Instructions to use eltorio/IDEFICS3_ROCO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use eltorio/IDEFICS3_ROCO with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceM4/Idefics3-8B-Llama3") model = PeftModel.from_pretrained(base_model, "eltorio/IDEFICS3_ROCO") - Notebooks
- Google Colab
- Kaggle
Download preload.py from eltorio/IDEFICS3_ROCO: direct link, hf CLI and curl.
- Browser
- Download file 294 Bytes
-
https://huggingface.co/eltorio/IDEFICS3_ROCO/resolve/6ff184ed91affaac7716e4e786ea9c19e4e4f2df/preload.py
- Command line
-
hf download hf://eltorio/IDEFICS3_ROCO@6ff184ed91affaac7716e4e786ea9c19e4e4f2df/preload.py
-
curl -L -o preload.py https://huggingface.co/eltorio/IDEFICS3_ROCO/resolve/6ff184ed91affaac7716e4e786ea9c19e4e4f2df/preload.py
294 Bytes
| # Description: Preload the dataset to cache_dir | |
| # Copyright (C) 2024 Ronan Le Meillat | |
| # License: Apache License 2.0 | |
| from datasets import load_dataset | |
| dataset_id = "eltorio/ROCO-radiology" | |
| cache_dir = "/workspace/data" | |
| train_dataset = load_dataset(dataset_id, split="train", cache_dir=cache_dir) |