This is a transformers model hosted on Hugging Face Hub. Specific functions and uses are pending completion.

Natural Language ProcessingTransformers

A lightweight Russian-English bilingual language model fine-tuned based on SmolLM2-135M, with enhanced Russian processing capabilities but notable limitations

Natural Language ProcessingSafetensorsMultiple Languages

Cambrian is an open-source multimodal LLM (Large Language Model) designed with a vision-centric approach.

MultimodalTransformers

ZoeDepth is a depth estimation model fine-tuned on NYU and KITTI datasets, capable of estimating depth values in actual metric units.

Computer VisionTransformers

ZoeDepth is a model for monocular depth estimation, specifically fine-tuned on the NYU dataset, capable of zero-shot transfer and metric depth estimation.

Computer VisionTransformers

This model is a classifier for detecting AI-generated images, achieving 97.36% accuracy on the evaluation set.

Computer VisionTransformers

RoBERTa series models pretrained on datasets of varying scales (1M-1B tokens), including BASE and MED-SMALL specifications

Natural Language ProcessingJax

The GLPN model is trained on the NYUv2 dataset for monocular depth estimation, combining global and local path networks to achieve high-precision depth prediction.

Computer VisionTransformers

A RoBERTa base model pre-trained on 1B tokens with a validation perplexity of 3.93, suitable for English text processing tasks.

Natural Language ProcessingJax

RoBERTa variants pre-trained on datasets ranging from 1M to 1B tokens, including BASE and MED-SMALL specifications, suitable for natural language processing tasks in resource-limited scenarios

Natural Language ProcessingJax

A RoBERTa model pretrained on a small-scale dataset of 1M tokens, using the MED-SMALL architecture, suitable for text understanding tasks.

Natural Language ProcessingJax