# English text processing

A quantized version of LiberalMind_v1.5, offering files of various quantization types and sizes for efficient use under different resource conditions.

Gemma 3 27B Instruct is a large language model developed by Google, fine-tuned on the neo4j/text2cypher-2025v1 dataset, specializing in converting natural language to Cypher query language.

A multi-category emotion classification model fine-tuned on ModernBERT-base, capable of recognizing 7 emotion labels

A dialogue summarization model fine-tuned based on the T5 Small architecture, specifically optimized for the Samsung/samsum dataset, capable of generating concise and accurate dialogue summaries.

A text summarization model based on the BART architecture, suitable for the abstract generation task of English scientific papers.

A zero-shot text classification model fine-tuned on DeBERTa-v3-base, suitable for scenarios with scarce labeled data or rapid prototyping.

stella_en_400M_v5_cpu is a model that performs excellently in multiple natural language processing tasks, especially in tasks such as classification, retrieval, clustering, and semantic text similarity.

Fast Emotion-X is an emotion detection model fine-tuned on Microsoft's DeBERTa V3 Small model, which can accurately classify text into six emotion categories.

A T5-based model specialized in extracting atomic claims from summary texts, serving as a key component in summary factuality assessment pipelines.

A RoBERTa-large model designed for efficient zero-shot classification, trained on commercially friendly data, capable of performing text classification tasks without training data.

A 15-million-parameter Llama 2 architecture model trained on the TinyStories dataset

One of the small BERT models released by Google Research, English-only, case-insensitive, trained with WordPiece masking.

E5-small is a compact sentence transformer model focused on sentence similarity and text embedding tasks, performing well on multiple classification and retrieval tasks.

BERT (Bidirectional Encoder Representations from Transformers) is a pre-trained language model based on the Transformer architecture, developed by Google.

Named entity recognition model based on distilbert-base-uncased architecture, fine-tuned on the conll2012_ontonotesv5-english-v4 dataset

This is a tiny version of the BERT model, case-insensitive, suitable for natural language processing tasks in resource-constrained environments.

A BERT-based fine-tuned named entity recognition model achieving an F1 score of 95.91% on the evaluation set

A fine-tuned version based on the BERT base model, specific use case and training data details are currently unknown

A lightweight sentence embedding model based on the MiniLM architecture that can map text to a 384-dimensional vector space, suitable for semantic search and clustering tasks.

A general self-supervised learning framework pre-trained on English language using the data2vec objective, handling different modality tasks through a unified approach

Flair's built-in fast model for 18-class English named entity recognition, trained on the Ontonotes dataset

PERT is a BERT-based pre-trained language model designed for English text processing tasks.

Flair's built-in standard English POS tagging model, trained on the Ontonotes dataset with an F1 score of 98.19.

A question generation model based on the BART-base architecture, fine-tuned on the SQuAD dataset, capable of generating questions without answer information.

Flair's built-in standard English phrase chunking model for identifying grammatical structures such as noun phrases and verb phrases in sentences.

This model is a fine-tuned version of distilbert-base-uncased on an unspecified dataset, primarily used for text-related tasks.

This is a modified version of EleutherAI's GPT-Neo (2.7B parameter version) that supports text generation and model fine-tuning on Colab or equivalent desktop GPUs.

DistilRoBERTa is a lightweight distilled version of the RoBERTa model, retaining most of its performance while being smaller and faster.

A text classification model fine-tuned on the Amazon product review sentiment analysis dataset based on the BERT base model, achieving 94.65% accuracy

This is a binary classification model trained on the AutoNLP platform for grammar correctness judgment.

A Named Entity Recognition model based on DistilBERT, fine-tuned on the CoNLL-2003 English dataset, suitable for case-sensitive text processing.

DeCLUTR-base is a universal sentence encoder model trained through deep contrastive learning for generating high-quality text representations.

This is a binary classification model trained via AutoNLP for IMDB review sentiment analysis

A sentiment analysis model fine-tuned based on bert-base-uncased for tweet sentiment classification

Flair's built-in English standard universal POS tagging model, trained on Ontonotes dataset with an F1 score of 98.6

A spelling error detection model based on the DistilBERT architecture, used to identify spelling errors in text

This is an encoder-decoder model based on the BERT-small architecture, specifically fine-tuned for summarization tasks on the CNN/Dailymail dataset.

A cross-encoder model trained on the Quora duplicate questions dataset, used to predict the probability of whether two questions are duplicates

Text summarization model fine-tuned on the cnn_dailymail dataset, trained using the DistilBERT architecture