Add handler.py to resolve “no handler.py file found” deployment error

**Title:** Add handler.py to resolve “no handler.py file found” deployment error

### Why

Deploying **allenai/olmOCR‑7B‑0725** on Hugging Face Inference Endpoints failed because the repository lacked a `handler.py`. A handler is required so the service knows how to run inference.
### What changed

* **Added `handler.py`**

* Loads the model and processor from `allenai/olmOCR‑7B‑0725`
* Accepts an image under the `inputs` key
* Reads `max_new_tokens` from `data["parameters"]` and defaults to `256` if not supplied
* Returns the OCR text in `generated_text`

handler.py

@@ -0,0 +1,33 @@
+from typing import Any
+import torch
+from transformers import AutoModelForSeq2SeqLM, AutoProcessor
+
+class EndpointHandler:
+    """
+    Handler for allenai/olmOCR-7B-0725
+
+    Input:
+      {
+        "inputs": <PIL.Image | base64 str | URL>,
+        "parameters": {"max_new_tokens": <int, optional>}
+      }
+
+    Output: {"generated_text": <str>}
+    """
+
+    def __init__(self, path: str = "") -> None:
+        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+        model_path = path or "allenai/olmOCR-7B-0725"
+        self.processor = AutoProcessor.from_pretrained(model_path)
+        self.model = AutoModelForSeq2SeqLM.from_pretrained(model_path).to(self.device)
+
+    def __call__(self, data: dict) -> Any:
+        image = data.get("inputs")
+        params = data.get("parameters", {})
+        max_tokens = params.get("max_new_tokens", 256)
+
+        inputs = self.processor(images=image, return_tensors="pt").to(self.device)
+        ids = self.model.generate(**inputs, max_new_tokens=max_tokens)
+        text = self.processor.batch_decode(ids, skip_special_tokens=True)[0]
+
+        return {"generated_text": text}