{
  "_name_or_path": "monoformer_imagenet_res256",
  "add_pos_embed_each_layer": false,
  "architectures": [
    "MonoFormerForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "decoder_t_embed": "adaln_before_decoder",
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "image_size": 256,
  "image_token_index": 32001,
  "in_channels": 4,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "learn_sigma": true,
  "max_position_embeddings": 2048,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "patch_size": 2,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "tokenizer_max_length": 512,
  "tokenizer_padding_side": "right",
  "torch_dtype": "float32",
  "transformers_version": "4.38.0",
  "use_adaln_final_layer": true,
  "use_bi_attn_img_tokens": true,
  "use_cache": true,
  "use_flash_attn": false,
  "use_pos_embed": true,
  "vocab_size": 32004
}