Apriel-1.5-15b-Thinker is a multimodal reasoning model in the ServiceNow Apriel SLM series, with 15 billion parameters. It can compete with models 10 times its size in text and image reasoning tasks. This model achieves excellent reasoning ability through a mid-term training scheme and can reach SOTA performance without image SFT training or reinforcement learning.

MultimodalTransformers

Kairos-10M is a time series foundation model designed for cross-domain zero-shot prediction, with approximately 10 million parameters. It can handle heterogeneous time series data with different information densities and achieve strong generalization ability across different domains without fine-tuning.

Scientific ComputingTransformers

Kairos-50M is a time series foundation model with 50 million parameters, specifically designed for zero-shot prediction across different domains. It uses adaptive word segmentation and position encoding techniques to handle heterogeneous time series data with different information densities and can achieve strong generalization ability across different domains without fine-tuning.

Scientific ComputingTransformers

PatchFM is a basic model for univariate time series forecasting based on the Transformer architecture. It uses a block-by-block forecasting method, drawing on the training ideas of large language models to divide the time series into blocks for next-block forecasting. It supports multi-quantile output and uncertainty estimation.

Scientific ComputingSafetensors

Moirai 2.0 is a decoder-only general time series prediction Transformer model that has been pre-trained on multiple high-quality datasets, including GIFT-Eval, a subset of the Chronos dataset, synthetic time series, and Salesforce's internal operational data. Compared with the first version, significant improvements have been made in aspects such as the loss function, prediction method, and data processing.

Scientific ComputingSafetensors

Nitro-T is a series of text-to-image diffusion models focused on efficient training, which are competitive in image generation benchmark tests and have extremely short training times.

MultimodalDiffusersOther

YingLong is a pretrained model for time series forecasting, which has been pretrained on 78 billion time points and provides strong support for time series forecasting tasks.

Scientific ComputingSafetensors

YingLong is a foundation model for time series forecasting, pre - trained on 78B time points, providing strong support for time series forecasting tasks.

Scientific ComputingSafetensors

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

Scientific ComputingSafetensors

Toto is a foundational model designed for multivariate time series forecasting, particularly optimized for efficient processing of observability metrics

Scientific ComputingTransformers

ChatTime-1-7B-Base is a foundational model specialized in time series forecasting, supporting multimodal time series processing.

MultimodalGguf

ChatTime-1-7B-Chat is a multimodal foundation model specialized in time series forecasting, built on a 7B parameter scale.

MultimodalGguf

This model is designed for time series forecasting, supports the English language, and uses a specific license (bethana15).

Scientific ComputingTensorflowEnglish

A time series prediction model based on LSTM, used to predict the length and duration of women's menstrual cycles.

Scientific ComputingTensorflowEnglish

FinSeer StockLLM is an open-source 1-billion-parameter large language model specifically designed for financial time series forecasting, utilizing a Retrieval-Augmented Generation (RAG) framework.

Natural Language ProcessingTransformersEnglish

GEM is a multimodal large language model that integrates ECG time series, 12-lead ECG images, and text to enable clinical evidence-based ECG interpretation.

MultimodalTransformers

ChronoBERT is a series of high-performance temporally consistent large language models designed to eliminate look-ahead bias and training data leakage while maintaining strong language understanding capabilities in time-sensitive applications.

Natural Language ProcessingTransformersEnglish

A time series forecasting model fine-tuned on proprietary datasets, particularly suitable for intermittent demand forecasting scenarios.

Scientific ComputingTransformers

A time series forecasting model fine-tuned based on the amazon/chronos-bolt-base architecture, specifically optimized for intermittent demand forecasting tasks

Scientific ComputingTransformers

Intermittent demand forecasting model fine-tuned on 190 million time series data points

Scientific ComputingTransformers