config.json

{
  "architectures": [
    "Llama4ForConditionalGeneration"
  ],
  "boi_token_index": 200080,
  "eoi_token_index": 200081,
  "image_token_index": 200092,
  "model_type": "llama4",
  "text_config": {
    "_attn_implementation_autoset": true,
    "attention_bias": false,
    "attention_chunk_size": 8192,
    "attention_dropout": 0.0,
    "attn_scale": 0.1,
    "attn_temperature_tuning": 4,
    "floor_scale": 8192,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 512,
    "initializer_range": 0.02,
    "interleave_moe_layer_step": 1,
    "intermediate_size": 1024,
    "intermediate_size_mlp": 1024,
    "max_position_embeddings": 131072,
    "model_type": "llama4_text",
    "moe_layers": [
      0,
      1,
      2,
      3
    ],
    "no_rope_layers": [
      1,
      1,
      1,
      0
    ],
    "num_attention_heads": 8,
    "num_experts_per_tok": 1,
    "num_hidden_layers": 4,
    "num_key_value_heads": 2,
    "num_local_experts": 2,
    "output_router_logits": false,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 500000,
    "router_aux_loss_coef": 0.001,
    "router_jitter_noise": 0.0,
    "use_cache": true,
    "use_qk_norm": true,
    "vocab_size": 202048
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.51.0",
  "vision_config": {
    "_attn_implementation_autoset": true,
    "attention_dropout": 0.0,
    "hidden_act": "gelu",
    "hidden_size": 1408,
    "image_size": 336,
    "initializer_range": 0.02,
    "intermediate_size": 5632,
    "model_type": "llama4_vision_model",
    "multi_modal_projector_bias": false,
    "norm_eps": 1e-05,
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 4,
    "patch_size": 14,
    "pixel_shuffle_ratio": 0.5,
    "projector_dropout": 0.0,
    "projector_input_dim": 4096,
    "projector_output_dim": 4096,
    "rope_theta": 10000,
    "vision_feature_layer": -1,
    "vision_feature_select_strategy": "default",
    "vision_output_dim": 4096
  }
}