Sentiment Roberta Large English Alternatives

A large RoBERTa model fine-tuned for sentiment analysis of English text with three output classes. It can be used via the Transformers library to classify text as positive, negative, or neutral. The model is open-weight and suitable for research or production text classification pipelines.

twitter-roberta-base-sentiment-latest is a transformer-based model fine-tuned for sentiment analysis on Twitter data. It enables developers and researchers to classify tweets as positive, negative, or neutral, supporting social media monitoring and analytics.

ruRoBERTa-large is a large-scale RoBERTa model pretrained on Russian text. It supports fill-mask and other downstream NLP tasks for the Russian language. Developed by AI Forever (Sber), it is one of the strongest openly available models for Russian language understanding.

Indonesian Roberta Base Sentiment Classifier is a machine learning model hosted on Hugging Face for text classification. It addresses the need to determine sentiment polarity in Indonesian-language text. The model is a fine-tuned version of the RoBERTa base architecture and carries the identifier w11wo/indonesian-roberta-base-sentiment-classifier. It supports the text-classification task and is provided with a tokenizer configuration that defines special tokens including bos_token as <s, eos_token as </s, sep_token as </s, cls_token as <s, pad_token as <pad, and mask_token as <mask. The model became available on 2022-03-02 and remains accessible for inference through hosted providers. It has recorded over 1.4 million total downloads. The model is delivered as an open artifact on the Hugging Face platform. It can be retrieved and run using the standard Hugging Face ecosystem, including inference endpoints when available. A DOI is assigned for citation purposes. No pricing, licensing terms, or specific end-user roles are stated for the model itself.

mmlw-retrieval-roberta-large is a large RoBERTa model fine-tuned specifically for multilingual retrieval and semantic similarity tasks. It produces high-quality embeddings suitable for information retrieval, duplicate detection, and clustering across many languages. The model is publicly hosted on Hugging Face and supports standard sentence-transformers usage patterns.

Robertuito-hate-speech is a model from the pysentimiento toolkit based on the RoBERTuito architecture. It is fine-tuned specifically for detecting hate speech in Spanish-language text. The model can be used for content moderation, social media monitoring, and research into online toxicity in Spanish-speaking communities.

robertuito-emotion-analysis is a fine-tuned Spanish language model based on RoBERTuito for detecting emotions in text. It is hosted on Hugging Face and can be used via the pysentimiento library or standard Transformers pipeline. The model supports common emotion categories and is intended for research and application developers working with Spanish-language content.

This is a large XLM-RoBERTa model fine-tuned on the CoNLL-03 English dataset for named entity recognition (NER). It supports token classification across a wide range of languages. The model is distributed on Hugging Face and can be used with the transformers library for extracting persons, organizations, locations, and other entities from text.

This RoBERTa model was fine-tuned on the i2b2 de-identification dataset for token classification. Its primary use is to identify and mask personally identifiable information (PHI) in clinical text to help comply with privacy regulations. It is available on Hugging Face and can be used with the Transformers library for clinical NLP pipelines.

cross-encoder/stsb-roberta-large is an open-source model hosted on Hugging Face for the task of text ranking and semantic textual similarity. Built on the RoBERTa architecture and the sentence-transformers framework, it evaluates how similar two pieces of text are. It is commonly used in information retrieval, duplicate detection, and semantic search pipelines by developers integrating it via Python libraries.

This is a large RoBERTa model fine-tuned on the TweetNER7 dataset for token classification and named entity recognition. It is distributed via Hugging Face and intended for researchers and developers working with social media text analysis.

This model is a DistilRoBERTa base fine-tuned on financial news for sentiment analysis. It classifies text into positive, negative, or neutral categories and has been widely downloaded for use in trading, investment research, and market analysis applications. The model is available on Hugging Face and can be used directly with the Transformers pipeline for text-classification.

SCIFACT_xlm_roberta_large is an XLM-RoBERTa large model fine-tuned on the SciFact dataset for the task of scientific fact verification (text-classification). It helps determine whether scientific claims are supported by evidence from research papers. The model is available through the Hugging Face Transformers library.

This is a base model from the SCUT-DLVCLab combining LiLT (Language-Independent Layout Transformer) with RoBERTa for English document understanding tasks. It processes both textual content and spatial layout information from documents. It is designed for researchers and developers working on layout-aware document AI.

SentimentArEng is an open-source transformer model hosted on Hugging Face for performing sentiment analysis on Arabic and English text. It uses the transformers library and supports text-classification pipelines. The model is designed for developers integrating multilingual sentiment detection into applications.

KoSimCSE-roberta is a RoBERTa-based model trained with SimCSE for Korean sentence representation learning. It produces high-quality embeddings for semantic textual similarity, retrieval, and clustering tasks in Korean. The model is compatible with Hugging Face Transformers and text-embeddings-inference.

sbert-legal-xlm-roberta-base is an open-source sentence embedding model based on XLM-RoBERTa, fine-tuned on legal corpora for semantic textual similarity tasks. It produces high-quality vector representations optimized for legal documents and multilingual use cases. Developers can integrate it via the sentence-transformers or Hugging Face Transformers libraries for retrieval, clustering, or classification in legal AI applications.