shikra
Spatial reference model
A multimodal language model designed to excel in spatial coordinate inputs/outputs and natural language referential dialogue without external models or vocabularies.
748 stars
8 watching
45 forks
Language: Python
last commit: 8 months ago Related projects:
Repository | Description | Stars |
---|---|---|
| An implementation of SegNet architecture for semantic segmentation using tensorflow and keras. | 179 |
| An implementation of an attention-based sequence-to-sequence neural machine translation model in Keras. | 30 |
| A unified interface to various deep learning architectures | 818 |
| Implementing a unified modal learning framework for generative vision-language models | 43 |
| Develops large multimodal models for high-resolution understanding and analysis of text, images, and other data types. | 143 |
| Aligns large multimodal models with human intentions and values using various algorithms and fine-tuning methods. | 270 |
| A package that adds unique references to models in Laravel, allowing quick reference-based routing and API building. | 13 |
| An implementation of a deep neural network architecture for real-time semantic segmentation in Python. | 115 |
| A multimodal language model designed to process video and text data for driving scenarios | 51 |
| A collection of lightweight state-of-the-art language models designed to support multilinguality, coding, and reasoning tasks on constrained resources. | 232 |
| An implementation of a deep learning model for image segmentation using Keras and dilated convolutions | 301 |
| A script for preparing datasets and training a VGG16-based segmentation model on the Cityscapes dataset | 6 |
| A Python library toolkit for geospatial machine learning focused on creating embeddings for downstream tasks | 225 |
| A personal collection of STEM resources and references | 41 |
| Provides simple features access for R, allowing users to work with geospatial data in a unified way across various formats and systems. | 1,353 |