Set a model from Mistral AI
Usage
model_mistral(
model = "open-mistral-7b",
temperature = 0,
top_p = 0.1,
max_tokens = 100,
min_tokens = 0,
stop = NULL,
seed = NA,
format = "none",
safe_prompt = FALSE,
tools = NULL,
tool_choice = "auto"
)Arguments
- temperature
The temperature of the model where higher temperature means higher creativity.
- top_p
The nucleus sampling or penalty. It limits the cumulative probability of the most likely tokens. Higher values allow more tokens and diverse responses, and while lower values are more focused and constrained answers.
- max_tokens
The maximum number of tokens to generate. This limits the length of the response. Tokens refers to a unit of text the model reads and can vary from one character to several words, varying based on the model. As a rule of thumb 1 token is approximately 4 characters or 0.75 words for English text.
- min_tokens
The minimum number of tokens to generate.
- stop
A list of stop sequences to use.
- seed
The seed to use for the model.
- format
The format
- safe_prompt
Whether to use safe prompt or not.
- tools
The list of tools. Not implemented.
- tool_choice
The choice of tool. Not implemented.
See also
Other large-lanugage-models:
model_ollama(),
model_openai(),
model_vendor()