,7 @@ python: "3.10"
 
 # Required environment variables
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
 commands:
   - pip install vllm
   - vllm serve meta-llama/Meta-Llama-3.1-8B-Instruct --max-model-len 4096
@@ -72,7 +72,7 @@ To run a configuration, use the [`dstack apply`](reference/cli/index.md#dstack-a
 <div class="termy">
 
 ```shell
-$ HUGGING_FACE_HUB_TOKEN=...
+$ HF_TOKEN=...
 
 $ dstack apply -f service.dstack.yml
 

diff --git a/docs/docs/tasks.md b/docs/docs/tasks.md
@@ -25,7 +25,7 @@ image: winglian/axolotl-cloud:main-20240429-py3.11-cu121-2.2.1
 
 # Required environment variables
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - WANDB_API_KEY
 # Commands of the task
 commands:
@@ -60,7 +60,7 @@ To run a configuration, use the [`dstack apply`](reference/cli/index.md#dstack-a
 <div class="termy">
 
 ```shell
-$ HUGGING_FACE_HUB_TOKEN=...
+$ HF_TOKEN=...
 $ WANDB_API_KEY=...
 
 $ dstack apply -f examples/.dstack.yml

diff --git a/examples/.dstack.yml b/examples/.dstack.yml
@@ -11,8 +11,6 @@ ide: vscode
 # Use either spot or on-demand instances
 spot_policy: auto
 
+# Required resources
 resources:
-   memory: 16MB..
-   shm_size: 8MB
-#  gpu: A10
-#  disk: 100GB..
+  gpu: 24GB
diff --git a/examples/accelerators/amd/README.md b/examples/accelerators/amd/README.md
@@ -21,7 +21,7 @@ Llama 3.1 70B in FP16 using [TGI :material-arrow-top-right-thin:{ .external }](h
 
     # Required environment variables
     env:
-      - HUGGING_FACE_HUB_TOKEN
+      - HF_TOKEN
       - MODEL_ID=meta-llama/Meta-Llama-3.1-70B-Instruct
       - TRUST_REMOTE_CODE=true
       - ROCM_USE_FLASH_ATTN_V2_TRITON=true
@@ -61,7 +61,7 @@ Llama 3.1 70B in FP16 using [TGI :material-arrow-top-right-thin:{ .external }](h
 
     # Required environment variables
     env:
-      - HUGGING_FACE_HUB_TOKEN
+      - HF_TOKEN
       - MODEL_ID=meta-llama/Meta-Llama-3.1-70B-Instruct
       - MAX_MODEL_LEN=126192
     # Commands of the task
@@ -135,7 +135,7 @@ To request multiple GPUs, specify the quantity after the GPU name, separated by
 
     # Required environment variables
     env:
-      - HUGGING_FACE_HUB_TOKEN
+      - HF_TOKEN
     # Commands of the task
     commands:
       - export PATH=/opt/conda/envs/py_3.10/bin:$PATH
@@ -177,7 +177,7 @@ To request multiple GPUs, specify the quantity after the GPU name, separated by
     image: runpod/pytorch:2.1.2-py3.10-rocm6.0.2-ubuntu22.04
     # Required environment variables
     env:
-      - HUGGING_FACE_HUB_TOKEN
+      - HF_TOKEN
     # Commands of the task
     commands:
       - export PATH=/opt/conda/envs/py_3.10/bin:$PATH
@@ -224,7 +224,7 @@ cloud resources and run the configuration.
 <div class="termy">
 
 ```shell
-$ HUGGING_FACE_HUB_TOKEN=...
+$ HF_TOKEN=...
 $ dstack apply -f examples/deployment/vllm/amd/service.dstack.yml
 ```
 

diff --git a/examples/accelerators/tpu/README.md b/examples/accelerators/tpu/README.md
@@ -25,7 +25,7 @@ and [vLLM :material-arrow-top-right-thin:{ .external }](https://github.com/vllm-
 
     image: dstackai/optimum-tpu:llama31
     env:
-      - HUGGING_FACE_HUB_TOKEN
+      - HF_TOKEN
       - MODEL_ID=meta-llama/Meta-Llama-3.1-8B-Instruct
       - MAX_TOTAL_TOKENS=4096
       - MAX_BATCH_PREFILL_TOKENS=4095
@@ -61,7 +61,7 @@ and [vLLM :material-arrow-top-right-thin:{ .external }](https://github.com/vllm-
 
     env:
       - MODEL_ID=meta-llama/Meta-Llama-3.1-8B-Instruct
-      - HUGGING_FACE_HUB_TOKEN
+      - HF_TOKEN
       - DATE=20240828
       - TORCH_VERSION=2.5.0
       - VLLM_TARGET_DEVICE=tpu
@@ -135,7 +135,7 @@ name: optimum-tpu-llama-train
 python: "3.11"
 
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
 commands:
   - git clone -b add_llama_31_support https://github.com/dstackai/optimum-tpu.git
   - mkdir -p optimum-tpu/examples/custom/

diff --git a/examples/deployment/lorax/serve-task.dstack.yml b/examples/deployment/lorax/serve-task.dstack.yml
@@ -3,7 +3,7 @@ type: task
 image: ghcr.io/predibase/lorax:latest
 
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - MODEL_ID=mistralai/Mistral-7B-Instruct-v0.1
 
 commands:

diff --git a/examples/deployment/lorax/serve.dstack.yml b/examples/deployment/lorax/serve.dstack.yml
@@ -3,7 +3,7 @@ type: service
 image: ghcr.io/predibase/lorax:latest
 
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - MODEL_ID=mistralai/Mistral-7B-Instruct-v0.1
 
 commands:

diff --git a/examples/deployment/optimum-tpu/.dstack.yml b/examples/deployment/optimum-tpu/.dstack.yml
@@ -7,7 +7,7 @@ name: vscode-optimum-tpu
 image: dstackai/optimum-tpu:llama31
 # Required environment variables
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
 ide: vscode
 
 resources:

diff --git a/examples/deployment/optimum-tpu/service.dstack.yml b/examples/deployment/optimum-tpu/service.dstack.yml
@@ -7,7 +7,7 @@ name: llama31-service-optimum-tpu
 image: dstackai/optimum-tpu:llama31
 # Required environment variables
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - MODEL_ID=meta-llama/Meta-Llama-3.1-8B-Instruct
   - MAX_TOTAL_TOKENS=4096
   - MAX_BATCH_PREFILL_TOKENS=4095

diff --git a/examples/deployment/optimum-tpu/task.dstack.yml b/examples/deployment/optimum-tpu/task.dstack.yml
@@ -7,7 +7,7 @@ name: llama31-task-optimum-tpu
 image: dstackai/optimum-tpu:llama31
 # Required environment variables
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - MODEL_ID=meta-llama/Meta-Llama-3.1-8B-Instruct
   - MAX_TOTAL_TOKENS=4096
   - MAX_BATCH_PREFILL_TOKENS=4095

diff --git a/examples/deployment/tgi/amd/.dstack.yml b/examples/deployment/tgi/amd/.dstack.yml
@@ -4,7 +4,7 @@ name: dev-tgi-amd
 image: ghcr.io/huggingface/text-generation-inference:sha-a379d55-rocm
 
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - ROCM_USE_FLASH_ATTN_V2_TRITON=true
 ide: vscode
 

diff --git a/examples/deployment/tgi/amd/service.dstack.yml b/examples/deployment/tgi/amd/service.dstack.yml
@@ -3,7 +3,7 @@ name: service-tgi-amd
 
 image: ghcr.io/huggingface/text-generation-inference:sha-a379d55-rocm
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - ROCM_USE_FLASH_ATTN_V2_TRITON=true
   - TRUST_REMOTE_CODE=true
   - MODEL_ID=meta-llama/Meta-Llama-3.1-70B-Instruct

diff --git a/examples/deployment/tgi/serve-task.dstack.yml b/examples/deployment/tgi/serve-task.dstack.yml
@@ -3,7 +3,7 @@ type: task
 
 image: ghcr.io/huggingface/text-generation-inference:latest
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - MODEL_ID=mistralai/Mistral-7B-Instruct-v0.2
 commands:
   - text-generation-launcher --port 8000 --trust-remote-code

diff --git a/examples/deployment/tgi/serve.dstack.yml b/examples/deployment/tgi/serve.dstack.yml
@@ -3,7 +3,7 @@ type: service
 
 image: ghcr.io/huggingface/text-generation-inference:latest
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - MODEL_ID=mistralai/Mistral-7B-Instruct-v0.2
 commands:
   - text-generation-launcher --port 8000 --trust-remote-code

diff --git a/examples/deployment/vllm/amd/.dstack.yml b/examples/deployment/vllm/amd/.dstack.yml
@@ -4,7 +4,7 @@ name: dev-vLLM-amd
 image: runpod/pytorch:2.4.0-py3.10-rocm6.1.0-ubuntu22.04
 
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
 
 ide: vscode
 

diff --git a/examples/deployment/vllm/amd/build.vllm-rocm.yaml b/examples/deployment/vllm/amd/build.vllm-rocm.yaml
@@ -4,7 +4,7 @@ name: build-vllm-rocm
 image: runpod/pytorch:2.4.0-py3.10-rocm6.1.0-ubuntu22.04
 
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - AWS_ACCESS_KEY_ID
   - AWS_SECRET_ACCESS_KEY
   - AWS_REGION

diff --git a/examples/deployment/vllm/amd/service.dstack.yml b/examples/deployment/vllm/amd/service.dstack.yml
@@ -4,7 +4,7 @@ name: llama31-service-vllm-amd
 image: runpod/pytorch:2.4.0-py3.10-rocm6.1.0-ubuntu22.04
 
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - MODEL_ID=meta-llama/Meta-Llama-3.1-70B-Instruct
   - MAX_MODEL_LEN=126192
 

diff --git a/examples/deployment/vllm/service-tpu.dstack.yml b/examples/deployment/vllm/service-tpu.dstack.yml
@@ -3,7 +3,7 @@ type: service
 name: llama31-service-vllm-tpu
 
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - MODEL_ID=meta-llama/Meta-Llama-3.1-8B-Instruct
   - DATE=20240828
   - TORCH_VERSION=2.5.0

diff --git a/examples/fine-tuning/alignment-handbook/.dstack.yml b/examples/fine-tuning/alignment-handbook/.dstack.yml
@@ -7,7 +7,7 @@ python: "3.10"
 
 # Required environment variables
 env:
-  - HUGGING_FACE_HUB_TOKEN
+  - HF_TOKEN
   - ACCELERATE_LOG_LEVEL=info
   - WANDB_API_KEY