Foundation Models

Warning

Warning! Supported only for IBM watsonx as a Service and IBM Cloud Pak for Data 4.8.

Modules

• Models
  • Modules
    • Model
      • Model
        • Model.generate()
        • Model.generate_text()
        • Model.generate_text_stream()
        • Model.get_details()
        • Model.to_langchain()
        • Model.tokenize()
      • Enums
        • GenTextParamsMetaNames
        • GenTextReturnOptMetaNames
        • DecodingMethods
          • DecodingMethods.GREEDY
          • DecodingMethods.SAMPLE
        • ModelTypes
          • ModelTypes.CODELLAMA_34B_INSTRUCT_HF
          • ModelTypes.ELYZA_JAPANESE_LLAMA_2_7B_INSTRUCT
          • ModelTypes.FLAN_T5_XL
          • ModelTypes.FLAN_T5_XXL
          • ModelTypes.FLAN_UL2
          • ModelTypes.GPT_NEOX
          • ModelTypes.GRANITE_13B_CHAT
          • ModelTypes.GRANITE_13B_CHAT_V2
          • ModelTypes.GRANITE_13B_INSTRUCT
          • ModelTypes.GRANITE_13B_INSTRUCT_V2
          • ModelTypes.GRANITE_20B_MULTILINGUAL
          • ModelTypes.LLAMA_2_13B_CHAT
          • ModelTypes.LLAMA_2_70B_CHAT
          • ModelTypes.MIXTRAL_8X7B_INSTRUCT_V01_Q
          • ModelTypes.MPT_7B_INSTRUCT2
          • ModelTypes.MT0_XXL
          • ModelTypes.STARCODER
    • ModelInference
      • ModelInference
        • ModelInference.generate()
        • ModelInference.generate_text()
        • ModelInference.generate_text_stream()
        • ModelInference.get_details()
        • ModelInference.get_identifying_params()
        • ModelInference.to_langchain()
        • ModelInference.tokenize()
    • ModelInference for Deployments
      • Infer text with deployments
      • Creating ModelInference instance
      • Generate methods
• Prompt Tuning
  • Working with TuneExperiment and PromptTuner
    • Tune Experiment run
      • Configure PromptTuner
      • Get configuration parameters
      • Run prompt tuning
      • Get run status, get run details
      • Get data connections
      • Summary
      • Plot learning curves
      • Get model identifier
    • Tuned Model Inference
      • Working with deployments
      • Creating ModelInference instance
      • Importing data
      • Analyzing satisfaction
      • Generate methods
  • Tune Experiment
    • TuneExperiment
      • TuneExperiment
        • TuneExperiment.prompt_tuner()
        • TuneExperiment.runs()
    • Tune Runs
      • TuneRuns
        • TuneRuns.get_run_details()
        • TuneRuns.get_tuner()
        • TuneRuns.list()
    • Prompt Tuner
      • PromptTuner
        • PromptTuner.cancel_run()
        • PromptTuner.get_data_connections()
        • PromptTuner.get_model_id()
        • PromptTuner.get_params()
        • PromptTuner.get_run_details()
        • PromptTuner.get_run_status()
        • PromptTuner.plot_learning_curve()
        • PromptTuner.run()
        • PromptTuner.summary()
    • Enums
      • PromptTuningTypes
        • PromptTuningTypes.PT
      • PromptTuningInitMethods
        • PromptTuningInitMethods.RANDOM
        • PromptTuningInitMethods.TEXT
      • TuneExperimentTasks
        • TuneExperimentTasks.CLASSIFICATION
        • TuneExperimentTasks.CODE_GENERATION_AND_CONVERSION
        • TuneExperimentTasks.EXTRACTION
        • TuneExperimentTasks.GENERATION
        • TuneExperimentTasks.QUESTION_ANSWERING
        • TuneExperimentTasks.RETRIEVAL_AUGMENTED_GENERATION
        • TuneExperimentTasks.SUMMARIZATION
• Prompt Template Manager
  • PromptTemplateManager
    • PromptTemplateManager.delete_prompt()
    • PromptTemplateManager.get_lock()
    • PromptTemplateManager.list()
    • PromptTemplateManager.load_prompt()
    • PromptTemplateManager.lock()
    • PromptTemplateManager.store_prompt()
    • PromptTemplateManager.unlock()
    • PromptTemplateManager.update_prompt()
  • Enums
    • PromptTemplateFormats
      • PromptTemplateFormats.LANGCHAIN
      • PromptTemplateFormats.PROMPTTEMPLATE
      • PromptTemplateFormats.STRING
• Extensions
  • LangChain
    • WatsonxLLM
• Helpers
  • get_model_specs()
  • get_model_lifecycle()
  • get_model_specs_with_prompt_tuning_support()
  • get_supported_tasks()
• Custom models
  • Initialize APIClient object
  • Listing models specification
  • Storing model in service repository
  • Defining hardware specification
  • Deployment of custom foundation model
  • Working with deployments