FacebookAI/xlm-roberta-base, finetuned for refusal classification task
Model Details
Model Description
I needed a classifier model to clean my synthetic dataset from refusals. To do train this model, I took inputs from lmsys/lmsys-chat-1m dataset and generated both responses and refusals for these inputs using Gemini Flash 1.5 and LLaMA 3.3 70b models to increase refusal diversity. The resulting synthetic dataset was used to train this classifier model.
import transformers
pipe = transformers.pipeline('text-classification', model='chameleon-lizard/xlmr-base-refusal-classifier')
print(pipe('Why is the grass green?')) # [{'label': 'NO_REFUSAL', 'score': 0.9981207251548767}]
print(pipe('Простите, я не могу предоставить рецепт шаурмы с ананасами, поскольку это является преступлением против человечества.')) # [{'label': 'REFUSAL', 'score': 0.9995238780975342}]
Runs of s-nlp xlmr-base-refusal-classifier on huggingface.co
107
Total runs
0
24-hour runs
0
3-day runs
23
7-day runs
107
30-day runs
More Information About xlmr-base-refusal-classifier huggingface.co Model
More xlmr-base-refusal-classifier license Visit here:
xlmr-base-refusal-classifier huggingface.co is an AI model on huggingface.co that provides xlmr-base-refusal-classifier's model effect (), which can be used instantly with this s-nlp xlmr-base-refusal-classifier model. huggingface.co supports a free trial of the xlmr-base-refusal-classifier model, and also provides paid use of the xlmr-base-refusal-classifier. Support call xlmr-base-refusal-classifier model through api, including Node.js, Python, http.
xlmr-base-refusal-classifier huggingface.co is an online trial and call api platform, which integrates xlmr-base-refusal-classifier's modeling effects, including api services, and provides a free online trial of xlmr-base-refusal-classifier, you can try xlmr-base-refusal-classifier online for free by clicking the link below.
s-nlp xlmr-base-refusal-classifier online free url in huggingface.co:
xlmr-base-refusal-classifier is an open source model from GitHub that offers a free installation service, and any user can find xlmr-base-refusal-classifier on GitHub to install. At the same time, huggingface.co provides the effect of xlmr-base-refusal-classifier install, users can directly use xlmr-base-refusal-classifier installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
xlmr-base-refusal-classifier install url in huggingface.co: