Instructions to use comacrae/roberta-unaugv3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use comacrae/roberta-unaugv3 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="comacrae/roberta-unaugv3")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("comacrae/roberta-unaugv3") model = AutoModelForQuestionAnswering.from_pretrained("comacrae/roberta-unaugv3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from comacrae/roberta-unaugv3: direct link, hf CLI and curl.
- Browser
- Download file 496 MB
-
https://huggingface.co/comacrae/roberta-unaugv3/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://comacrae/roberta-unaugv3/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/comacrae/roberta-unaugv3/resolve/main/pytorch_model.bin
496 MB
- Xet hash:
- e5aa2d088eeee77068463fcadbb1879ca6755fc760caa05e1a2d2c7b7867faa3
- Size of remote file:
- 496 MB
- SHA256:
- 639a83025018e914ce55039134c68018b60430cdcb76554d6ac203d360ea77cf
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.