ChatBridge
Multimodal Model
A unified multimodal language model capable of interpreting and reasoning about various modalities without paired data.
ChatBridge, an approach to learning a unified multimodal model to interpret, correlate, and reason about various modalities without relying on all combinations of paired data.
49 stars
2 watching
1 forks
Language: Python
last commit: over 1 year ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 thunlp/muffin | A framework for building multimodal foundation models that can serve as bridges between different modalities and language models. | 59 |
 42wim/matterbridge | A bridge that connects multiple chat protocols to a unified interface | 6,745 |
 andrewnguonly/chatabstractions | Provides a framework for creating custom chat models with dynamic failover and load balancing features | 79 |
 multimodal-art-projection/omnibench | Evaluates and benchmarks multimodal language models' ability to process visual, acoustic, and textual inputs simultaneously. | 15 |
 langboat/mengzi3 | An 8B and 13B language model based on the Llama architecture with multilingual capabilities. | 2,031 |
 mainframecomputer/fullmoon-ios | An iOS app that provides a chat interface to local large language models, optimized for Apple silicon. | 450 |
 openbmb/viscpm | A family of large multimodal models supporting multimodal conversational capabilities and text-to-image generation in multiple languages | 1,098 |
 yuliang-liu/monkey | An end-to-end image captioning system that uses large multi-modal models and provides tools for training, inference, and demo usage. | 1,849 |
 lyuchenyang/macaw-llm | A multi-modal language model that integrates image, video, audio, and text data to improve language understanding and generation | 1,568 |
 deltachat-bot/matterdelta | A tool that enables communication between Delta Chat and other supported chat services using Matterbridge. | 13 |
 xverse-ai/xverse-v-13b | A large multimodal model for visual question answering, trained on a dataset of 2.1B image-text pairs and 8.2M instruction sequences. | 78 |
 kohjingyu/fromage | A framework for grounding language models to images and handling multimodal inputs and outputs | 478 |
 tele-ai/telechat-52b | An open-source chat model built on top of the 52B large language model, with improvements in position encoding, activation function, and layer normalization. | 40 |
 pleisto/yuren-baichuan-7b | A multi-modal large language model that integrates natural language and visual capabilities with fine-tuning for various tasks | 73 |
 mshukor/unival | A unified model for image, video, audio, and language tasks that can be fine-tuned for various downstream applications. | 224 |