Instructions to use 1024m/SMM4H-Task5-BartL-2A with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 1024m/SMM4H-Task5-BartL-2A with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="1024m/SMM4H-Task5-BartL-2A")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("1024m/SMM4H-Task5-BartL-2A") model = AutoModelForSequenceClassification.from_pretrained("1024m/SMM4H-Task5-BartL-2A", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from 1024m/SMM4H-Task5-BartL-2A: direct link, hf CLI and curl.
- Browser
- Download file 3.26 GB
-
https://huggingface.co/1024m/SMM4H-Task5-BartL-2A/resolve/main/optimizer.pt
- Command line
-
hf download hf://1024m/SMM4H-Task5-BartL-2A/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/1024m/SMM4H-Task5-BartL-2A/resolve/main/optimizer.pt
3.26 GB
- Xet hash:
- 4379821052f829e7065137531f40f1fc713c370a0b6a81b0e0159255aa132728
- Size of remote file:
- 3.26 GB
- SHA256:
- aaaff72d8dbf79f67666d91e8305154d42c29a088c83cd120828aa5447dc7f5b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.