Class InferenceParameter (2.33.0)

InferenceParameter(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Attributes

Name Description
max_output_tokens int
Optional. Maximum number of the output tokens for the generator. This field is a member of oneof_ _max_output_tokens.
temperature float
Optional. Controls the randomness of LLM predictions. Low temperature = less random. High temperature = more random. If unset (or 0), uses a default value of 0. This field is a member of oneof_ _temperature.
top_k int
Optional. Top-k changes how the model selects tokens for output. A top-k of 1 means the selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-k of 3 means that the next token is selected from among the 3 most probable tokens (using temperature). For each token selection step, the top K tokens with the highest probabilities are sampled. Then tokens are further filtered based on topP with the final token selected using temperature sampling. Specify a lower value for less random responses and a higher value for more random responses. Acceptable value is [1, 40], default to 40. This field is a member of oneof_ _top_k.
top_p float
Optional. Top-p changes how the model selects tokens for output. Tokens are selected from most K (see topK parameter) probable to least until the sum of their probabilities equals the top-p value. For example, if tokens A, B, and C have a probability of 0.3, 0.2, and 0.1 and the top-p value is 0.5, then the model will select either A or B as the next token (using temperature) and doesn't consider C. The default top-p value is 0.95. Specify a lower value for less random responses and a higher value for more random responses. Acceptable value is [0.0, 1.0], default to 0.95. This field is a member of oneof_ _top_p.