Merge branch 'main' into add-got-ocr2

.circleci/config.yml

@@ -58,14 +58,14 @@ jobs:
                 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/transformed_artifacts.json
             - store_artifacts:

.circleci/create_circleci_config.py

@@ -32,17 +32,30 @@
     "RUN_PT_FLAX_CROSS_TESTS": False,
 }
 # Disable the use of {"s": None} as the output is way too long, causing the navigation on CircleCI impractical
-COMMON_PYTEST_OPTIONS = {"max-worker-restart": 0, "dist": "loadfile", "vvv": None, "rsf":None}
+COMMON_PYTEST_OPTIONS = {"max-worker-restart": 0, "dist": "loadfile", "vvv": None, "rsfE":None}
 DEFAULT_DOCKER_IMAGE = [{"image": "cimg/python:3.8.12"}]
 
 
 class EmptyJob:
     job_name = "empty"
 
     def to_dict(self):
+        steps = [{"run": 'ls -la'}]
+        if self.job_name == "collection_job":
+            steps.extend(
+                [
+                    "checkout",
+                    {"run": "pip install requests || true"},
+                    {"run": """while [[ $(curl --location --request GET "https://circleci.com/api/v2/workflow/$CIRCLE_WORKFLOW_ID/job" --header "Circle-Token: $CCI_TOKEN"| jq -r '.items[]|select(.name != "collection_job")|.status' | grep -c "running") -gt 0 ]]; do sleep 5; done || true"""},
+                    {"run": 'python utils/process_circleci_workflow_test_reports.py --workflow_id $CIRCLE_WORKFLOW_ID || true'},
+                    {"store_artifacts": {"path": "outputs"}},
+                    {"run": 'echo "All required jobs have now completed"'},
+                ]
+            )
+
         return {
             "docker": copy.deepcopy(DEFAULT_DOCKER_IMAGE),
-            "steps":["checkout"],
+            "steps": steps,
         }
 
 
@@ -133,7 +146,7 @@ def to_dict(self):
                 "command": """dpkg-query --show --showformat='${Installed-Size}\t${Package}\n' | sort -rh | head -25 | sort -h | awk '{ package=$2; sub(".*/", "", package); printf("%.5f GB %s\n", $1/1024/1024, package)}' || true"""}
             },
             {"run": {"name": "Create `test-results` directory", "command": "mkdir test-results"}},
-            {"run": {"name": "Get files to test", "command":f'curl -L -o {self.job_name}_test_list.txt <<pipeline.parameters.{self.job_name}_test_list>>' if self.name != "pr_documentation_tests" else 'echo "Skipped"'}},
+            {"run": {"name": "Get files to test", "command":f'curl -L -o {self.job_name}_test_list.txt <<pipeline.parameters.{self.job_name}_test_list>> --header "Circle-Token: $CIRCLE_TOKEN"' if self.name != "pr_documentation_tests" else 'echo "Skipped"'}},
                         {"run": {"name": "Split tests across parallel nodes: show current parallel tests",
                     "command": f"TESTS=$(circleci tests split  --split-by=timings {self.job_name}_test_list.txt) && echo $TESTS > splitted_tests.txt && echo $TESTS | tr ' ' '\n'" if self.parallelism else f"awk '{{printf \"%s \", $0}}' {self.job_name}_test_list.txt > splitted_tests.txt"
                     }
@@ -352,6 +365,7 @@ def job_name(self):
 DOC_TESTS = [doc_test_job]
 ALL_TESTS = REGULAR_TESTS + EXAMPLES_TESTS + PIPELINE_TESTS + REPO_UTIL_TESTS + DOC_TESTS + [custom_tokenizers_job] + [exotic_models_job]  # fmt: skip
 
+
 def create_circleci_config(folder=None):
     if folder is None:
         folder = os.getcwd()
@@ -361,7 +375,13 @@ def create_circleci_config(folder=None):
 
     if len(jobs) == 0:
         jobs = [EmptyJob()]
-    print("Full list of job name inputs", {j.job_name + "_test_list":{"type":"string", "default":''} for j in jobs})
+    else:
+        print("Full list of job name inputs", {j.job_name + "_test_list":{"type":"string", "default":''} for j in jobs})
+        # Add a job waiting all the test jobs and aggregate their test summary files at the end
+        collection_job = EmptyJob()
+        collection_job.job_name = "collection_job"
+        jobs = [collection_job] + jobs
+
     config = {
         "version": "2.1",
         "parameters": {
@@ -371,9 +391,14 @@ def create_circleci_config(folder=None):
             **{j.job_name + "_test_list":{"type":"string", "default":''} for j in jobs},
             **{j.job_name + "_parallelism":{"type":"integer", "default":1} for j in jobs},
         },
-        "jobs" : {j.job_name: j.to_dict() for j in jobs},
-        "workflows": {"version": 2, "run_tests": {"jobs": [j.job_name for j in jobs]}}
+        "jobs": {j.job_name: j.to_dict() for j in jobs}
     }
+    if "CIRCLE_TOKEN" in os.environ:
+        # For private forked repo. (e.g. new model addition)
+        config["workflows"] = {"version": 2, "run_tests": {"jobs": [{j.job_name: {"context": ["TRANSFORMERS_CONTEXT"]}} for j in jobs]}}
+    else:
+        # For public repo. (e.g. `transformers`)
+        config["workflows"] = {"version": 2, "run_tests": {"jobs": [j.job_name for j in jobs]}}
     with open(os.path.join(folder, "generated_config.yml"), "w") as f:
         f.write(yaml.dump(config, sort_keys=False, default_flow_style=False).replace("' << pipeline", " << pipeline").replace(">> '", " >>"))
 

.github/workflows/self-push-amd-mi210-caller.yml

@@ -1,25 +1,25 @@
-name: Self-hosted runner (AMD mi210 CI caller)
-
-on:
-  workflow_run:
-    workflows: ["Self-hosted runner (push-caller)"]
-    branches: ["main"]
-    types: [completed]
-  push:
-    branches:
-      - run_amd_push_ci_caller*
-    paths:
-      - "src/**"
-      - "tests/**"
-      - ".github/**"
-      - "templates/**"
-      - "utils/**"
-
-jobs:
-  run_amd_ci:
-    name: AMD mi210
-    if: (cancelled() != true) && ((github.event_name == 'workflow_run') || ((github.event_name == 'push') && startsWith(github.ref_name, 'run_amd_push_ci_caller')))
-    uses: ./.github/workflows/self-push-amd.yml
-    with:
-      gpu_flavor: mi210
-    secrets: inherit
+name: Self-hosted runner (AMD mi210 CI caller)
+
+on:
+  #workflow_run:
+  #  workflows: ["Self-hosted runner (push-caller)"]
+  #  branches: ["main"]
+  #  types: [completed]
+  push:
+    branches:
+      - run_amd_push_ci_caller*
+    paths:
+      - "src/**"
+      - "tests/**"
+      - ".github/**"
+      - "templates/**"
+      - "utils/**"
+
+jobs:
+  run_amd_ci:
+    name: AMD mi210
+    if: (cancelled() != true) && ((github.event_name == 'workflow_run') || ((github.event_name == 'push') && startsWith(github.ref_name, 'run_amd_push_ci_caller')))
+    uses: ./.github/workflows/self-push-amd.yml
+    with:
+      gpu_flavor: mi210
+    secrets: inherit

.github/workflows/self-push-amd-mi250-caller.yml

@@ -1,25 +1,25 @@
-name: Self-hosted runner (AMD mi250 CI caller)
-
-on:
-  workflow_run:
-    workflows: ["Self-hosted runner (push-caller)"]
-    branches: ["main"]
-    types: [completed]
-  push:
-    branches:
-      - run_amd_push_ci_caller*
-    paths:
-      - "src/**"
-      - "tests/**"
-      - ".github/**"
-      - "templates/**"
-      - "utils/**"
-
-jobs:
-  run_amd_ci:
-    name: AMD mi250
-    if: (cancelled() != true) && ((github.event_name == 'workflow_run') || ((github.event_name == 'push') && startsWith(github.ref_name, 'run_amd_push_ci_caller')))
-    uses: ./.github/workflows/self-push-amd.yml
-    with:
-      gpu_flavor: mi250
-    secrets: inherit
+name: Self-hosted runner (AMD mi250 CI caller)
+
+on:
+  #workflow_run:
+  #  workflows: ["Self-hosted runner (push-caller)"]
+  #  branches: ["main"]
+  #  types: [completed]
+  push:
+    branches:
+      - run_amd_push_ci_caller*
+    paths:
+      - "src/**"
+      - "tests/**"
+      - ".github/**"
+      - "templates/**"
+      - "utils/**"
+
+jobs:
+  run_amd_ci:
+    name: AMD mi250
+    if: (cancelled() != true) && ((github.event_name == 'workflow_run') || ((github.event_name == 'push') && startsWith(github.ref_name, 'run_amd_push_ci_caller')))
+    uses: ./.github/workflows/self-push-amd.yml
+    with:
+      gpu_flavor: mi250
+    secrets: inherit

.github/workflows/self-push-amd-mi300-caller.yml

@@ -1,10 +1,10 @@
 name: Self-hosted runner (AMD mi300 CI caller)
 
 on:
-  workflow_run:
-    workflows: ["Self-hosted runner (push-caller)"]
-    branches: ["main"]
-    types: [completed]
+  #workflow_run:
+  #  workflows: ["Self-hosted runner (push-caller)"]
+  #  branches: ["main"]
+  #  types: [completed]
   push:
     branches:
       - run_amd_push_ci_caller*

docker/transformers-pytorch-amd-gpu/Dockerfile

@@ -1,4 +1,4 @@
-FROM rocm/dev-ubuntu-22.04:6.0.2
+FROM rocm/dev-ubuntu-22.04:6.1
 # rocm/pytorch has no version with 2.1.0
 LABEL maintainer="Hugging Face"
 
@@ -11,7 +11,7 @@ RUN apt update && \
 
 RUN python3 -m pip install --no-cache-dir --upgrade pip numpy
 
-RUN python3 -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.0
+RUN python3 -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.1
 
 RUN python3 -m pip install --no-cache-dir --upgrade importlib-metadata setuptools ninja git+https://github.com/facebookresearch/detectron2.git pytesseract "itsdangerous<2.1.0"
 
@@ -30,5 +30,5 @@ RUN python3 -m pip uninstall -y tensorflow flax
 # this line must be added in order for python to be aware of transformers.
 RUN cd transformers && python3 setup.py develop
 
-# Remove nvml as it is not compatible with ROCm. apex is not tested on NVIDIA either.
-RUN python3 -m pip uninstall py3nvml pynvml apex -y
+# Remove nvml and nvidia-ml-py as it is not compatible with ROCm. apex is not tested on NVIDIA either.
+RUN python3 -m pip uninstall py3nvml pynvml nvidia-ml-py apex -y

docs/source/ar/_toctree.yml

@@ -133,12 +133,18 @@
     title: المعايير
   - local: notebooks
     title: دفاتر الملاحظات مع الأمثلة
-#   - local: community
-#     title: موارد المجتمع
+  - local: community
+    title: موارد المجتمع
   - local: troubleshooting
     title: استكشاف الأخطاء وإصلاحها
   - local: gguf
     title: التوافق مع ملفات GGUF
+  - local: tiktoken
+    title: التوافق مع ملفات TikToken
+  - local: modular_transformers
+    title: الوحدات النمطية في `transformers`
+  - local: how_to_hack_models
+    title: اختراق النموذج (الكتابة فوق فئة لاستخدامك)
   title: أدلة المطورين
 # - sections:
 #   - local: quantization/overview