config.json

{
  "_name_or_path": "physical-intelligence/pi0fast_base",
  "_vocab_size": 257157,
  "architectures": [
    "PaliGemmaForConditionalGeneration"
  ],
  "bos_token_id": 2,
  "eos_token_id": 1,
  "hidden_size": 2048,
  "ignore_index": -100,
  "image_token_index": 257152,
  "think_start_token_index": 257153,
  "think_end_token_index": 257154,
  "action_start_token_index": 257155,
  "action_end_token_index": 257156,
  "action_token_begin_idx": 254976,
  "action_token_end_idx": 257023,
  "model_type": "paligemma",
  "pad_token_id": 0,
  "projection_dim": 2048,
  "text_config": {
    "hidden_activation": "gelu_pytorch_tanh",
    "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": 257157
  },
  "torch_dtype": "float32",
  "transformers_version": "4.48.1",
  "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_pytorch_tanh",
    "torch_dtype": "float32",
    "vision_use_head": false
  }
}