config.json

{
  "architectures": [
    "AriaForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "modeling_aria.AriaConfig",
    "AutoModelForCausalLM": "modeling_aria.AriaForConditionalGeneration"
  },
  "ignore_index": -100,
  "image_token_index": 9,
  "model_type": "aria",
  "projector_patch_to_query_dict": {
    "1225": 128,
    "4900": 256
  },
  "text_config": {
    "hidden_size": 2560,
    "intermediate_size": 13568,
    "max_position_embeddings": 65536,
    "model_type": "aria_moe_lm",
    "moe_intermediate_size": 1664,
    "moe_num_experts": 64,
    "moe_topk": 6,
    "num_attention_heads": 20,
    "num_experts_per_tok": 6,
    "num_hidden_layers": 28,
    "num_key_value_heads": 20,
    "rope_theta": 5000000,
    "vocab_size": 100352
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.0",
  "vision_config": {
    "_flash_attn_2_enabled": true,
    "architectures": [
      "AriaVisionModel"
    ],
    "hidden_size": 1152,
    "image_size": 980,
    "intermediate_size": 4304,
    "model_type": "aria_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14,
    "torch_dtype": "bfloat16"
  }
}