Instructions to use wi-lab/lwm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wi-lab/lwm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="wi-lab/lwm")# Load model directly from transformers import LWM model = LWM.from_pretrained("wi-lab/lwm", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Training Code
#3
by linker81 - opened
I would like to train the LWM from scratch and I would like to know if you can share the complete training code.
You can find the pre-training script here. While this script is fully functional, you are welcome to modify the methods used during pre-training to enhance the performance and capabilities of the LWM model. We would love to hear about your improvements and results!
To replicate the exact pre-training process we followed, please refer to the instructions provided here. If you would like to use our pre-training dataset, you can find more details in this discussion.
Feel free to reach out if you have any questions or need further assistance!