isort all imports

batch_generate_example.py

@@ -1,6 +1,7 @@
-from moondream.hf import Moondream, detect_device, LATEST_REVISION
-from transformers import AutoTokenizer
 from PIL import Image
+from transformers import AutoTokenizer
+
+from moondream.hf import LATEST_REVISION, Moondream, detect_device
 
 device, dtype = detect_device()
 

clients/python/README.md

@@ -23,7 +23,7 @@ Then download the model weights:
 ```
 # int8 weights (recommended):
 wget "https://huggingface.co/vikhyatk/moondream2/resolve/client/moondream-latest-int8.bin.gz?download=true" -O - | gunzip > moondream-latest-int8.bin
-# ...or, for FP16 weights:
+# ...or, for fp16 weights:
 wget "https://huggingface.co/vikhyatk/moondream2/resolve/client/moondream-latest-f16.bin.gz?download=true" -O - | gunzip > moondream-latest-f16.bin
 ```
 
@@ -56,7 +56,3 @@ answer = model.answer_question(encoded_image, question)["answer"]
 for t in model.answer_question(encoded_image, question, stream=True)["answer"]:
     print(t, end="", flush=True)
 ```
-
-### Accelerators
-
-(TK -- document how ONNX execution providers work.)

clients/python/moondream/preprocess.py

@@ -1,5 +1,6 @@
-import numpy as np
 from typing import List, Tuple, Union
+
+import numpy as np
 from PIL import Image
 
 

clients/python/moondream/vl.py

@@ -1,16 +1,17 @@
-import onnx
-import onnxruntime as ort
-import numpy as np
+import json
 import os
 import tarfile
-import json
-
-from typing import Generator, List, Union, Optional, Dict, TypedDict, Any
-from PIL import Image
 from dataclasses import dataclass
 from io import BytesIO
+from typing import Any, Dict, Generator, List, Optional, TypedDict, Union
+
+import numpy as np
+import onnxruntime as ort
+from PIL import Image
 from tokenizers import Tokenizer
 
+import onnx
+
 from .preprocess import create_patches