Idefics2 is an open multimodal model that accepts arbitrary sequences of image and text inputs and produces text outputs.

Idefics2 8B

Detail

HTTPValidationError

Image URL to be used for the image description

Image URL


        Parameter to manage the number of tokens the model generates by adjusting the max new tokens.

        Specifying max new tokens helps you prevent long or irrelevant responses and control costs.
        

Max New Tokens

Prompt to be used for the image description

Prompt


        Parameter to penalty for repeating the same token.

        This setting reduces the repetition of words in the model's response by giving tokens that appear more a higher penalty.
        

Repetition Penalty


        Parameter to adjust the temperature value for the generation.

        Increasing temperature could lead to more randomness, which encourages more diverse or creative outputs.
        

Temperature


        Parameter to adjust the Top P probability for the generation.

        A high Top P value will enable the model to look at more possible words, including less likely ones, leading to more diverse outputs.
        

Idefics2 8B

Input

Result

Logs