RunGPT supports the following models out of the box:
-
LLM (Large Language Model)
- LLaMA: open and efficient foundation language models by Meta
- Pythia: a collection of models developed to facilitate interpretability research by EleutherAI
- StableLM: series of large language models by Stability AI
- Vicuna: a chat assistant fine-tuned from LLaMA on user-shared conversations by LMSYS
- MOSS: conversational language model from Fudan University
-
LMM (Large Multi-modal Model)
- OpenFlamingo: an open source version of DeepMind's Flamingo model
- MiniGPT-4: aligns a frozen visual encoder with a frozen LLM, Vicuna, using just one projection layer.