config.json

{
  "architectures": [
    "BagelForConditionalGeneration"
  ],
  "model_type": "bagel",
  "visual_gen": true,
  "visual_und": true,
  "llm_config": {
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "hidden_act": "silu",
    "hidden_size": 3584,
    "initializer_range": 0.02,
    "intermediate_size": 18944,
    "max_position_embeddings": 32768,
    "max_window_layers": 28,
    "model_type": "qwen2",
    "num_attention_heads": 28,
    "num_hidden_layers": 28,
    "num_key_value_heads": 4,
    "qk_norm": true,
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000.0,
    "sliding_window": 131072,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.43.1",
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 152064
  },
  "vit_config": {
    "hidden_size": 1152,
    "image_size": 980,
    "intermediate_size": 4304,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14,
    "num_channels": 3
  },
  "vae_config": {
    "z_channels": 16,
    "downsample": 8
  },
  "latent_patch_size": 2,
  "max_latent_size": 32,
  "vit_max_num_patch_per_side": 70,
  "connector_act": "gelu_pytorch_tanh",
  "interpolate_pos": false,
  "timestep_shift": 1.0,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.49.0"
}