# Transformer architecture

FastVLM-1.5B-Stage3-MNN is a text generation model based on the Transformer architecture. It is an 8-bit quantized version of FastVLM-1.5B-Stage3, suitable for text generation scenarios such as chatting.

Sundial is a series of generative time series foundation models capable of zero-shot inference for both deterministic and probabilistic forecasting.

This is the ONNX version of the AST (Audio Spectrogram Transformer) model, designed specifically for audio classification tasks and fine-tuned on the AudioSet dataset.

Falcon-E-3B-Instruct is an efficient language model based on a 1.58-bit architecture, optimized for edge devices, with excellent inference capabilities and low memory usage.

This is an Arabic model trained on the MediaSpeech dataset. Specific uses and functionalities require further information for confirmation.

The Camel Model is a text generation model based on the transformer architecture, supporting Azerbaijani and trained using reinforcement learning.

Transformer-based bidirectional machine translation model supporting mutual translation among Slavic languages

A vision Transformer (ViT)-based image feature model, pre-trained on the LVD-142M dataset using the self-supervised DINOv2 method.

This model is a face liveness detection model based on the Transformer library and has achieved excellent performance on the evaluation set.

MOMENT is a series of general-purpose foundational models for time series analysis, supporting various tasks such as forecasting, classification, anomaly detection, etc., with out-of-the-box and fine-tuning capabilities.

A Turkish text-to-speech model fine-tuned based on Microsoft SpeechT5, capable of generating high-quality Turkish speech.

A Transformer model specifically developed for bidirectional translation between Swahili and English, fine-tuned on 210,000 sentence pairs

A Transformer encoder model based on BERT architecture, specifically designed for generating RNA sequence embeddings

This is a fine-tuned version of Dicta - IL's dictalm2.0 - instruct model, specifically designed for generating Hebrew question-answer pairs.

Real3D is a 2D-to-3D mapping Transformer model based on the TripoSR architecture, extending its capability to process real-world images through unsupervised self-training and automatic data filtering.

The ultimate tool for codon optimization, capable of converting protein sequences into DNA sequences optimized for target organisms.

Image segmentation model based on the Transformers library for image segmentation tasks in vision applications

A fashion item image segmentation model based on SegFormer architecture, specifically designed for identifying and segmenting clothing and accessories

PLLaVA is an open-source video language chatbot, obtained by fine-tuning a large image language model on video instruction following data, which can be used for the research of multimodal large models and chatbots.

Base version of TrOCR model, specifically designed for Spanish printed text, based on Transformer architecture, fine-tuned on a custom dataset

PatchTST is a Transformer-based time series forecasting model designed for long-term time series forecasting, utilizing subsequence patching and channel independence techniques to improve prediction accuracy.

A monocular depth estimation model based on BEiT Transformer, capable of inferring fine depth information from a single image

A large-scale language model developed by the Japanese LLM-jp project, supporting text generation tasks in Japanese and English

GPT-2 is a self-supervised pre-trained language model based on the Transformer architecture, which excels at text generation tasks.

BGE Base English v1.5 is a transformer-based sentence embedding model, specifically designed for extracting sentence features and calculating sentence similarity.

MAEST is a Transformer model family based on PASST, focusing on music analysis applications, particularly excelling in music genre classification tasks.

This is a model for image classification tasks, supporting the English language and adopting an open license.

Audio representation model based on HuBERT architecture, pre-trained on the complete AudioSet dataset, suitable for general audio tasks

A vision Transformer model trained using the DINOv2 method, extracting robust visual features from massive image data through self-supervised learning

A SegFormer semantic segmentation model fine-tuned on the Segments.ai sidewalk-semantic dataset, suitable for sidewalk scene analysis

Transformer-based French printed text OCR model, filling the gap of French version in TrOCR models

Japanese HuBERT base model trained by rinna Co., Ltd., based on approximately 19,000 hours of Japanese speech corpus ReazonSpeech v1.

TrOCR is a Transformer-based optical character recognition model specifically designed for handwritten text recognition, fine-tuned on the IAM handwritten database.

An image classification model based on the transformers library for identifying and classifying plant diseases.

An OCR system based on Transformer architecture, specifically designed for recognizing Central Kurdish text, trained using synthetic data.

Pythia-160M is a language model dedicated to interpretability research developed by EleutherAI. It belongs to the 160M parameter scale version in the Pythia suite and is based on the Transformer architecture, trained on the Pile dataset.

The BLEURT model implemented based on PyTorch, used for text evaluation tasks in natural language processing.

A building facade semantic segmentation model based on SegFormer architecture, capable of recognizing 12 types of architectural elements

The first multi-task universal image segmentation framework, supporting semantic/instance/panoptic segmentation tasks with a single model

A scientific term recognition model based on SciBERT, supporting NER-enhanced topic modeling