Instructions to use connectivity/feather_berts_65 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use connectivity/feather_berts_65 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="connectivity/feather_berts_65")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("connectivity/feather_berts_65") model = AutoModelForSequenceClassification.from_pretrained("connectivity/feather_berts_65", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download hans_eval_bert_65.json from connectivity/feather_berts_65: direct link, hf CLI and curl.
- Browser
- Download file 12.1 MB
-
https://huggingface.co/connectivity/feather_berts_65/resolve/main/hans_eval_bert_65.json
- Command line
-
hf download hf://connectivity/feather_berts_65/hans_eval_bert_65.json
-
curl -L -o hans_eval_bert_65.json https://huggingface.co/connectivity/feather_berts_65/resolve/main/hans_eval_bert_65.json
12.1 MB
- Xet hash:
- 7cc13f85fb54cc01dadfa245a5fd37e7fc0c5786255361c8c282bb20cb45097e
- Size of remote file:
- 12.1 MB
- SHA256:
- 34d90e57c08302033a01608a0603170094f1e67fa8cc7a3d35ce701d15f5c6d0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.