image_audio/metadata.json

{
  "source": "sglang",
  "model_id": "hf-internal-testing/tiny-inkling",
  "case": "image_audio",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Describe the image and tell me what is said in the clip."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "http://images.cocodataset.org/val2017/000000039769.jpg"
          }
        },
        {
          "type": "audio_url",
          "audio_url": {
            "url": "https://huggingface.co/datasets/adarshxs/voxcpm2-native-generated-audio-user-ref/resolve/main/zs_medium.wav"
          }
        }
      ]
    }
  ],
  "image_urls": [
    "http://images.cocodataset.org/val2017/000000039769.jpg"
  ],
  "audio_urls": [
    "https://huggingface.co/datasets/adarshxs/voxcpm2-native-generated-audio-user-ref/resolve/main/zs_medium.wav"
  ],
  "quantity": "next_token_logprobs (log_softmax of last-position logits)",
  "logit_vocab_size": 200058,
  "input_ids_len": 26,
  "argmax_token_id": 176530
}