Local LLM

Following configurations are required to interact with a Local LLM:

• local.llm.temperature.default=2.0 : Temperature for the model
• local.llm.frequency_penalty.default=2.0 : Frequency Penalty for the model
• local.llm.presence_penalty.default=2.0 : Presence Penalty for the model
• local.llm.max_tokens.default=256 : Max Tokens for the model
• local.llm.top_p.default=2.0 : Top P for the model