Merge branch 'main' into moshi-integration

huggingface · Sep 20, 2024 · 81432c0 · 81432c0
2 parents 50f9eb8 + 653eb40
commit 81432c0
Show file tree

Hide file tree

Showing 271 changed files with 14,164 additions and 1,395 deletions.
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -47,13 +47,13 @@ jobs:
 
             - run:
                 name: "Retrieve Artifact Paths"
-                env:
-                    CIRCLE_TOKEN: ${{ secrets.CI_ARTIFACT_TOKEN }}
+                # [reference] https://circleci.com/docs/api/v2/index.html#operation/getJobArtifacts
+                # `CIRCLE_TOKEN` is defined as an environment variables set within a context, see `https://circleci.com/docs/contexts/`
                 command: |
                     project_slug="gh/${CIRCLE_PROJECT_USERNAME}/${CIRCLE_PROJECT_REPONAME}"
                     job_number=${CIRCLE_BUILD_NUM}
                     url="https://circleci.com/api/v2/project/${project_slug}/${job_number}/artifacts"
-                    curl -o  test_preparation/artifacts.json ${url}
+                    curl -o test_preparation/artifacts.json ${url} --header "Circle-Token: $CIRCLE_TOKEN"
             - run:
                 name: "Prepare pipeline parameters"
                 command: |
@@ -82,22 +82,49 @@ jobs:
         parallelism: 1
         steps:
             - checkout
-            - run: uv pip install -e .
-            - run: |
-                  mkdir test_preparation
-                  echo -n "tests" > test_preparation/test_list.txt
-                  echo -n "all" > test_preparation/examples_test_list.txt
-                  echo -n "tests/repo_utils" > test_preparation/test_repo_utils.txt
+            - run: uv pip install -U -e .
+            - run: echo 'export "GIT_COMMIT_MESSAGE=$(git show -s --format=%s)"' >> "$BASH_ENV" && source "$BASH_ENV"
+            - run: mkdir -p test_preparation
+            - run: python utils/tests_fetcher.py --fetch_all | tee tests_fetched_summary.txt
+            - run: python utils/tests_fetcher.py --filter_tests
+            - run: export "GIT_COMMIT_MESSAGE=$(git show -s --format=%s)" && echo $GIT_COMMIT_MESSAGE && python .circleci/create_circleci_config.py --fetcher_folder test_preparation
             - run: |
-                  echo -n "tests" > test_list.txt
-                  python utils/tests_fetcher.py --filter_tests
-                  mv test_list.txt test_preparation/filtered_test_list.txt
-            - run: python .circleci/create_circleci_config.py --fetcher_folder test_preparation
-            - run: cp test_preparation/generated_config.yml test_preparation/generated_config.txt
+                if [ ! -s test_preparation/generated_config.yml ]; then
+                    echo "No tests to run, exiting early!"
+                    circleci-agent step halt
+                fi
+
+            - store_artifacts:
+                path: test_preparation
+
+            - run:
+                name: "Retrieve Artifact Paths"
+                env:
+                    CIRCLE_TOKEN: ${{ secrets.CI_ARTIFACT_TOKEN }}
+                command: |
+                    project_slug="gh/${CIRCLE_PROJECT_USERNAME}/${CIRCLE_PROJECT_REPONAME}"
+                    job_number=${CIRCLE_BUILD_NUM}
+                    url="https://circleci.com/api/v2/project/${project_slug}/${job_number}/artifacts"
+                    curl -o  test_preparation/artifacts.json ${url}
+            - run:
+                name: "Prepare pipeline parameters"
+                command: |
+                    python utils/process_test_artifacts.py 
+
+            # To avoid too long generated_config.yaml on the continuation orb, we pass the links to the artifacts as parameters.
+            # Otherwise the list of tests was just too big. Explicit is good but for that it was a limitation.
+            # We used:
+
+            # https://circleci.com/docs/api/v2/index.html#operation/getJobArtifacts : to get the job artifacts
+            # We could not pass a nested dict, which is why we create the test_file_... parameters for every single job
+
             - store_artifacts:
-                  path: test_preparation/generated_config.txt
+                path: test_preparation/transformed_artifacts.json
+            - store_artifacts:
+                path: test_preparation/artifacts.json
             - continuation/continue:
-                  configuration_path: test_preparation/generated_config.yml
+                parameters:  test_preparation/transformed_artifacts.json
+                configuration_path: test_preparation/generated_config.yml
 
     check_code_quality:
         working_directory: ~/transformers
@@ -163,7 +190,10 @@ workflows:
             - check_circleci_user
             - check_code_quality
             - check_repository_consistency
-            - fetch_tests
+            - fetch_tests:
+                # [reference] https://circleci.com/docs/contexts/
+                context:
+                    - TRANSFORMERS_CONTEXT
 
     nightly:
         when: <<pipeline.parameters.nightly>>

diff --git a/.coveragerc b/.coveragerc
diff --git a/.github/workflows/build-docker-images.yml b/.github/workflows/build-docker-images.yml
@@ -20,7 +20,8 @@ concurrency:
 jobs:
   latest-docker:
     name: "Latest PyTorch + TensorFlow [dev]"
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       -
         name: Set up Docker Buildx
@@ -68,7 +69,8 @@ jobs:
 
   latest-torch-deepspeed-docker:
     name: "Latest PyTorch + DeepSpeed"
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       -
         name: Set up Docker Buildx
@@ -104,7 +106,8 @@ jobs:
   # Can't build 2 images in a single job `latest-torch-deepspeed-docker` (for `nvcr.io/nvidia`)
   latest-torch-deepspeed-docker-for-push-ci-daily-build:
     name: "Latest PyTorch + DeepSpeed (Push CI - Daily Build)"
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       -
         name: Set up Docker Buildx
@@ -145,7 +148,8 @@ jobs:
     name: "Doc builder"
     # Push CI doesn't need this image
     if: inputs.image_postfix != '-push-ci'
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       -
         name: Set up Docker Buildx
@@ -180,7 +184,8 @@ jobs:
     name: "Latest PyTorch [dev]"
     # Push CI doesn't need this image
     if: inputs.image_postfix != '-push-ci'
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       -
         name: Set up Docker Buildx
@@ -215,7 +220,8 @@ jobs:
 
   latest-pytorch-amd:
     name: "Latest PyTorch (AMD) [dev]"
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       - 
         name: Set up Docker Buildx
@@ -265,7 +271,8 @@ jobs:
     name: "Latest TensorFlow [dev]"
     # Push CI doesn't need this image
     if: inputs.image_postfix != '-push-ci'
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       -
         name: Set up Docker Buildx
@@ -300,7 +307,8 @@ jobs:
 
   latest-pytorch-deepspeed-amd:
     name: "PyTorch + DeepSpeed (AMD) [dev]"
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       - 
         name: Set up Docker Buildx
@@ -350,7 +358,8 @@ jobs:
     name: "Latest Pytorch + Quantization [dev]"
      # Push CI doesn't need this image
     if: inputs.image_postfix != '-push-ci'
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       -
         name: Set up Docker Buildx

diff --git a/.github/workflows/build-nightly-ci-docker-images.yml b/.github/workflows/build-nightly-ci-docker-images.yml
@@ -13,7 +13,8 @@ concurrency:
 jobs:
   latest-with-torch-nightly-docker:
     name: "Nightly PyTorch + Stable TensorFlow"
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       -
         name: Set up Docker Buildx
@@ -40,7 +41,8 @@ jobs:
 
   nightly-torch-deepspeed-docker:
     name: "Nightly PyTorch + DeepSpeed"
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       -
         name: Set up Docker Buildx
@@ -62,4 +64,4 @@ jobs:
           build-args: |
             REF=main
           push: true
-          tags: huggingface/transformers-pytorch-deepspeed-nightly-gpu
+          tags: huggingface/transformers-pytorch-deepspeed-nightly-gpu
diff --git a/.github/workflows/build-past-ci-docker-images.yml b/.github/workflows/build-past-ci-docker-images.yml
@@ -16,7 +16,8 @@ jobs:
       fail-fast: false
       matrix:
         version: ["1.13", "1.12", "1.11"]
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       -
         name: Set up Docker Buildx
@@ -60,7 +61,8 @@ jobs:
       fail-fast: false
       matrix:
         version: ["2.11", "2.10", "2.9", "2.8", "2.7", "2.6", "2.5"]
-    runs-on: [intel-cpu, 8-cpu, ci]
+    runs-on:
+      group: aws-general-8-plus
     steps:
       -
         name: Set up Docker Buildx

diff --git a/.github/workflows/build_documentation.yml b/.github/workflows/build_documentation.yml
@@ -1,6 +1,7 @@
 name: Build documentation
 
 on:
+  workflow_dispatch:
   push:
     branches:
       - main
@@ -15,7 +16,7 @@ jobs:
       commit_sha: ${{ github.sha }}
       package: transformers
       notebook_folder: transformers_doc
-      languages: de en es fr hi it ko pt tr zh ja te
+      languages: ar de en es fr hi it ko pt tr zh ja te
       custom_container: huggingface/transformers-doc-builder
     secrets:
       token: ${{ secrets.HUGGINGFACE_PUSH }}

diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml
@@ -14,5 +14,5 @@ jobs:
       commit_sha: ${{ github.event.pull_request.head.sha }}
       pr_number: ${{ github.event.number }}
       package: transformers
-      languages: de en es fr hi it ko pt tr zh ja te
+      languages: ar de en es fr hi it ko pt tr zh ja te
       custom_container: huggingface/transformers-doc-builder
diff --git a/.github/workflows/ssh-runner.yml b/.github/workflows/ssh-runner.yml
@@ -58,8 +58,19 @@ jobs:
         #because the SSH can be enabled dynamically if the workflow failed, so we need to store slack infos to be able to retrieve them during the waitforssh step
         shell: bash
         run: |
-          if [ "${{ secrets[format('{0}_{1}', github.actor, 'SLACK_ID')] }}" != "" ]; then
-            echo "SLACKCHANNEL=${{ secrets[format('{0}_{1}', github.actor, 'SLACK_ID')] }}" >> $GITHUB_ENV
+          echo "${{ github.actor }}"
+          github_actor=${{ github.actor }}
+          github_actor=${github_actor/'-'/'_'}
+          echo "$github_actor"
+          echo "github_actor=$github_actor" >> $GITHUB_ENV
+
+      - name: Store Slack infos
+        #because the SSH can be enabled dynamically if the workflow failed, so we need to store slack infos to be able to retrieve them during the waitforssh step
+        shell: bash
+        run: |
+          echo "${{ env.github_actor }}"
+          if [ "${{ secrets[format('{0}_{1}', env.github_actor, 'SLACK_ID')] }}" != "" ]; then
+            echo "SLACKCHANNEL=${{ secrets[format('{0}_{1}', env.github_actor, 'SLACK_ID')] }}" >> $GITHUB_ENV
           else
             echo "SLACKCHANNEL=${{ secrets.SLACK_CIFEEDBACK_CHANNEL }}" >> $GITHUB_ENV
           fi

diff --git a/README.md b/README.md
@@ -48,7 +48,8 @@ limitations under the License.
         <a href="https://github.com/huggingface/transformers/blob/main/i18n/README_fr.md">Français</a> |
         <a href="https://github.com/huggingface/transformers/blob/main/i18n/README_de.md">Deutsch</a> |
         <a href="https://github.com/huggingface/transformers/blob/main/i18n/README_vi.md">Tiếng Việt</a> |
-	<a href="https://github.com/huggingface/transformers/blob/main/i18n/README_ar.md">العربية</a> |
+        <a href="https://github.com/huggingface/transformers/blob/main/i18n/README_ar.md">العربية</a> |
+        <a href="https://github.com/huggingface/transformers/blob/main/i18n/README_ur.md">اردو</a> |
     </p>
 </h4>
 

diff --git a/docs/source/ar/_config.py b/docs/source/ar/_config.py
@@ -0,0 +1,14 @@
+# docstyle-ignore
+INSTALL_CONTENT = """
+# Transformers installation
+! pip install transformers datasets evaluate accelerate
+# To install from source instead of the last release, comment the command above and uncomment the following one.
+# ! pip install git+https://github.com/huggingface/transformers.git
+"""
+
+notebook_first_cells = [{"type": "code", "content": INSTALL_CONTENT}]
+black_avoid_patterns = {
+    "{processor_class}": "FakeProcessorClass",
+    "{model_class}": "FakeModelClass",
+    "{object_class}": "FakeObjectClass",
+}