This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
This is a sentence-transformers model: It maps sentences & paragraphs to a 128 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
Welcome to the Suicidality Detection AI Model! This project aims to provide a machine learning solution for detecting sequences of words indicative of suicidality in text. By utilizing the ELECTRA architecture and fine-tuning on a diverse dataset, we have created a powerful classification model that can distinguish between suicidal and non-suicidal text expressions. - `LABEL_0`: Indicates that the text is non-suicidal. - `LABEL_1`: Indicates that the text is indicative of suicidality. The model was fine-tuned using the ELECTRA architecture on a carefully curated dataset. Our training process involved cleaning and preprocessing various text sources to create a comprehensive training set. The training results indicate promising performance, with metrics including:
**NOTE**: This model exists only for test cases in the SetFit repository, it was not trained to be strong. This is a SetFit model that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a Sentence Transformer with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer.
--- language: "en" tags: - neural-search-query-classification - neural-search widget: - text: "keyword query." --- | Train Loss | Validation Acc.| Test Acc.| | ------------- |:-------------: | -----: | | 0.000806 | 0.99 | 0.997 | Trained to add feature for classifying queries between Keyword Query or Question + Statement Query using classification in Haystack Problem Statement: One common challenge that we saw in deployments: We need to distinguish between real questions and keyword queries that come in. We only want to route questions to the Reader branch in order to maximize the accuracy of results and minimize computation efforts/costs.
This model is used to detect AI-generated texts from the RAID dataset. The model outputs a score corresponding to the likelihood that the text is human.
This model is a fine-tuned version of ModernBERT-large for binary classification of human-written vs. AI-generated text. It outputs a single probability, P(AI), indicating the likelihood that a given input was generated by a language model. Vanguard AI-text detector was part of the 2nd-place system at PAN-CLEF 2026's Voight-Kampff Generative AI Detection leaderboard. This model was trained on approximately 1.1 million texts from three datasets: DACTYL 2.0, LLMTrace, and MAGA-Bench. The model was evaluated against two leading open-source AI text detectors, Fakespot and Desklib, across ten benchmark datasets. Three of these (dactyl-v2.0, llm-trace-eng, maga) are in-distribution with respect to this model's training data; the remaining seven (beemo, coconuts, detectrl, dolly-cosmopedia, originalityai, realdet, uchicago) are out-of-distribution and were not seen during training.
**Fast, compact prompt-injection and jailbreak detection for lightweight deployment.** This 68.4M-parameter model is designed for low-latency local, edge, and agent-side use. It detects direct and indirect prompt injection and jailbreak attempts while also returning optional channel, objective, and technique classifications. The model provides a security signal for policy and approval systems. Runtime permissions must still be enforced at the action boundary. Apply sigmoid to presence, objective, and technique logits. Apply softmax to the three channel logits. Presence then uses the runtime-specific calibration in `calibration.json`; objective and technique calibration is already embedded in the weights.
It maps sentences to a 768 dimensional dense vector space and can be used for tasks like sentence embeddings, text matching or semantic search. For an automated evaluation of this model, see the *Evaluation Benchmark*: text2vec 说明： - 结果评测指标：spearman系数 - `shibing624/text2vec-base-chinese`模型，是用CoSENT方法训练，基于`hfl/chinese-macbert-base`在中文STS-B数据训练得到，并在中文STS-B测试集评估达到较好效果，运行examples/training_sup_text_matching_model.py代码可训练模型，模型文件已经上传HF model hub，中文通用语义匹配任务推荐使用 - `shibing624/text2vec-base-chinese-sentence`模型，是用CoSENT方法训练，基于`nghuyong/ernie-3.0-base-zh`用人工挑选后的中文STS数据集shibing624/nli-zh-all/text2vec-base-chinese-sentence-dataset训练得到，并在中文各NLI测试集评估达到较好效果，运行examples/training_sup_text_matching_model_jsonl_data.py代码可训练模型，模型文件已经上传HF model hub，中文s2s(句子vs句子)语义匹配任务推荐使用 - `shibing624/text2vec-base-chinese-paraphrase`模型，是用CoSENT方法训练，基于`nghuyong/ernie-3.0-base-zh`用人工挑选后的中文STS数据集shibing624/nli-zh-all/text2vec-base-chinese-paraphrase-dataset，数据集相对于shibing624/nli-zh-all/text2vec-base-chinese-sentence-dataset加入了s2p(sentence to paraphrase)数据，强化了其长文本的表征能力，并在中文各NLI测试集评估达到SOTA，运行examples/training_sup_text_matching_model_jsonl_data.py代码可训练模型，模型文件已经上传HF model hub，中文s2p(句子vs段落)语义匹配任务推荐使用 - `sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2`模型是用SBERT训练，是`paraphrase-MiniLM-L12-v2`模型的多语言版本，支持中文、英文等 - `w2v-light-tencent-chinese`是腾讯词向量的Word2Vec模型，CPU加载使用，适用于中文字面匹配任务和缺少数据的冷启动情况
