# English NLP

This is a static quantized version of the chandar-lab/NeoBERT model, aiming to reduce model storage space and computational resource requirements.

This model has undergone self-quantization processing, with output and embedding tensors quantized to f16 format, and the remaining tensors quantized to q5_k or q6_k format, resulting in a smaller size while maintaining performance comparable to pure f16.

Falcon-H1 is a decoder-only causal model with a hybrid Transformers + Mamba architecture developed by TII, focusing on English NLP tasks with excellent performance.

T0++ is a natural language processing model based on the T5 architecture, achieving zero-shot task generalization through multi-task prompt training, outperforming GPT-3 on various NLP tasks while being more compact.

OLMo 2 1B SFT is a supervised fine-tuned version of the OLMo-2-0425-1B model, trained on the Tulu 3 dataset, designed to achieve state-of-the-art performance across multiple tasks.

Falcon-E-1B-Base is an efficient 1.58-bit language model developed by TII, featuring a pure Transformer architecture and optimized for edge devices.

A model fine-tuned based on bert-base-uncased for textual entailment recognition tasks, with an accuracy of 66.43%

Bonsai is a small ternary-weighted language model with 500 million parameters, built on the Llama architecture and using the Mistral tokenizer, trained on fewer than 5 billion tokens.

A text classification model fine-tuned based on distilbert-base-uncased, achieving an F1 score of 0.6147

Tülu 3 is a leading family of instruction-following models, offering fully open-source data, code, and training methodologies as a comprehensive guide to modern technology. Version 3.1 features improvements in the reinforcement learning phase, delivering enhanced overall performance.

Stella 400M v5 is an English text embedding model that excels in multiple text classification and retrieval tasks.

A sentiment analysis model fine-tuned on distilbert-base-uncased, achieving 94% accuracy on the evaluation set

A sentiment analysis model based on DistilBERT, fine-tuned on an unknown dataset with an accuracy of 56.16%

A natural language inference model fine-tuned based on ModernBERT-large, specifically designed for zero-shot classification tasks

A lightweight text classification model based on the DistilBERT architecture, designed to classify English news into four major categories: World, Sports, Business, and Technology

Stella 400M is a medium-scale English text processing model focused on classification and information retrieval tasks.

A text generation model employing mixed quantization techniques, with output and embedding tensors in f16 format and other tensors quantized using q5_k or q6_k. It has a smaller size than the standard q8_0 quantization format while maintaining performance comparable to the pure f16 version.

This is a clinical note summarization model fine-tuned based on the T5-small model, primarily used for generating summaries of clinical notes.

This model is a natural language inference model based on the RoBERTa architecture, specifically fine-tuned for depression detection tasks.

A text classification model fine-tuned based on distilbert-base-uncased for topic abstract classification tasks

This is a fine-tuned large language model for mental health prediction using online text data.

An English emotional text generation model based on the GPT-2 architecture, supporting six basic emotion categories as generation conditions.

INSTRUCTOR is a text embedding model based on the T5 architecture, focusing on sentence similarity calculation and text classification tasks, and supports English language processing.

This model is a fine-tuned version of DistilBERT on the SQuAD question-answering dataset, designed for QA tasks.

This model is a question-answering model fine-tuned on the SQuAD v2 dataset based on DistilBERT, suitable for reading comprehension tasks.

Lightweight Q&A model based on DistilBERT, fine-tuned on the SQuAD dataset

This is a BERT-based pre-trained language model for the biomedical domain, suitable for processing biomedical text data.

A question answering system model based on the DeBERTa-v3-xsmall architecture, specifically fine-tuned for the SQuAD2.0 dataset

This model is a question-answering model fine-tuned on the SQuAD v2 dataset based on DistilBERT, suitable for reading comprehension tasks.

A question-answering model based on DistilBERT, fine-tuned on the SQuAD v2 dataset, suitable for QA tasks

This model is a fine-tuned version of distilbert-base-uncased on the becasv2 dataset, primarily used for text classification tasks.

A fine-tuned version of the distilbert-base-uncased model on the becasv2 dataset, primarily used for text-related tasks.

A question-answering model fine-tuned on the squad_v2 dataset based on the distilbert-base-uncased model

This model is a fine-tuned version of distilbert-base-uncased on the becasv2 dataset, primarily used for text generation tasks.

A text classification model fine-tuned on the becasv2 dataset based on distilbert-base-uncased

This model is a fine-tuned version of the DistilBERT base model on the SQuAD question answering dataset, specifically designed for question answering tasks.

A question-answering model fine-tuned on the SQuAD 2.0 dataset based on RoBERTa-base, designed to answer questions based on given text

This model is a fine-tuned version of DistilBERT on the SQuAD Q&A dataset, suitable for question-answering tasks.

This model is a fine-tuned version of bert-base-uncased on the squad_v2 dataset, suitable for question-answering tasks.

A Q&A model based on DistilBERT, fine-tuned on the SQuAD dataset for reading comprehension tasks