Instructions to use immanuelpeter/MiniMax-M3-Vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use immanuelpeter/MiniMax-M3-Vision with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="immanuelpeter/MiniMax-M3-Vision")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("immanuelpeter/MiniMax-M3-Vision") model = AutoModel.from_pretrained("immanuelpeter/MiniMax-M3-Vision", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "processor_class": "AutoImageProcessor", | |
| "image_processor_type": "MiniMaxM3VLImageProcessor", | |
| "process_image_mode": "dynamic_res", | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "size": [ | |
| 672, | |
| 672 | |
| ], | |
| "patch_size": 14, | |
| "img_token_compression_config": { | |
| "image_token_compression_threshold": 1.1, | |
| "image_token_compression_method": "patch_merge", | |
| "max_image_resolution": 1008, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "add_start_end_special_tokens": true | |
| } | |