Models

The Model module is an extension of ModelInference with langchain support (option to get WatsonxLLM wrapper for watsonx foundation 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