Image-to-Text
Transformers
Safetensors
MLX
qwen2_5_vl
image-text-to-text
OCR
vision-language
VLM
Reasoning
document-to-markdown
qwen2.5
markdown
extraction
RAG
text-generation-inference
8-bit precision
Instructions to use numind/NuMarkdown-8B-Thinking-mlx-8bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use numind/NuMarkdown-8B-Thinking-mlx-8bits with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="numind/NuMarkdown-8B-Thinking-mlx-8bits")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("numind/NuMarkdown-8B-Thinking-mlx-8bits") model = AutoModelForMultimodalLM.from_pretrained("numind/NuMarkdown-8B-Thinking-mlx-8bits") - MLX
How to use numind/NuMarkdown-8B-Thinking-mlx-8bits with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir NuMarkdown-8B-Thinking-mlx-8bits numind/NuMarkdown-8B-Thinking-mlx-8bits
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "crop_size": null, | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "device": null, | |
| "disable_grouping": null, | |
| "do_center_crop": null, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_pad": null, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "Qwen2VLImageProcessorFast", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "input_data_format": null, | |
| "max_pixels": 3920000, | |
| "merge_size": 2, | |
| "min_pixels": 200704, | |
| "pad_size": null, | |
| "patch_size": 14, | |
| "processor_class": "Qwen2_5_VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_tensors": null, | |
| "size": { | |
| "longest_edge": 3920000, | |
| "shortest_edge": 200704 | |
| }, | |
| "temporal_patch_size": 2 | |
| } | |