- Removed unused Python imports (#683)

- bert/model.py:10: tree_unflatten
  - bert/model.py:2: dataclass
  - bert/model.py:8: numpy
  - cifar/resnet.py:6: Any
  - clip/model.py:15: tree_flatten
  - clip/model.py:9: Union
  - gcn/main.py:8: download_cora
  - gcn/main.py:9: cross_entropy
  - llms/gguf_llm/models.py:12: tree_flatten, tree_unflatten
  - llms/gguf_llm/models.py:9: numpy
  - llms/mixtral/mixtral.py:12: tree_map
  - llms/mlx_lm/models/dbrx.py:2: Dict, Union
  - llms/mlx_lm/tuner/trainer.py:5: partial
  - llms/speculative_decoding/decoder.py:1: dataclass, field
  - llms/speculative_decoding/decoder.py:2: Optional
  - llms/speculative_decoding/decoder.py:5: mlx.nn
  - llms/speculative_decoding/decoder.py:6: numpy
  - llms/speculative_decoding/main.py:2: glob
  - llms/speculative_decoding/main.py:3: json
  - llms/speculative_decoding/main.py:5: Path
  - llms/speculative_decoding/main.py:8: mlx.nn
  - llms/speculative_decoding/model.py:6: tree_unflatten
  - llms/speculative_decoding/model.py:7: AutoTokenizer
  - llms/tests/test_lora.py:13: yaml_loader
  - lora/lora.py:14: tree_unflatten
  - lora/models.py:11: numpy
  - lora/models.py:3: glob
  - speechcommands/kwt.py:1: Any
  - speechcommands/main.py:7: mlx.data
  - stable_diffusion/stable_diffusion/model_io.py:4: partial
  - whisper/benchmark.py:5: sys
  - whisper/test.py:5: subprocess
  - whisper/whisper/audio.py:6: Optional
  - whisper/whisper/decoding.py:8: mlx.nn

clip/model.py

@@ -6,13 +6,12 @@ import logging
 import math
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Optional, Union
+from typing import Optional
 
 import mlx.core as mx
 import mlx.nn as nn
 from mlx.core import linalg as LA
 from mlx.nn.losses import cross_entropy
-from mlx.utils import tree_flatten
 
 
 @dataclass