feat(ml): export clip models to ONNX and host models on Hugging Face (#4700)

* export clip models

* export to hf

refactored export code

* export mclip, general refactoring

cleanup

* updated conda deps

* do transforms with pillow and numpy, add tokenization config to export, general refactoring

* moved conda dockerfile, re-added poetry

* minor fixes

* updated link

* updated tests

* removed `requirements.txt` from workflow

* fixed mimalloc path

* removed torchvision

* cleaner np typing

* review suggestions

* update default model name

* update test

machine-learning/app/models/__init__.py

@@ -1,3 +1,25 @@
-from .clip import CLIPEncoder
+from typing import Any
+
+from app.schemas import ModelType
+
+from .base import InferenceModel
+from .clip import MCLIPEncoder, OpenCLIPEncoder, is_mclip, is_openclip
 from .facial_recognition import FaceRecognizer
 from .image_classification import ImageClassifier
+
+
+def from_model_type(model_type: ModelType, model_name: str, **model_kwargs: Any) -> InferenceModel:
+    match model_type:
+        case ModelType.CLIP:
+            if is_openclip(model_name):
+                return OpenCLIPEncoder(model_name, **model_kwargs)
+            elif is_mclip(model_name):
+                return MCLIPEncoder(model_name, **model_kwargs)
+            else:
+                raise ValueError(f"Unknown CLIP model {model_name}")
+        case ModelType.FACIAL_RECOGNITION:
+            return FaceRecognizer(model_name, **model_kwargs)
+        case ModelType.IMAGE_CLASSIFICATION:
+            return ImageClassifier(model_name, **model_kwargs)
+        case _:
+            raise ValueError(f"Unknown model type {model_type}")