
StableVicuna is the first product from StabilityAI, the company behind Stable Diffusion, to be released via theReinforcement Learning Based on Human Feedback (RLHF)A large-scale open-source chatbot for training.StableVicuna is a further instruction-fine-tuned and RLHF-trained version of Vicuna v0 13b, which is an instruction-fine-tuned LLaMA 13 billion model.
data statistics
Data evaluation
This site blue shirt technology to provide theStableVicunaAll from the network, does not guarantee the accuracy and completeness of the external links, at the same time, for the external links to point to, not by the Blue Shirt Technology actual control, in August 10, 2023 4:00 pm included in the web page, the content, all belong to the compliance and legal, the content of the late web page, such as violations, you can directly contact the webmaster for deletion, Blue Shirt Technology does not assume any responsibility.
Relevant Navigation

Evidently AI
Auto-GPT
Gradio
BLOOM
Tiangong AI Assistant
ChatGLM




