Instructions to use daydrill/table_qa_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use daydrill/table_qa_1 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="daydrill/table_qa_1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("daydrill/table_qa_1") model = AutoModelForQuestionAnswering.from_pretrained("daydrill/table_qa_1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/optimizer.pt from daydrill/table_qa_1: direct link, hf CLI and curl.
- Browser
- Download file 943 MB
-
https://huggingface.co/daydrill/table_qa_1/resolve/main/last-checkpoint/optimizer.pt
- Command line
-
hf download hf://daydrill/table_qa_1/last-checkpoint/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/daydrill/table_qa_1/resolve/main/last-checkpoint/optimizer.pt
943 MB
- Xet hash:
- 43696f73b21588ab17a3239f3982f0cefccd2bfeb7b4ab47a0229eea813d1491
- Size of remote file:
- 943 MB
- SHA256:
- 3f3b5dbaaab2ff80c51aab2baf4b9611bddb09fa3492187cd0c4986ca1141032
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.