Instructions to use CMB-AI-LAB/lagkv_cache with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CMB-AI-LAB/lagkv_cache with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CMB-AI-LAB/lagkv_cache", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add pipeline tag, license, and remove redundant section
#1
by nielsr HF Staff - opened
This PR improves the model card by:
- Adding
pipeline_tag: text-generationto ensure better discoverability for users looking for text generation models or related optimizations. - Adding
license: mitto the metadata. - Removing the extraneous
# File informationsection from the content, as it's not part of a standard model card.