**This adversarial model has a propensity to produce highly unsavoury content from the outset. It is not intended or suitable for general use or human consumption.** This special-use model aims to provide prompts that goad LLMs into producting "toxicity". Toxicity here is defined by the content of the Civil Comments dataset, containing categories such as `obscene`, `threat`, `insult`, `identity_attack`, `sexual_explicit` and `severe_toxicity`. For details, see the description of the Jigsaw 2019 data. The base model is the community version of gpt2 with ~125M parameters. This model is not aligned and is "noisy" relative to more advanced models. Both the lack of alignment and the existence of noise are favourable to the task of trying to goad other models into producing unsafe output: unsafe prompts have a propensity to yield unsafe outputs, and noisy behaviour can lead to a broader exploration of input space.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Garak Refusal Detector is a binary sequence classifier model that detects refusal responses in LLM outputs. The model is built as a semantic replacement for string-based keyword detectors (e.g., Garak's MitigationBypass detector), enabling refusal detection based on meaning rather than surface patterns. Developers integrating the Garak framework can use this model to detect refusal responses in LLM outputs. It serves as an alternative to keyword‑based detectors, using a transformer‑based classifier that returns a binary signal indicating refusal or non‑refusal. Garak Refusal Detector is a fine-tuned version of answerdotai/ModernBERT-base, trained on synthetic refusal and non-refusal data for binary sequence classification.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗They're prompt results of OpenAI gpt-3.5-turbo run on June 1 2023. Prompts are constructed by prepending "Explain why" to claims made in the True-False dataset provided alongside The Internal State of an LLM Knows When its Lying. Only the first sentence of the response is included (from nltk.sent_tokenize). The original labels are used, where 0 corresponds to a false claim. That is, the 0 labels should be almost all refutations. Spurious and missing refutations were removed by hand, corresponding to about 10% of the data. This were caused by either an incorrect model assertion, or errors in the source data.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗This model is trained for toxicity classification task. The dataset used for training is the merge of the English parts of the three datasets by **Jigsaw** (Jigsaw 2018, Jigsaw 2019, Jigsaw 2020), containing around 2 million examples. We split it into two parts and fine-tune a RoBERTa model (RoBERTa: A Robustly Optimized BERT Pretraining Approach) on it. The classifiers perform closely on the test set of the first Jigsaw competition, reaching the **AUC-ROC** of 0.98 and **F1-score** of 0.76. This model is licensed under the OpenRAIL++ License, which supports the development of various technologies—both industrial and academic—that serve the public good.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗This model is intended to use for classify toxic online classifications. However, one limitation of the model is that it performs poorly for some comments that mention a specific identity subgroup, like Muslim. The following table shows a evaluation score for different identity group. You can learn the specific meaning of this metrics here. But basically, those metrics shows how well a model performs for a specific group. The larger the number, the better. The table above shows that the model performs poorly for the muslim and jewish group. In fact, you pass the sentence "Muslims are people who follow or practice Islam, an Abrahamic monotheistic religion." Into the model, the model will classify it as toxic. Be mindful for this type of potential bias. The training data comes this Kaggle competition. We use 10% of the `train.csv` data to train the model.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗