Instructions to use connectivity/feather_berts_40 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use connectivity/feather_berts_40 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="connectivity/feather_berts_40")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("connectivity/feather_berts_40") model = AutoModelForSequenceClassification.from_pretrained("connectivity/feather_berts_40", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download hans_eval_bert_40.json from connectivity/feather_berts_40: direct link, hf CLI and curl.
- Browser
- Download file 12.1 MB
-
https://huggingface.co/connectivity/feather_berts_40/resolve/main/hans_eval_bert_40.json
- Command line
-
hf download hf://connectivity/feather_berts_40/hans_eval_bert_40.json
-
curl -L -o hans_eval_bert_40.json https://huggingface.co/connectivity/feather_berts_40/resolve/main/hans_eval_bert_40.json
12.1 MB
- Xet hash:
- ba9d8ff2dd18932ea7c379c02e962ca988629a71239948ab4ab7a6c0097d612c
- Size of remote file:
- 12.1 MB
- SHA256:
- a4d13ea6fd1de179c7c7d9ad5dbfc0d18cc67a2a5262762facbb5d00484f9751
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.