Instructions to use kumapo/llm-jp-modernbert-base-jsquad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kumapo/llm-jp-modernbert-base-jsquad with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="kumapo/llm-jp-modernbert-base-jsquad")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("kumapo/llm-jp-modernbert-base-jsquad") model = AutoModelForQuestionAnswering.from_pretrained("kumapo/llm-jp-modernbert-base-jsquad", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from kumapo/llm-jp-modernbert-base-jsquad: direct link, hf CLI and curl.
- Browser
- Download file 5.71 kB
-
https://huggingface.co/kumapo/llm-jp-modernbert-base-jsquad/resolve/main/training_args.bin
- Command line
-
hf download hf://kumapo/llm-jp-modernbert-base-jsquad/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/kumapo/llm-jp-modernbert-base-jsquad/resolve/main/training_args.bin
5.71 kB
- Xet hash:
- ecb6849536551f7c080d0b8e965ccc82918ba0f6eba4f6cc441d3ac2935f6075
- Size of remote file:
- 5.71 kB
- SHA256:
- 0caf4a2bd00f5c4190d771ad1c57c1c2bc06bae8c1880cab947433020aca0ffe
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.