This is a merge of llama-2-70b with the "creative" adapter from https://hf.co/jondurbin/airoboros-lmoe-70b-2.1
Basically, it's using a subset of the airoboros 2.1 training that is specifically focused on creative tasks, such as writing, roleplay, etc.
- Downloads last month
- 7
Inference API (serverless) is not available, repository is disabled.