version

.circleci/config.yml

@@ -31,13 +31,12 @@ jobs:
             source env/bin/activate
             pip install --upgrade pip
             pip install unittest-xml-reporting
-            cd llms/
             pip install -e ".[test]"
       - run:
           name: Run Python tests
           command: |
             source env/bin/activate
-            python -m xmlrunner discover -v llms/tests -o test-results/
+            python -m xmlrunner discover -v tests -o test-results/
       - store_test_results:
           path: test-results
 

mlx_lm/_version.py

@@ -1,3 +1,3 @@
 # Copyright © 2023-2024 Apple Inc.
 
-__version__ = "0.21.6"
+__version__ = "0.22.0"

mlx_lm/examples/pipeline_generate.py

@@ -24,6 +24,7 @@ from pathlib import Path
 import mlx.core as mx
 from huggingface_hub import snapshot_download
 from mlx.utils import tree_flatten
+
 from mlx_lm import load, stream_generate
 from mlx_lm.utils import load_model, load_tokenizer
 

mlx_lm/models/plamo2.py

@@ -6,6 +6,7 @@ from typing import Any, Optional
 
 import mlx.core as mx
 import mlx.nn as nn
+
 from mlx_lm.models.base import BaseModelArgs, create_attention_mask
 
 from .cache import KVCache, MambaCache

tests/test_datsets.py

@@ -6,9 +6,10 @@ import tempfile
 import types
 import unittest
 
-from mlx_lm.tuner import datasets
 from transformers import AutoTokenizer
 
+from mlx_lm.tuner import datasets
+
 HF_MODEL_PATH = "mlx-community/Qwen1.5-0.5B-Chat-4bit"
 
 

tests/test_finetune.py

@@ -11,6 +11,7 @@ import mlx.core as mx
 import mlx.nn as nn
 import mlx.optimizers as opt
 from mlx.utils import tree_flatten
+
 from mlx_lm import lora, tuner
 from mlx_lm.tuner.dora import DoRAEmbedding, DoRALinear
 from mlx_lm.tuner.lora import LoRAEmbedding, LoRALinear

tests/test_gguf.py

@@ -5,6 +5,7 @@ from pathlib import Path
 from unittest.mock import MagicMock, patch
 
 import mlx.core as mx
+
 from mlx_lm.gguf import convert_to_gguf
 
 

tests/test_models.py

@@ -4,6 +4,7 @@ import unittest
 import mlx.core as mx
 import mlx.nn as nn
 from mlx.utils import tree_map
+
 from mlx_lm.models import rope_utils
 from mlx_lm.models.base import create_causal_mask
 from mlx_lm.models.cache import KVCache, RotatingKVCache, make_prompt_cache

tests/test_prompt_cache.py

@@ -6,6 +6,7 @@ import tempfile
 import unittest
 
 import mlx.core as mx
+
 from mlx_lm.models.cache import (
     KVCache,
     MambaCache,

tests/test_sample_utils.py

@@ -1,6 +1,7 @@
 import unittest
 
 import mlx.core as mx
+
 from mlx_lm.sample_utils import apply_min_p, apply_top_k, apply_top_p
 
 

tests/test_server.py

@@ -6,6 +6,7 @@ import threading
 import unittest
 
 import requests
+
 from mlx_lm.server import APIHandler
 from mlx_lm.utils import load
 

tests/test_tokenizers.py

@@ -4,6 +4,7 @@ import unittest
 from pathlib import Path
 
 from huggingface_hub import snapshot_download
+
 from mlx_lm.tokenizer_utils import (
     BPEStreamingDetokenizer,
     NaiveStreamingDetokenizer,

tests/test_tuner_utils.py

@@ -6,6 +6,7 @@ from io import StringIO
 from unittest.mock import MagicMock
 
 import mlx.nn as nn
+
 from mlx_lm.tuner.lora import LoRALinear
 from mlx_lm.tuner.utils import print_trainable_parameters
 

tests/test_utils.py

@@ -7,6 +7,7 @@ import unittest
 import mlx.core as mx
 import mlx.nn as nn
 from mlx.utils import tree_flatten
+
 from mlx_lm import utils
 
 HF_MODEL_PATH = "mlx-community/Qwen1.5-0.5B-Chat-4bit"

tests/test_utils_load_model.py

@@ -2,6 +2,7 @@ import unittest
 from pathlib import Path
 
 import mlx.nn as nn
+
 from mlx_lm.models.qwen2 import Model as Qwen2Model
 from mlx_lm.utils import get_model_path, load_model