Instructions to use dineshananthi/colgranite-4.1-4b-lora-72k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dineshananthi/colgranite-4.1-4b-lora-72k with PEFT:
Task type is invalid.
- ColPali
How to use dineshananthi/colgranite-4.1-4b-lora-72k with ColPali:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
ColGranite 4.1-4B β LoRA Adapter
Late-interaction (ColBERT-style) visual retrieval adapter on top of
ibm-granite/granite-vision-4.1-4b.
Contents
adapter_config.json,adapter_model.safetensorsβ LoRA adapter (text-decoder projections)col_linear_head.ptβ the trained 2560 to 128 projection head (REQUIRED for retrieval)- processor / tokenizer files
Usage
Rebuild the ColGranite wrapper, attach this adapter to the inner model with
PeftModel.from_pretrained(...), then load col_linear_head.pt into the projection head.
- Downloads last month
- 12
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support
Model tree for dineshananthi/colgranite-4.1-4b-lora-72k
Base model
ibm-granite/granite-vision-4.1-4b