stable-vicuna-13b-delta
StableVicuna-13B is a Vicuna-13B v0 model fine-tuned using reinforcement learning from human feedback (RLHF) via Proximal Policy Optimization (PPO) on various conversational and instructional datasets.
text → text · made by CarperAI
Sold by
Nobody in the catalogue publishes a price for this yet.
About
stable-vicuna-13b-delta — a text model from CarperAI.
It takes text and returns text. It was published in April 2023. The catalogue files it under chat. Its weights are published, but the licence forbids selling what it produces.
Every current figure
- Maker
- CarperAI
- Register
- model
- Takes
- text
- Returns
- text
- Published
- April 2023
- Parameters
- 13 billion · read from its own name
- Licence
- cc-by-nc-sa-4.0
Known as 1 name
CarperAI/stable-vicuna-13b-delta