Instructions to use jplu/tf-flaubert-large-cased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jplu/tf-flaubert-large-cased with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="jplu/tf-flaubert-large-cased")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("jplu/tf-flaubert-large-cased") model = AutoModelForMaskedLM.from_pretrained("jplu/tf-flaubert-large-cased", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tf_model.h5 from jplu/tf-flaubert-large-cased: direct link, hf CLI and curl.
- Browser
- Download file 1.78 GB
-
https://huggingface.co/jplu/tf-flaubert-large-cased/resolve/main/tf_model.h5
- Command line
-
hf download hf://jplu/tf-flaubert-large-cased/tf_model.h5
-
curl -L -o tf_model.h5 https://huggingface.co/jplu/tf-flaubert-large-cased/resolve/main/tf_model.h5
1.78 GB
- Xet hash:
- 2135c0f277be5b855a4b01d35db0517359c33117602ff0903e1fc462d7d63981
- Size of remote file:
- 1.78 GB
- SHA256:
- 564f315bc83356deef263376f2dcc20863f2b48e8cb3c8c528dbd7179a20e03e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.