/AWS1/CL_SGMMDELSPECULATIVED00¶
Settings for the model speculative decoding technique that's applied by a model optimization job.
CONSTRUCTOR¶
IMPORTING¶
Required arguments:¶
iv_technique TYPE /AWS1/SGMMDELSPECULATIVEDECO00 /AWS1/SGMMDELSPECULATIVEDECO00¶
The speculative decoding technique to apply during model optimization.
Optional arguments:¶
io_trainingdatasource TYPE REF TO /AWS1/CL_SGMMDELSPECULATIVED01 /AWS1/CL_SGMMDELSPECULATIVED01¶
The location of the training data to use for speculative decoding. The data must be formatted as ShareGPT, OpenAI Completions or OpenAI Chat Completions. The input can also be unencrypted captured data from a SageMaker endpoint as long as the endpoint uses one of the above formats.
Queryable Attributes¶
Technique¶
The speculative decoding technique to apply during model optimization.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_TECHNIQUE() |
Getter for TECHNIQUE, with configurable default |
ASK_TECHNIQUE() |
Getter for TECHNIQUE w/ exceptions if field has no value |
HAS_TECHNIQUE() |
Determine if TECHNIQUE has a value |
TrainingDataSource¶
The location of the training data to use for speculative decoding. The data must be formatted as ShareGPT, OpenAI Completions or OpenAI Chat Completions. The input can also be unencrypted captured data from a SageMaker endpoint as long as the endpoint uses one of the above formats.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_TRAININGDATASOURCE() |
Getter for TRAININGDATASOURCE |