MOSS
MOSS is the first domestically released conversational large-scale language model developed by the Fudan University team
Tags:AI Dialogue Chat AI Training ModelAI Model modelMOSS is the first domestically released conversational large-scale language model developed by the Fudan University team, and the public was invited to participate in the internal testing in February this year. It can perform a series of tasks such as dialogue generation, programming, and fact answering, bridging the entire technical path for generative language models to understand human intentions and have dialogue capabilities. On April 21st, the new version of MOSS model was officially launched and announced as open source.
data statistics
Relevant Navigation
![StableVicuna](https://gpttopic.com/wp-content/uploads/2023/12/b906e-chat.lmsys.org.png)
StableVicuna is the first large-scale open-source chatbot trained through human feedback based reinforcement learning (RLHF), launched by StablityAI behind Stable Diffusion. StableVicuna is a further instruction fine-tuning and RLHF training version of Vicuna v0 13b, which is an LLaMA 13 billion model with instruction fine-tuning.
![StableLM](https://gpttopic.com/wp-content/uploads/2023/12/8aaab-github.com.png)
StableLM is the latest open-source ChatGPT like large language model launched by the team behind Stable Diffusion, Stability AI. The model is currently in the Alpha version and has parameter quantities of 3 billion and 7 billion, respectively. In the future, a parameter model of 15 billion to 65 billion will be launched.