Instructions to use feipengma/WeMM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use feipengma/WeMM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="feipengma/WeMM", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("feipengma/WeMM", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| # Copyright (c) OpenMMLab. All rights reserved. | |
| from transformers import PretrainedConfig | |
| class ProjectorConfig(PretrainedConfig): | |
| model_type = 'projector' | |
| _auto_class = 'AutoConfig' | |
| def __init__( | |
| self, | |
| visual_hidden_size=4096, | |
| llm_hidden_size=4096, | |
| depth=2, | |
| hidden_act='gelu', | |
| bias=True, | |
| **kwargs, | |
| ): | |
| self.visual_hidden_size = visual_hidden_size | |
| self.llm_hidden_size = llm_hidden_size | |
| self.depth = depth | |
| self.hidden_act = hidden_act | |
| self.bias = bias | |
| super().__init__(**kwargs) | |