Instructions to use connectivity/feather_berts_28 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use connectivity/feather_berts_28 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="connectivity/feather_berts_28")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("connectivity/feather_berts_28") model = AutoModelForSequenceClassification.from_pretrained("connectivity/feather_berts_28", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download hans_eval_bert_28.json from connectivity/feather_berts_28: direct link, hf CLI and curl.
- Browser
- Download file 12.1 MB
-
https://huggingface.co/connectivity/feather_berts_28/resolve/main/hans_eval_bert_28.json
- Command line
-
hf download hf://connectivity/feather_berts_28/hans_eval_bert_28.json
-
curl -L -o hans_eval_bert_28.json https://huggingface.co/connectivity/feather_berts_28/resolve/main/hans_eval_bert_28.json
12.1 MB
- Xet hash:
- 6aeb353304c2fa130d410eee2df995f1c8332ca16c2f7b8ac8d0578b14061452
- Size of remote file:
- 12.1 MB
- SHA256:
- 26b71b63f82bfcdca0ba984f6b0add761b3d7fb10dbc345bc6fb2eafb3a7b812
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.