Instructions to use mattymchen/deebert-base-sst2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mattymchen/deebert-base-sst2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="mattymchen/deebert-base-sst2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("mattymchen/deebert-base-sst2") model = AutoModelForSequenceClassification.from_pretrained("mattymchen/deebert-base-sst2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from mattymchen/deebert-base-sst2: direct link, hf CLI and curl.
- Browser
- Download file 466 MB
-
https://huggingface.co/mattymchen/deebert-base-sst2/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://mattymchen/deebert-base-sst2/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/mattymchen/deebert-base-sst2/resolve/main/pytorch_model.bin
466 MB
- Xet hash:
- c5c2f658de7418ca2217a367019879c546185bb3da3426e3ab298cbb9ddeed5e
- Size of remote file:
- 466 MB
- SHA256:
- 9273ee1f2b67e0d80e8b26671ff8adeffcfb0a46eb7d911e3413d723e3636118
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.