Instructions to use connectivity/feather_berts_71 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use connectivity/feather_berts_71 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="connectivity/feather_berts_71")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("connectivity/feather_berts_71") model = AutoModelForSequenceClassification.from_pretrained("connectivity/feather_berts_71", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download hans_eval_bert_71.json from connectivity/feather_berts_71: direct link, hf CLI and curl.
- Browser
- Download file 12.1 MB
-
https://huggingface.co/connectivity/feather_berts_71/resolve/main/hans_eval_bert_71.json
- Command line
-
hf download hf://connectivity/feather_berts_71/hans_eval_bert_71.json
-
curl -L -o hans_eval_bert_71.json https://huggingface.co/connectivity/feather_berts_71/resolve/main/hans_eval_bert_71.json
12.1 MB
- Xet hash:
- 190492b3f5e973b3a3636cf45f345590e5848b8737e3003ffc6ffc0a192a3cfc
- Size of remote file:
- 12.1 MB
- SHA256:
- ebd6e36886eeee8708a450aed723ded29f0c3ac6ec879cf684ca674848f8f033
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.