config.json

{
  "_name_or_path": "nsandiman/imagecraft-ft-co-224",
  "_vocab_size": 257216,
  "architectures": [
    "PaliGemmaForConditionalGeneration"
  ],
  "bos_token_id": 2,
  "eos_token_id": 1,
  "hidden_size": 2048,
  "image_token_index": 257152,
  "model_type": "paligemma",
  "pad_token_id": 0,
  "projection_dim": 2048,
  "text_config": {
    "hidden_size": 2048,
    "intermediate_size": 16384,
    "model_type": "gemma",
    "num_attention_heads": 8,
    "num_hidden_layers": 18,
    "num_image_tokens": 256,
    "num_key_value_heads": 1,
    "torch_dtype": "float32",
    "vocab_size": 257216
  },
  "torch_dtype": "float32",
  "transformers_version": "4.46.0.dev0",
  "vision_config": {
    "hidden_size": 1152,
    "intermediate_size": 4304,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "num_image_tokens": 256,
    "patch_size": 14,
    "projection_dim": 2048,
    "projector_hidden_act": "gelu_fast",
    "torch_dtype": "float32",
    "vision_use_head": false
  },
  "voicecraft_config": {
    "model_name": "330M_TTSEnhanced.pth",
    "encoded": "encodec_4cb2048_giga.th",
    "voice_audio_path": "84_121550_000074_000000.wav",
    "voice_audio_transcript": "But when I had approached so near to them The common object, which the sense deceives, Lost not by distance any of its marks",
    "top_k": 0,
    "top_p": 0.9,
    "temperature": 1,
    "kvcache": 1,
    "codec_sr": 50,
    "codec_audio_sr": 16000,
    "silence_tokens": [1388, 1898, 131],
    "stop_repetition": 3,
    "sample_batch_size": 2,
    "seed": 1,
    "cut_off_sec": 7.87
  }
}