mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-07-23 17:01:04 +02:00
891c0bd256
* faster slice * add facts + ctx_qa * new configs * new scripts * intx_sft.py to train.py * add kaggle for downloading facts * max_new_tokens cli for eval * generate negative_nq * scripts + configs * default vals * max_val_samples_per_ds=500 * more efficient layer-to-layer ctx encoder * use_per_ctx_average_loss * faster processing * small exp distill * scripts * more robust watcher * per-module l1_norm avg * per-ctx average loss * clear_gpu
20 lines
666 B
Python
20 lines
666 B
Python
# Install dependencies as needed:
|
|
# pip install kagglehub[hf-datasets]
|
|
import kagglehub
|
|
from kagglehub import KaggleDatasetAdapter
|
|
|
|
# Set the path to the file you'd like to load
|
|
file_path = "data/raw_datasets/FACTS/ds.parquet"
|
|
|
|
# Load the latest version
|
|
hf_dataset = kagglehub.load_dataset(
|
|
KaggleDatasetAdapter.HUGGING_FACE,
|
|
"deepmind/FACTS-grounding-examples",
|
|
file_path,
|
|
# Provide any additional arguments like
|
|
# sql_query, hf_kwargs, or pandas_kwargs. See
|
|
# the documenation for more information:
|
|
# https://github.com/Kaggle/kagglehub/blob/main/README.md#kaggledatasetadapterhugging_face
|
|
)
|
|
|
|
print("Hugging Face Dataset:", hf_dataset)
|