cambrian
Vision-based LLM
An open-source multimodal LLM project with a vision-centric design
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
2k stars
23 watching
117 forks
Language: Python
last commit: almost 2 years agochatbotclipcomputer-visiondinoinstruction-tuninglarge-language-modelsllmsmllmmultimodal-large-language-modelsrepresentation-learning
Related projects:
| Repository | Description | Stars |
|---|---|---|
 pleisto/yuren-baichuan-7b | A multi-modal large language model that integrates natural language and visual capabilities with fine-tuning for various tasks | 73 |
 mbzuai-oryx/groundinglmm | An end-to-end trained model capable of generating natural language responses integrated with object segmentation masks for interactive visual conversations | 797 |
 bobazooba/xllm-demo | A demo project showcasing customization possibilities of an XLLM library | 9 |
 lyuchenyang/macaw-llm | A multi-modal language model that integrates image, video, audio, and text data to improve language understanding and generation | 1,568 |
 victordibia/llmx | An API that provides a unified interface to multiple large language models for chat fine-tuning | 79 |
 bytedance/lynx-llm | A framework for training GPT4-style language models with multimodal inputs using large datasets and pre-trained models | 231 |
| bobazooba/xllm | A tool for training and fine-tuning large language models using advanced techniques | 387 |
 ailab-cvc/seed | An implementation of a multimodal language model with capabilities for comprehension and generation | 585 |
 damo-nlp-mt/polylm | A polyglot large language model designed to address limitations in current LLM research and provide better multilingual instruction-following capability. | 77 |
 openbmb/viscpm | A family of large multimodal models supporting multimodal conversational capabilities and text-to-image generation in multiple languages | 1,098 |
 terminaldweller/milla | An IRC bot that interacts with language models to provide answers and has customizable syntax highlighting. | 5 |
 nvlabs/eagle | Develops high-resolution multimodal LLMs by combining vision encoders and various input resolutions | 549 |
 open-mmlab/multimodal-gpt | Trains a multimodal chatbot that combines visual and language instructions to generate responses | 1,478 |
 evolvinglmms-lab/longva | An open-source project that enables the transfer of language understanding to vision capabilities through long context processing. | 347 |
 phellonchen/x-llm | A framework that enables large language models to process and understand multimodal inputs from various sources such as images and speech. | 308 |