llava-1.5-7b-hf Beta

l

llava-1.5-7b-hf Beta

Image-to-Text • llava-hf

@cf/llava-hf/llava-1.5-7b-hf

LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.

Usage

Workers - TypeScript

export interface Env {
  AI: Ai;
}


export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const res = await fetch("https://cataas.com/cat");
    const blob = await res.arrayBuffer();
    const input = {
      image: [...new Uint8Array(blob)],
      prompt: "Generate a caption for this image",
      max_tokens: 512,
    };
    const response = await env.AI.run(
      "@cf/llava-hf/llava-1.5-7b-hf",
      input
      );
    return new Response(JSON.stringify(response));
  },
} satisfies ExportedHandler<Env>;

Parameters

Input

• 0 string

  Binary string representing the image contents.

• 1 object
  • temperature number

    Controls the randomness of the output; higher values produce more random results.

  • prompt string

    The input text prompt for the model to generate a response.

  • raw boolean

    If true, a chat template is not applied and you must adhere to the specific model's expected formatting.

  • image
    • 0 array

      An array of integers that represent the image data constrained to 8-bit unsigned integer values

      • items number

        A value between 0 and 255

    • 1 string

      Binary string representing the image contents.

  • max_tokens integer default 512

    The maximum number of tokens to generate in the response.

Output

• description string

API Schemas

The following schemas are based on JSON Schema

Input

{
    "oneOf": [
        {
            "type": "string",
            "format": "binary",
            "description": "Binary string representing the image contents."
        },
        {
            "type": "object",
            "properties": {
                "temperature": {
                    "type": "number",
                    "description": "Controls the randomness of the output; higher values produce more random results."
                },
                "prompt": {
                    "type": "string",
                    "description": "The input text prompt for the model to generate a response."
                },
                "raw": {
                    "type": "boolean",
                    "default": false,
                    "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting."
                },
                "image": {
                    "oneOf": [
                        {
                            "type": "array",
                            "description": "An array of integers that represent the image data constrained to 8-bit unsigned integer values",
                            "items": {
                                "type": "number",
                                "description": "A value between 0 and 255"
                            }
                        },
                        {
                            "type": "string",
                            "format": "binary",
                            "description": "Binary string representing the image contents."
                        }
                    ]
                },
                "max_tokens": {
                    "type": "integer",
                    "default": 512,
                    "description": "The maximum number of tokens to generate in the response."
                }
            },
            "required": [
                "image"
            ]
        }
    ]
}

Output

{
    "type": "object",
    "contentType": "application/json",
    "properties": {
        "description": {
            "type": "string"
        }
    }
}