Class: Google::Cloud::Dialogflow::CX::V3::Generator::ModelParameter

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/dialogflow/cx/v3/generator.rb

Overview

Parameters to be passed to the LLM. If not set, default values will be used.

Instance Attribute Summary collapse

Instance Attribute Details

#max_decode_steps ⇒ ::Integer

Returns The maximum number of tokens to generate.

Returns:

  • (::Integer) —

    The maximum number of tokens to generate.



93
94
95
96
 
# File 'proto_docs/google/cloud/dialogflow/cx/v3/generator.rb', line 93

class ModelParameter
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#temperature ⇒ ::Float

Returns The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied. Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random.

Returns:

  • (::Float) —

    The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied. Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random.



93
94
95
96
 
# File 'proto_docs/google/cloud/dialogflow/cx/v3/generator.rb', line 93

class ModelParameter
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#top_k ⇒ ::Integer

Returns If set, the sampling process in each step is limited to the top_k tokens with highest probabilities. Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random.

Returns:

  • (::Integer) —

    If set, the sampling process in each step is limited to the top_k tokens with highest probabilities. Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random.



93
94
95
96
 
# File 'proto_docs/google/cloud/dialogflow/cx/v3/generator.rb', line 93

class ModelParameter
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#top_p ⇒ ::Float

Returns If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k. Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random.

Returns:

  • (::Float) —

    If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k. Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random.



93
94
95
96
 
# File 'proto_docs/google/cloud/dialogflow/cx/v3/generator.rb', line 93

class ModelParameter
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end