view release on metacpan or  search on metacpan

ollama/ollama-curated.yaml  view on Meta::CPAN

          description: |
            Enable NUMA support. (Default: false)
        num_ctx:
          type: integer
          description: |
            Sets the size of the context window used to generate the next token.
        num_batch:
          type: integer
          description: |
            Sets the number of batches to use for generation. (Default: 1)
        num_gqa:
          type: integer
          description: |
            The number of GQA groups in the transformer layer. Required for some models, for example it is 8 for `llama2:70b`.
        num_gpu:
          type: integer
          description: |
            The number of layers to send to the GPU(s). On macOS it defaults to 1 to enable metal support, 0 to disable.
        main_gpu:
          type: integer
          description: |
            The GPU to use for the main model. Default is 0.
        low_vram:
          type: boolean
          description: |
            Enable low VRAM mode. (Default: false)
        f16_kv:
          type: boolean
          description: |
            Enable f16 key/value. (Default: false)
        logits_all:
          type: boolean
          description: |
            Enable logits all. (Default: false)
        vocab_only:
          type: boolean
          description: |
            Enable vocab only. (Default: false)
        use_mmap:
          type: boolean
          description: |
            Enable mmap. (Default: false)
        use_mlock:
          type: boolean
          description: |
            Enable mlock. (Default: false)
        embedding_only:
          type: boolean
          description: |
            Enable embedding only. (Default: false)
        rope_frequency_base:
          type: number
          format: float
          description: |
            The base of the rope frequency scale. (Default: 1.0)
        rope_frequency_scale:
          type: number
          format: float
          description: |
            The scale of the rope frequency. (Default: 1.0)
        num_thread:
          type: integer
          description: |
            Sets the number of threads to use during computation. By default, Ollama will detect this for optimal performance. It is recommended to set this value to the number of physical CPU cores your system has (as opposed to the logical number o...
    ResponseFormat:
      type: string
      description: |
        The format to return a response in. Currently the only accepted value is json.

        Enable JSON mode by setting the format parameter to json. This will structure the response as valid JSON.

        Note: it's important to instruct the model to use JSON in the prompt. Otherwise, the model may generate large amounts whitespace.
      enum:
        - json
    GenerateCompletionResponse:
      type: object
      description: The response class for the generate endpoint.
      properties:
        model:
          type: string
          description: *model_name
          example: llama2:7b
        created_at:
          type: string
          format: date-time
          description: Date on which a model was created.
          example: 2023-08-04T19:22:45.499127Z
        response:
          type: string
          description: The response for a given prompt with a provided model.
          example: The sky appears blue because of a phenomenon called Rayleigh scattering.
        done:
          type: boolean
          description: Whether the response has completed.
          example: true
        context:
          type: array
          description: |
            An encoding of the conversation used in this response, this can be sent in the next request to keep a conversational memory.
          items:
            type: integer
          example: [ 1, 2, 3 ]
        total_duration:
          type: integer
          description: Time spent generating the response.
          example: 5589157167
        load_duration:
          type: integer
          description: Time spent in nanoseconds loading the model.
          example: 3013701500
        prompt_eval_count:
          type: integer
          description: Number of tokens in the prompt.
          example: 46
        prompt_eval_duration:
          type: integer
          description: Time spent in nanoseconds evaluating the prompt.
          example: 1160282000
        eval_count:
          type: integer
          description: Number of tokens the response.
          example: 113
        eval_duration:
          type: integer