Instructions to use connectivity/feather_berts_35 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use connectivity/feather_berts_35 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="connectivity/feather_berts_35")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("connectivity/feather_berts_35") model = AutoModelForSequenceClassification.from_pretrained("connectivity/feather_berts_35", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download hans_eval_bert_35.json from connectivity/feather_berts_35: direct link, hf CLI and curl.
- Browser
- Download file 12.1 MB
-
https://huggingface.co/connectivity/feather_berts_35/resolve/main/hans_eval_bert_35.json
- Command line
-
hf download hf://connectivity/feather_berts_35/hans_eval_bert_35.json
-
curl -L -o hans_eval_bert_35.json https://huggingface.co/connectivity/feather_berts_35/resolve/main/hans_eval_bert_35.json
12.1 MB
- Xet hash:
- 6f9fcb3559cce4cd4ef938fde3244d97ee220b6048aa3e2c4ea68124e5e24a5a
- Size of remote file:
- 12.1 MB
- SHA256:
- 6cd02c62f92b27d8ba12a41a96c4c11f775d61651e99cfdf13c5a4425b82289d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.