AI NEWS・モデル情報能力を知り、根拠ある選択を。 ↗基本情報を先に収録・詳細を随時追加
THE AI MODEL DIRECTORY ここからモデルを探す

あなたに合う AIモデルを。

言語から画像、オープンウェイトからAPIまで。能力と実際の費用を比較。
次のアイデアに合うAIを見つけましょう。

人気の検索
84,991 件のモデル13202 社の提供元・公開者45 件の機能分類465件の比較可能な料金・30件の公開評価
Tテキスト生成▧画像生成▷動画生成⌘コード生成◖音声合成♫音楽生成⬡3Dモデリング▤文書分析
DISCOVER & COMPARE

AIモデルを探す 2428

注目のモデルを見つける

BLEURT-20

lucadiliello

Take a look at this repository for the definition of `BleurtConfig`, `BleurtForSequenceClassification` and `BleurtTokenizer` in PyTorch.

翻訳待ち・原文を表示

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗

BLEURT-20-D12

lucadiliello

Take a look at this repository for the definition of `BleurtConfig`, `BleurtForSequenceClassification` and `BleurtTokenizer` in PyTorch.

翻訳待ち・原文を表示

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗

FinBERT-PT-BR

lucas-leme

FinBERT-PT-BR is a pre-trained NLP model to analyze sentiment of Brazilian Portuguese financial texts. The model was trained in two main stages: language modeling and sentiment modeling. In the first stage, a language model was trained with more than 1.4 million texts of financial news in Portuguese. From this first training, it was possible to build a sentiment classifier with few labeled texts (500) that presented a satisfactory convergence. At the end of the work, a comparative analysis with other models and the possible applications of the developed model are presented. In the comparative analysis, it was possible to observe that the developed model presented better results than the current models in the state of the art. Among the applications, it was demonstrated that the model can be used to build sentiment indices, investment strategies and macroeconomic data analysis, such as inflation.

翻訳待ち・原文を表示

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗

pos_thai

lunarlist

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。

基本情報を収録・詳細は順次追加

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗

This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset (training notebook is here). It achieves the following results on the evaluation set: - Loss: 0.1903 - Accuracy: 0.928 The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 - Transformers 4.15.0 - Pytorch 1.10.0+cu111 - Datasets 1.17.0 - Tokenizers 0.10.3

翻訳待ち・原文を表示

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗

This model is distilled from the zero-shot classification pipeline on the Multilingual Sentiment dataset using this script. In reality the multilingual-sentiment dataset is annotated of course, but we'll pretend and ignore the annotations for the sake of example. Teacher model: MoritzLaurer/mDeBERTa-v3-base-mnli-xnli Teacher hypothesis template: "The sentiment of this text is {}." Student model: distilbert-base-multilingual-cased

翻訳待ち・原文を表示

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗

- **Paper:** https://arxiv.org/pdf/2410.00847 - **Model:** URM-LLaMa-3.1-8B - Fine-tuned from Skywork-Reward-Llama-3.1-8B

翻訳待ち・原文を表示

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗

The model is based on DeBERTa-v3-Large that predicts a binary label - 1 for supported and 0 for unsupported. The model is doing predictions on the *sentence-level*. It takes as input a document and a sentence and determine whether the sentence is supported by the document: **MiniCheck-Model(document, claim) -> {0, 1}** MiniCheck-DeBERTa-v3-Large is fine tuned from `microsoft/deberta-v3-large` (He et al., 2023) on the combination of 35K data: - 21K ANLI data (Nie et al., 2020) - 14K synthetic data generated from scratch in a structed way (more details in the paper). The performance of these models is evaluated on our new collected benchmark (unseen by our models during training), LLM-AggreFact, from 11 recent human annotated datasets on fact-checking and grounding LLM generations. MiniCheck-DeBERTa-v3-Large outperform all exisiting specialized fact-checkers with a similar scale. See full results in our work.

翻訳待ち・原文を表示

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗

📃 **MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents**,(EMNLP 2024, GitHub Repo) The model is based on Flan-T5-Large that predicts a binary label - 1 for supported and 0 for unsupported. The model is doing predictions on the *sentence-level*. It takes as input a document and a sentence and determine whether the sentence is supported by the document: **MiniCheck-Model(document, claim) -> {0, 1}** The performance of these models is evaluated on our new collected benchmark (unseen by our models during training), LLM-AggreFact, from 11 recent human annotated datasets on fact-checking and grounding LLM generations. MiniCheck-Flan-T5-Large outperform all exisiting specialized fact-checkers with a similar scale by a large margin (4-10% absolute increase) and is on par with GPT-4, but 400x cheaper. See full results in our work.

翻訳待ち・原文を表示

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗

The model is based on RoBERTA-Large that predicts a binary label - 1 for supported and 0 for unsupported. The model is doing predictions on the *sentence-level*. It takes as input a document and a sentence and determine whether the sentence is supported by the document: **MiniCheck-Model(document, claim) -> {0, 1}** MiniCheck-RoBERTa-Large is fine tuned from the trained RoBERTA-Large model from AlignScore (Zha et al., 2023) on 14K synthetic data generated from scratch in a structed way (more details in the paper). We also have other three MiniCheck model variants: - bespokelabs/Bespoke-Minicheck-7B (Model Size: 7B) - lytang/MiniCheck-Flan-T5-Large (Model Size: 0.8B) - lytang/MiniCheck-DeBERTa-v3-Large (Model Size: 0.4B)

翻訳待ち・原文を表示

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗

{ "@context": "https://schema.org", "@type": "SoftwareApplication", "name": "Gibberish Detector - High-Accuracy Text Classification Model", "url": "https://huggingface.co/madhurjindal/autonlp-Gibberish-Detector-492513457", "applicationCategory": "NaturalLanguageProcessing", "description": "State-of-the-art gibberish detection model using DistilBERT. Detect nonsensical text, spam, and incoherent input with 97.36% accuracy. Perfect for chatbots, content moderation, and text validation.", "keywords": "gibberish detector, gibberish detection, text classification, spam filter, content moderation, text validation, NLP model, DistilBERT, AutoNLP, text quality, input validation, chatbot filter", "creator": { "@type": "Person", "name": "Madhur Jindal" }, "datePublished": "2021-05-01", "softwareVersion": "1.0", "operatingSystem": "Cross-platform", "offers": { "@type": "Offer", "price": "0", "priceCurrency": "USD" } } **State-of-the-art gibberish detection model** that accurately identifies nonsensical text, spam, and incoherent input in English. Built with DistilBERT and AutoNLP, this model achieves **97.36% accuracy** in multi-class text classification, making it the ideal solution for content moderation, chatbot input validation, and text quality assurance. - **🎯 97.36% Accuracy**: Industry-leading performance in gibberish detection - **⚡ Fast Inference**: Optimized DistilBERT architecture for real-time applications - **🏷️ Multi-Class Detection**: Distinguishes between Noise, Word Salad, Mild Gibberish, and Clean text - **🔧 Easy Integration**: Simple API with transformers pipeline - **🌐 Production Ready**: Tested on diverse real-world datasets - **💚 Eco-Friendly**: Low carbon footprint (5.53g CO2 emissions)

翻訳待ち・原文を表示

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗

Jailbreak-Detector

madhurjindal

Welcome to the **Jailbreak-Detector** model, an advanced AI solution engineered for detecting jailbreak attempts in user interactions. This state-of-the-art model is pivotal for maintaining the security, integrity, and reliability of AI systems across various applications, including automated customer service, content moderation, and other interactive AI platforms. By leveraging this model, organizations can enhance their AI system's defenses against malicious activities, ensuring safe and secure user interactions. In the rapidly evolving field of artificial intelligence (AI), ensuring the security and integrity of deployed models is of paramount importance. One critical challenge is the potential for "jailbreaking"—a process where users exploit vulnerabilities to manipulate AI systems into performing unintended or harmful actions. To mitigate this risk, we present the **Jailbreak-Detector** model, meticulously trained to identify and classify jailbreak attempts.

翻訳待ち・原文を表示

入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗
出典・文書 ↗
COST EXPLORER

モデル選びに、費用の視点も。

コスト分析

月間トークン数を調整してAPI費用を比較。

1 M = 100万トークン・米ドル
同一チャネルの基本テキスト料金を比較

収集済みの比較可能な100万トークン当たり米ドル料金です。キャッシュ割引、段階料金、追加推論出力、税金は含みません。最新料金は出典で確認してください。

MODEL HANDBOOK

モデルを理解して選ぶ

選び方とよくある質問
API料金はどう比較しますか?+

入力・出力・キャッシュ料金を分け、同じ用途と使用量で総費用を比較します。画像・音声・動画は枚数、時間、解像度で課金される場合があります。

オープンウェイトは無料で商用利用できますか?+

必ずしもそうではありません。バージョンごとのライセンス、商用制限、ポリシーを確認してください。自前運用には計算資源と保守費用も必要です。

ランキング1位が最適ですか?+

順位はテスト、バージョン、評価方法によります。実際の業務データで精度、遅延、安定性、費用を比較してください。

AI NEWS・情報から選択へ

ニュースで知り、ツールで効率化、モデルで可能性を。

AIニュースを読む ↗AIツールを探す ↗