LICENSE
README.md
pyproject.toml
requirements.txt
mlx_vlm/__init__.py
mlx_vlm/__main__.py
mlx_vlm/chat.py
mlx_vlm/chat_ui.py
mlx_vlm/convert.py
mlx_vlm/deprecation.py
mlx_vlm/generate.py
mlx_vlm/lora.py
mlx_vlm/prompt_utils.py
mlx_vlm/sample_utils.py
mlx_vlm/server.py
mlx_vlm/smolvlm_video_generate.py
mlx_vlm/tokenizer_utils.py
mlx_vlm/turboquant.py
mlx_vlm/utils.py
mlx_vlm/version.py
mlx_vlm/video_generate.py
mlx_vlm.egg-info/PKG-INFO
mlx_vlm.egg-info/SOURCES.txt
mlx_vlm.egg-info/dependency_links.txt
mlx_vlm.egg-info/entry_points.txt
mlx_vlm.egg-info/requires.txt
mlx_vlm.egg-info/top_level.txt
mlx_vlm/evals/__init__.py
mlx_vlm/evals/math_vista.py
mlx_vlm/evals/mmmu.py
mlx_vlm/evals/mmstar.py
mlx_vlm/evals/ocrbench.py
mlx_vlm/evals/utils.py
mlx_vlm/models/__init__.py
mlx_vlm/models/base.py
mlx_vlm/models/cache.py
mlx_vlm/models/interpolate.py
mlx_vlm/models/kernels.py
mlx_vlm/models/aya_vision/__init__.py
mlx_vlm/models/aya_vision/aya_vision.py
mlx_vlm/models/aya_vision/config.py
mlx_vlm/models/aya_vision/language.py
mlx_vlm/models/aya_vision/processing_aya_vision.py
mlx_vlm/models/aya_vision/vision.py
mlx_vlm/models/deepseek_vl_v2/__init__.py
mlx_vlm/models/deepseek_vl_v2/config.py
mlx_vlm/models/deepseek_vl_v2/conversation.py
mlx_vlm/models/deepseek_vl_v2/deepseek_vl_v2.py
mlx_vlm/models/deepseek_vl_v2/language.py
mlx_vlm/models/deepseek_vl_v2/processing_deepsek_vl_v2.py
mlx_vlm/models/deepseek_vl_v2/vision.py
mlx_vlm/models/deepseekocr/__init__.py
mlx_vlm/models/deepseekocr/config.py
mlx_vlm/models/deepseekocr/conversation.py
mlx_vlm/models/deepseekocr/deepseekocr.py
mlx_vlm/models/deepseekocr/language.py
mlx_vlm/models/deepseekocr/processing_deepseekocr.py
mlx_vlm/models/deepseekocr/sam.py
mlx_vlm/models/deepseekocr/vision.py
mlx_vlm/models/deepseekocr_2/__init__.py
mlx_vlm/models/deepseekocr_2/config.py
mlx_vlm/models/deepseekocr_2/deepseekocr_2.py
mlx_vlm/models/deepseekocr_2/processing_deepseekocr.py
mlx_vlm/models/deepseekocr_2/vision.py
mlx_vlm/models/dots_ocr/__init__.py
mlx_vlm/models/dots_ocr/config.py
mlx_vlm/models/dots_ocr/dots_ocr.py
mlx_vlm/models/dots_ocr/processing_dots_ocr.py
mlx_vlm/models/dots_ocr/vision.py
mlx_vlm/models/ernie4_5_moe_vl/__init__.py
mlx_vlm/models/ernie4_5_moe_vl/config.py
mlx_vlm/models/ernie4_5_moe_vl/ernie4_5_moe_vl.py
mlx_vlm/models/ernie4_5_moe_vl/language.py
mlx_vlm/models/ernie4_5_moe_vl/processing_ernie4_5_moe_vl.py
mlx_vlm/models/ernie4_5_moe_vl/vision.py
mlx_vlm/models/falcon_ocr/__init__.py
mlx_vlm/models/falcon_ocr/config.py
mlx_vlm/models/falcon_ocr/falcon_ocr.py
mlx_vlm/models/falcon_ocr/language.py
mlx_vlm/models/falcon_ocr/layout.py
mlx_vlm/models/falcon_ocr/processing_falcon_ocr.py
mlx_vlm/models/falcon_perception/__init__.py
mlx_vlm/models/falcon_perception/anyup.py
mlx_vlm/models/falcon_perception/config.py
mlx_vlm/models/falcon_perception/falcon_perception.py
mlx_vlm/models/falcon_perception/language.py
mlx_vlm/models/falcon_perception/processing_falcon_perception.py
mlx_vlm/models/fastvlm/__init__.py
mlx_vlm/models/fastvlm/config.py
mlx_vlm/models/fastvlm/fastvlm.py
mlx_vlm/models/fastvlm/language.py
mlx_vlm/models/fastvlm/processing.py
mlx_vlm/models/fastvlm/vision.py
mlx_vlm/models/florence2/__init__.py
mlx_vlm/models/florence2/config.py
mlx_vlm/models/florence2/florence2.py
mlx_vlm/models/florence2/language.py
mlx_vlm/models/florence2/processing_florence2.py
mlx_vlm/models/florence2/vision.py
mlx_vlm/models/gemma3/__init__.py
mlx_vlm/models/gemma3/config.py
mlx_vlm/models/gemma3/gemma3.py
mlx_vlm/models/gemma3/language.py
mlx_vlm/models/gemma3/processing_gemma3.py
mlx_vlm/models/gemma3/vision.py
mlx_vlm/models/gemma3n/__init__.py
mlx_vlm/models/gemma3n/audio.py
mlx_vlm/models/gemma3n/config.py
mlx_vlm/models/gemma3n/gemma3n.py
mlx_vlm/models/gemma3n/language.py
mlx_vlm/models/gemma3n/processing_gemma3n.py
mlx_vlm/models/gemma3n/vision.py
mlx_vlm/models/gemma4/__init__.py
mlx_vlm/models/gemma4/audio.py
mlx_vlm/models/gemma4/audio_feature_extractor.py
mlx_vlm/models/gemma4/config.py
mlx_vlm/models/gemma4/gemma4.py
mlx_vlm/models/gemma4/language.py
mlx_vlm/models/gemma4/processing_gemma4.py
mlx_vlm/models/gemma4/vision.py
mlx_vlm/models/glm4v/__init__.py
mlx_vlm/models/glm4v/config.py
mlx_vlm/models/glm4v/glm4v.py
mlx_vlm/models/glm4v/language.py
mlx_vlm/models/glm4v/processing.py
mlx_vlm/models/glm4v/vision.py
mlx_vlm/models/glm4v_moe/__init__.py
mlx_vlm/models/glm4v_moe/config.py
mlx_vlm/models/glm4v_moe/glm4v_moe.py
mlx_vlm/models/glm4v_moe/language.py
mlx_vlm/models/glm4v_moe/processing.py
mlx_vlm/models/glm4v_moe/vision.py
mlx_vlm/models/glm_ocr/__init__.py
mlx_vlm/models/glm_ocr/config.py
mlx_vlm/models/glm_ocr/glm_ocr.py
mlx_vlm/models/glm_ocr/language.py
mlx_vlm/models/glm_ocr/processing.py
mlx_vlm/models/glm_ocr/vision.py
mlx_vlm/models/granite4_vision/__init__.py
mlx_vlm/models/granite4_vision/config.py
mlx_vlm/models/granite4_vision/downsampling.py
mlx_vlm/models/granite4_vision/granite4_vision.py
mlx_vlm/models/granite4_vision/language.py
mlx_vlm/models/granite4_vision/processing_granite4_vision.py
mlx_vlm/models/granite4_vision/qformer.py
mlx_vlm/models/granite4_vision/vision.py
mlx_vlm/models/granite_vision/__init__.py
mlx_vlm/models/granite_vision/config.py
mlx_vlm/models/granite_vision/granite_vision.py
mlx_vlm/models/granite_vision/language.py
mlx_vlm/models/granite_vision/processing_granite_vision.py
mlx_vlm/models/granite_vision/vision.py
mlx_vlm/models/hunyuan_vl/__init__.py
mlx_vlm/models/hunyuan_vl/config.py
mlx_vlm/models/hunyuan_vl/hunyuan_vl.py
mlx_vlm/models/hunyuan_vl/language.py
mlx_vlm/models/hunyuan_vl/processing_hunyuan_vl.py
mlx_vlm/models/hunyuan_vl/vision.py
mlx_vlm/models/idefics2/__init__.py
mlx_vlm/models/idefics2/config.py
mlx_vlm/models/idefics2/idefics2.py
mlx_vlm/models/idefics2/language.py
mlx_vlm/models/idefics2/processing_idefics2.py
mlx_vlm/models/idefics2/vision.py
mlx_vlm/models/idefics3/__init__.py
mlx_vlm/models/idefics3/config.py
mlx_vlm/models/idefics3/idefics3.py
mlx_vlm/models/idefics3/language.py
mlx_vlm/models/idefics3/processing_idefics3.py
mlx_vlm/models/idefics3/vision.py
mlx_vlm/models/internvl_chat/__init__.py
mlx_vlm/models/internvl_chat/config.py
mlx_vlm/models/internvl_chat/internvl_chat.py
mlx_vlm/models/internvl_chat/language.py
mlx_vlm/models/internvl_chat/processor.py
mlx_vlm/models/internvl_chat/vision.py
mlx_vlm/models/jina_vlm/__init__.py
mlx_vlm/models/jina_vlm/config.py
mlx_vlm/models/jina_vlm/image_processor.py
mlx_vlm/models/jina_vlm/jina_vlm.py
mlx_vlm/models/jina_vlm/language.py
mlx_vlm/models/jina_vlm/processing_jinavlm.py
mlx_vlm/models/jina_vlm/vision.py
mlx_vlm/models/kimi_vl/__init__.py
mlx_vlm/models/kimi_vl/config.py
mlx_vlm/models/kimi_vl/kimi_vl.py
mlx_vlm/models/kimi_vl/language.py
mlx_vlm/models/kimi_vl/processing_kimi_vl.py
mlx_vlm/models/kimi_vl/vision.py
mlx_vlm/models/lfm2_vl/__init__.py
mlx_vlm/models/lfm2_vl/config.py
mlx_vlm/models/lfm2_vl/language.py
mlx_vlm/models/lfm2_vl/lfm2_vl.py
mlx_vlm/models/lfm2_vl/processing_lfm2_vl.py
mlx_vlm/models/lfm2_vl/vision.py
mlx_vlm/models/llama4/__init__.py
mlx_vlm/models/llama4/config.py
mlx_vlm/models/llama4/language.py
mlx_vlm/models/llama4/llama4.py
mlx_vlm/models/llama4/processing_llama4.py
mlx_vlm/models/llama4/vision.py
mlx_vlm/models/llava/__init__.py
mlx_vlm/models/llava/config.py
mlx_vlm/models/llava/language.py
mlx_vlm/models/llava/llava.py
mlx_vlm/models/llava/processing_llava.py
mlx_vlm/models/llava/vision.py
mlx_vlm/models/llava_bunny/__init__.py
mlx_vlm/models/llava_bunny/config.py
mlx_vlm/models/llava_bunny/language.py
mlx_vlm/models/llava_bunny/llava_bunny.py
mlx_vlm/models/llava_bunny/vision.py
mlx_vlm/models/llava_next/__init__.py
mlx_vlm/models/llava_next/config.py
mlx_vlm/models/llava_next/language.py
mlx_vlm/models/llava_next/llava_next.py
mlx_vlm/models/llava_next/processing_llava_next.py
mlx_vlm/models/llava_next/vision.py
mlx_vlm/models/minicpmo/__init__.py
mlx_vlm/models/minicpmo/audio.py
mlx_vlm/models/minicpmo/config.py
mlx_vlm/models/minicpmo/minicpmo.py
mlx_vlm/models/minicpmo/processing_minicpmo.py
mlx_vlm/models/minicpmo/vision.py
mlx_vlm/models/mistral3/__init__.py
mlx_vlm/models/mistral3/config.py
mlx_vlm/models/mistral3/language.py
mlx_vlm/models/mistral3/mistral3.py
mlx_vlm/models/mistral3/processing_mistral3.py
mlx_vlm/models/mistral4/__init__.py
mlx_vlm/models/mistral4/language.py
mlx_vlm/models/mllama/__init__.py
mlx_vlm/models/mllama/config.py
mlx_vlm/models/mllama/language.py
mlx_vlm/models/mllama/mllama.py
mlx_vlm/models/mllama/processing_mllama.py
mlx_vlm/models/mllama/vision.py
mlx_vlm/models/molmo/__init__.py
mlx_vlm/models/molmo/config.py
mlx_vlm/models/molmo/language.py
mlx_vlm/models/molmo/molmo.py
mlx_vlm/models/molmo/processing_molmo.py
mlx_vlm/models/molmo/vision.py
mlx_vlm/models/molmo2/__init__.py
mlx_vlm/models/molmo2/config.py
mlx_vlm/models/molmo2/language.py
mlx_vlm/models/molmo2/molmo2.py
mlx_vlm/models/molmo2/processing.py
mlx_vlm/models/molmo2/vision.py
mlx_vlm/models/molmo_point/__init__.py
mlx_vlm/models/molmo_point/config.py
mlx_vlm/models/molmo_point/image_processing.py
mlx_vlm/models/molmo_point/language.py
mlx_vlm/models/molmo_point/molmo_point.py
mlx_vlm/models/molmo_point/point_utils.py
mlx_vlm/models/molmo_point/processing_molmo_point.py
mlx_vlm/models/molmo_point/vision.py
mlx_vlm/models/moondream3/__init__.py
mlx_vlm/models/moondream3/config.py
mlx_vlm/models/moondream3/image_crops.py
mlx_vlm/models/moondream3/language.py
mlx_vlm/models/moondream3/moondream3.py
mlx_vlm/models/moondream3/processing_moondream3.py
mlx_vlm/models/moondream3/vision.py
mlx_vlm/models/multi_modality/__init__.py
mlx_vlm/models/multi_modality/config.py
mlx_vlm/models/multi_modality/language.py
mlx_vlm/models/multi_modality/multi_modality.py
mlx_vlm/models/multi_modality/processing_multi_modality.py
mlx_vlm/models/multi_modality/sam.py
mlx_vlm/models/multi_modality/vision.py
mlx_vlm/models/paddleocr_vl/__init__.py
mlx_vlm/models/paddleocr_vl/config.py
mlx_vlm/models/paddleocr_vl/language.py
mlx_vlm/models/paddleocr_vl/paddleocr_vl.py
mlx_vlm/models/paddleocr_vl/processing_paddleocr_vl.py
mlx_vlm/models/paddleocr_vl/vision.py
mlx_vlm/models/paligemma/__init__.py
mlx_vlm/models/paligemma/config.py
mlx_vlm/models/paligemma/language.py
mlx_vlm/models/paligemma/paligemma.py
mlx_vlm/models/paligemma/processing_paligemma.py
mlx_vlm/models/paligemma/vision.py
mlx_vlm/models/phi3_v/__init__.py
mlx_vlm/models/phi3_v/config.py
mlx_vlm/models/phi3_v/language.py
mlx_vlm/models/phi3_v/phi3_v.py
mlx_vlm/models/phi3_v/processing_phi3_v.py
mlx_vlm/models/phi3_v/vision.py
mlx_vlm/models/phi4_siglip/__init__.py
mlx_vlm/models/phi4_siglip/config.py
mlx_vlm/models/phi4_siglip/language.py
mlx_vlm/models/phi4_siglip/phi4_siglip.py
mlx_vlm/models/phi4_siglip/processing_phi4_siglip.py
mlx_vlm/models/phi4_siglip/vision.py
mlx_vlm/models/phi4mm/__init__.py
mlx_vlm/models/phi4mm/audio.py
mlx_vlm/models/phi4mm/config.py
mlx_vlm/models/phi4mm/language.py
mlx_vlm/models/phi4mm/phi4mm.py
mlx_vlm/models/phi4mm/processing_phi4mm.py
mlx_vlm/models/phi4mm/vision.py
mlx_vlm/models/pixtral/__init__.py
mlx_vlm/models/pixtral/config.py
mlx_vlm/models/pixtral/language.py
mlx_vlm/models/pixtral/pixtral.py
mlx_vlm/models/pixtral/processing_pixtral.py
mlx_vlm/models/pixtral/vision.py
mlx_vlm/models/qwen2_5_vl/__init__.py
mlx_vlm/models/qwen2_5_vl/config.py
mlx_vlm/models/qwen2_5_vl/language.py
mlx_vlm/models/qwen2_5_vl/processing_qwen2_5_vl.py
mlx_vlm/models/qwen2_5_vl/qwen2_5_vl.py
mlx_vlm/models/qwen2_5_vl/vision.py
mlx_vlm/models/qwen2_vl/__init__.py
mlx_vlm/models/qwen2_vl/config.py
mlx_vlm/models/qwen2_vl/language.py
mlx_vlm/models/qwen2_vl/processing_qwen2_vl.py
mlx_vlm/models/qwen2_vl/qwen2_vl.py
mlx_vlm/models/qwen2_vl/vision.py
mlx_vlm/models/qwen3_5/__init__.py
mlx_vlm/models/qwen3_5/config.py
mlx_vlm/models/qwen3_5/language.py
mlx_vlm/models/qwen3_5/qwen3_5.py
mlx_vlm/models/qwen3_5/vision.py
mlx_vlm/models/qwen3_5_moe/__init__.py
mlx_vlm/models/qwen3_5_moe/config.py
mlx_vlm/models/qwen3_5_moe/language.py
mlx_vlm/models/qwen3_5_moe/qwen3_5_moe.py
mlx_vlm/models/qwen3_5_moe/vision.py
mlx_vlm/models/qwen3_omni_moe/__init__.py
mlx_vlm/models/qwen3_omni_moe/audio.py
mlx_vlm/models/qwen3_omni_moe/code2wav.py
mlx_vlm/models/qwen3_omni_moe/config.py
mlx_vlm/models/qwen3_omni_moe/language.py
mlx_vlm/models/qwen3_omni_moe/omni_utils.py
mlx_vlm/models/qwen3_omni_moe/processing_qwen3_omni_moe.py
mlx_vlm/models/qwen3_omni_moe/qwen3_omni_moe.py
mlx_vlm/models/qwen3_omni_moe/talker.py
mlx_vlm/models/qwen3_omni_moe/thinker.py
mlx_vlm/models/qwen3_omni_moe/vision.py
mlx_vlm/models/qwen3_vl/__init__.py
mlx_vlm/models/qwen3_vl/config.py
mlx_vlm/models/qwen3_vl/language.py
mlx_vlm/models/qwen3_vl/processing_qwen3_vl.py
mlx_vlm/models/qwen3_vl/qwen3_vl.py
mlx_vlm/models/qwen3_vl/vision.py
mlx_vlm/models/qwen3_vl_moe/__init__.py
mlx_vlm/models/qwen3_vl_moe/config.py
mlx_vlm/models/qwen3_vl_moe/language.py
mlx_vlm/models/qwen3_vl_moe/qwen3_vl_moe.py
mlx_vlm/models/qwen3_vl_moe/vision.py
mlx_vlm/models/rfdetr/__init__.py
mlx_vlm/models/rfdetr/config.py
mlx_vlm/models/rfdetr/convert.py
mlx_vlm/models/rfdetr/generate.py
mlx_vlm/models/rfdetr/language.py
mlx_vlm/models/rfdetr/processing_rfdetr.py
mlx_vlm/models/rfdetr/rfdetr.py
mlx_vlm/models/rfdetr/segmentation.py
mlx_vlm/models/rfdetr/transformer.py
mlx_vlm/models/rfdetr/vision.py
mlx_vlm/models/sam3/__init__.py
mlx_vlm/models/sam3/annotators.py
mlx_vlm/models/sam3/config.py
mlx_vlm/models/sam3/decoder.py
mlx_vlm/models/sam3/encoder.py
mlx_vlm/models/sam3/generate.py
mlx_vlm/models/sam3/geometry.py
mlx_vlm/models/sam3/position.py
mlx_vlm/models/sam3/processing_sam3.py
mlx_vlm/models/sam3/sam3.py
mlx_vlm/models/sam3/sam_components.py
mlx_vlm/models/sam3/segmentation.py
mlx_vlm/models/sam3/text_encoder.py
mlx_vlm/models/sam3/tracker.py
mlx_vlm/models/sam3/vision.py
mlx_vlm/models/sam3_1/__init__.py
mlx_vlm/models/sam3_1/config.py
mlx_vlm/models/sam3_1/convert_weights.py
mlx_vlm/models/sam3_1/generate.py
mlx_vlm/models/sam3_1/processing_sam3_1.py
mlx_vlm/models/sam3_1/sam3_1.py
mlx_vlm/models/sam3_1/sam_components.py
mlx_vlm/models/sam3_1/tracker.py
mlx_vlm/models/sam3_1/vision.py
mlx_vlm/models/smolvlm/__init__.py
mlx_vlm/models/smolvlm/config.py
mlx_vlm/models/smolvlm/processing_smolvlm.py
mlx_vlm/models/smolvlm/smolvlm.py
mlx_vlm/trainer/__init__.py
mlx_vlm/trainer/datasets.py
mlx_vlm/trainer/lora.py
mlx_vlm/trainer/orpo_trainer.py
mlx_vlm/trainer/sft_trainer.py
mlx_vlm/trainer/utils.py