Instructions to use connectivity/feather_berts_3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use connectivity/feather_berts_3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="connectivity/feather_berts_3")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("connectivity/feather_berts_3") model = AutoModelForSequenceClassification.from_pretrained("connectivity/feather_berts_3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download hans_eval_bert_3.json from connectivity/feather_berts_3: direct link, hf CLI and curl.
- Browser
- Download file 12.1 MB
-
https://huggingface.co/connectivity/feather_berts_3/resolve/main/hans_eval_bert_3.json
- Command line
-
hf download hf://connectivity/feather_berts_3/hans_eval_bert_3.json
-
curl -L -o hans_eval_bert_3.json https://huggingface.co/connectivity/feather_berts_3/resolve/main/hans_eval_bert_3.json
12.1 MB
- Xet hash:
- 3774437531f1a6ae31848179b0a9457e9d8c185a41bd04ba2554ec747c0aba31
- Size of remote file:
- 12.1 MB
- SHA256:
- 90d579dcdc01ea991cb30a12e79592f57d0314f2561e262f0a0dab318ba72f36
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.