Llama 2 Uncensored is based on Meta’s Llama 2 model, and was created by George Sung and Jarrad Hope using the process defined by Eric Hartford in his blog post.
CLI
Open the terminal and run ollama run llama2-uncensored
API
Example:
curl -X POST http://localhost:11434/api/generate -d '{
"model": "llama2-uncensored",
"prompt":"Write a recipe for dangerously spicy mayo."
}'
Memory requirements
- 7b models generally require at least 8GB of RAM
- 70b models generally require at least 64GB of RAM
References
https://erichartford.com/uncensored-models
7b parameters original source: George Sung
70b parameters original source: George Sung