Instructions to use mmiteva/qa_model-customs_optimized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mmiteva/qa_model-customs_optimized 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="mmiteva/qa_model-customs_optimized")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("mmiteva/qa_model-customs_optimized") model = AutoModelForQuestionAnswering.from_pretrained("mmiteva/qa_model-customs_optimized", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tf_model.h5 from mmiteva/qa_model-customs_optimized: direct link, hf CLI and curl.
- Browser
- Download file 266 MB
-
https://huggingface.co/mmiteva/qa_model-customs_optimized/resolve/main/tf_model.h5
- Command line
-
hf download hf://mmiteva/qa_model-customs_optimized/tf_model.h5
-
curl -L -o tf_model.h5 https://huggingface.co/mmiteva/qa_model-customs_optimized/resolve/main/tf_model.h5
266 MB
- Xet hash:
- b164a2a653098581c218e1c621405de98b6bac00b3b6c27055479c2ee10634a3
- Size of remote file:
- 266 MB
- SHA256:
- 68ce45ffae7bb57c7c03f197aef0a552a3d0c97ae12b1cdd8ac2ba1f7907519b
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.