GroqLLMConfiguration#
- class council.llm.GroqLLMConfiguration(model: str, api_key: str)[source]#
Bases:
LLMConfigurationBase
- __init__(model: str, api_key: str) None [source]#
Initialize a new instance
- Parameters:
api_key (str) – the api key
model (str) – the model name
- property model: Parameter[str]#
Groq model name
- property api_key: Parameter[str]#
Groq API Key
- property frequency_penalty: Parameter[float]#
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.
- property max_tokens: Parameter[int]#
Maximum number of tokens to generate.
- property presence_penalty: Parameter[float]#
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.
- property seed: Parameter[int]#
Random seed for generation.
- property stop: Parameter[str]#
Stop sequence.
- property temperature: Parameter[float]#
What sampling temperature to use, between 0 and 2.
- property top_p: Parameter[float]#
Nucleus sampling threshold.