Instructions to use connectivity/feather_berts_50 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use connectivity/feather_berts_50 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="connectivity/feather_berts_50")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("connectivity/feather_berts_50") model = AutoModelForSequenceClassification.from_pretrained("connectivity/feather_berts_50", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download hans_eval_bert_50.json from connectivity/feather_berts_50: direct link, hf CLI and curl.
- Browser
- Download file 12.1 MB
-
https://huggingface.co/connectivity/feather_berts_50/resolve/main/hans_eval_bert_50.json
- Command line
-
hf download hf://connectivity/feather_berts_50/hans_eval_bert_50.json
-
curl -L -o hans_eval_bert_50.json https://huggingface.co/connectivity/feather_berts_50/resolve/main/hans_eval_bert_50.json
12.1 MB
- Xet hash:
- 68349c6e6556cade08f9298b0a06ef6a907e67b086fb1eb3e58a4bde64f9f47b
- Size of remote file:
- 12.1 MB
- SHA256:
- c98c45d7e10b0485468bdfaa35451e6d4f144d053210f6d95b59c7950e8afae9
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.