Instructions to use connectivity/feather_berts_2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use connectivity/feather_berts_2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="connectivity/feather_berts_2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("connectivity/feather_berts_2") model = AutoModelForSequenceClassification.from_pretrained("connectivity/feather_berts_2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download hans_eval_bert_2.json from connectivity/feather_berts_2: direct link, hf CLI and curl.
- Browser
- Download file 12.1 MB
-
https://huggingface.co/connectivity/feather_berts_2/resolve/main/hans_eval_bert_2.json
- Command line
-
hf download hf://connectivity/feather_berts_2/hans_eval_bert_2.json
-
curl -L -o hans_eval_bert_2.json https://huggingface.co/connectivity/feather_berts_2/resolve/main/hans_eval_bert_2.json
12.1 MB
- Xet hash:
- 8150838192a7468d29e5dca528f0148738194e1629b3e57b5901ef4fa6bc7ada
- Size of remote file:
- 12.1 MB
- SHA256:
- 5aaab43231e1e561fb0184b8180d77d7800f8491b81d260290b1bf10f8699a0d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.