Instructions to use cardiffnlp/roberta-base-topic-multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cardiffnlp/roberta-base-topic-multi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="cardiffnlp/roberta-base-topic-multi")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("cardiffnlp/roberta-base-topic-multi") model = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/roberta-base-topic-multi", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download metric.json from cardiffnlp/roberta-base-topic-multi: direct link, hf CLI and curl.
- Browser
- Download file 232 Bytes
-
https://huggingface.co/cardiffnlp/roberta-base-topic-multi/resolve/main/metric.json
- Command line
-
hf download hf://cardiffnlp/roberta-base-topic-multi/metric.json
-
curl -L -o metric.json https://huggingface.co/cardiffnlp/roberta-base-topic-multi/resolve/main/metric.json
232 Bytes
| {"eval_loss": 0.11193934082984924, "eval_f1": 0.7546616383825687, "eval_f1_macro": 0.5959450154471646, "eval_accuracy": 0.5318642048838594, "eval_runtime": 10.5507, "eval_samples_per_second": 159.137, "eval_steps_per_second": 9.952} |