add commit description

app.py

@@ -84,8 +84,8 @@ with gr.Blocks() as demo:
     gr.Markdown(DESCRIPTION)
 
     with gr.Row():
-        input_token = gr.Textbox(max_lines=1, label="Hugging Face token"),
-        input_model = gr.Textbox(max_lines=1, label="Model name", placeholder="textattack/distilbert-base-cased-CoLA"),
+        input_token = gr.Textbox(max_lines=1, label="Hugging Face token")
+        input_model = gr.Textbox(max_lines=1, label="Model name", placeholder="textattack/distilbert-base-cased-CoLA")
         input_task = gr.Textbox(value="auto", max_lines=1, label="Task (can be left blank, will be automatically inferred)")
         output = gr.Markdown(label="Output")
     

onnx_export.py

@@ -17,6 +17,8 @@ from typing import Optional, Tuple, List
 from huggingface_hub import CommitOperationAdd, HfApi, hf_hub_download, get_repo_discussions
 from huggingface_hub.file_download import repo_folder_name
 
+SPACES_URL = "https://huggingface.co/spaces/optimum/exporters"
+
 def previous_pr(api: "HfApi", model_id: str, pr_title: str) -> Optional["Discussion"]:
     try:
         discussions = api.get_repo_discussions(repo_id=model_id)
@@ -90,6 +92,8 @@ def convert(api: "HfApi", model_id: str, task: str, force: bool = False) -> Tupl
     info = api.model_info(model_id)
     filenames = set(s.rfilename for s in info.siblings)
 
+    requesting_user = api.whoami()["name"]
+
     if task == "auto":
         try:
             task = TasksManager.infer_task_from_model(model_id)
@@ -111,10 +115,21 @@ def convert(api: "HfApi", model_id: str, task: str, force: bool = False) -> Tupl
             else:
                 operations = convert_onnx(model_id, task, folder)
 
+                commit_description = f"""
+                Beep boop I am the [ONNX export bot 🤖🏎️]({SPACES_URL}). On behalf of [{requesting_user}](https://huggingface.co/{requesting_user}), I would like to
+                add to this repository the model converted to ONNX.
+
+                What is ONNX? It stands for "Open Neural Network Exchange", and is the most commonly used open standard for machine learning interoperability.
+                You can find out more at [onnx.ai](https://onnx.ai/)!
+
+                The exported ONNX model can be then be consumed by various backends as TensorRT or TVM, or simply be used in a few lines
+                with 🤗 Optimum through ONNX Runtime, check out how [here](https://huggingface.co/docs/optimum/main/en/onnxruntime/usage_guides/models)!
+                """
                 new_pr = api.create_commit(
                     repo_id=model_id,
                     operations=operations,
                     commit_message=pr_title,
+                    commit_description=commit_description,  # TODO
                     create_pr=True,
                 )
         finally: