ml-ferret
Multilingual task-computer
An end-to-end multilingual language model that can perform various tasks like referring and grounding with high granularity
9k stars
160 watching
501 forks
Language: Python
last commit: about 1 year ago Related projects:
| Repository | Description | Stars |
|---|---|---|
| | Evaluates and compares the performance of multimodal large language models on various tasks | 56 |
| | Develops and maintains large language models with improved stability and performance | 15,829 |
| | A platform providing data, models, and evaluation benchmarks for large language models to promote accessibility and democratization of AI technology | 2,938 |
| | An end-to-end trained model capable of generating natural language responses integrated with object segmentation masks for interactive visual conversations | 797 |
| | A general-purpose language model pre-trained with an autoregressive blank-filling objective and designed for various natural language understanding and generation tasks. | 3,207 |
| | A framework for efficient fine-tuning and deployment of large language models | 4,659 |
| | A platform for collaboration, data management, and reproducibility in machine learning development | 1,440 |
| | A high-performance deep learning library written in Swift for Apple platforms. | 6,032 |
| | An evaluation toolkit for large vision-language models | 1,514 |
| | Demonstrates Flux and MVVM architecture on iOS with RxSwift for managing user authentication and data fetching from a Qiita API. | 105 |
| | A framework for building geospatial machine learning models that fuse multiple datasets to gain insights into agriculture and sustainability | 694 |
| | An open-source toolkit for pretraining and fine-tuning large language models | 2,732 |
| | Automates the creation of CRUD iOS apps based on Swift data models using Realm as the persistence layer. | 136 |
| | Enables secure, on-device machine learning training and inference for Android devices using PySyft models | 86 |
| | Develops strong fundamental image recognition models with high accuracy and flexibility | 2,963 |