config.json

{
  "_name_or_path": "/data/cambrian-u/ckpt/20251105_instruction-tune_60k_v5-64_1_5b_diffloss_1_dit9_8b_cfg0_1_context1024_ep64_bs64_lr5_66e-5-last",
  "architectures": [
    "CambrianQwenForCausalLM"
  ],
  "attention_dropout": 0.0,
  "aux_regression": false,
  "aux_regression_coef": 1.0,
  "bos_token_id": 151643,
  "connector_only": true,
  "ddt_encoder_depth": 2,
  "diff_head_lr": 0.000566,
  "diffusion_base_dim": null,
  "diffusion_class_dropout_prob": 0.1,
  "diffusion_model_channels": 1152,
  "diffusion_model_depth": 32,
  "diffusion_model_heads": 32,
  "diffusion_model_hidden_size": 4096,
  "diffusion_model_z_channels": 4096,
  "diffusion_norm_stats_path": null,
  "diffusion_split_per_token": 256,
  "diffusion_timesteps_per_sample": 1,
  "dit_cls": "DiT",
  "eos_token_id": 151645,
  "freeze_mm_mlp_adapter": false,
  "generation_alignment_tower": null,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "image_aspect_ratio": "square",
  "image_position": 35,
  "initializer_range": 0.02,
  "intermediate_size": 8960,
  "max_position_embeddings": 32768,
  "max_window_layers": 21,
  "miv_token_len": 0,
  "mm_hidden_size": 1152,
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": true,
  "mm_vision_sampler_lr": null,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -1,
  "mm_vision_tower_aux_list": [
    "google/siglip2-so400m-patch14-224"
  ],
  "mm_vision_tower_aux_token_len_list": [
    256
  ],
  "mm_vision_tower_lr": 2e-06,
  "model_type": "cambrian_qwen",
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "num_key_value_heads": 2,
  "patch_size": 2,
  "pretrain_adapter_and_vision_head": null,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "si_token_len": 729,
  "sliding_window": 32768,
  "tie_word_embeddings": true,
  "tokenizer_model_max_length": 1024,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.37.0",
  "tune_adapter_and_vision_head": false,
  "tune_mm_mlp_adapter": false,
  "tune_vision_head": false,
  "unfreeze_mm_vision_tower": false,
  "use_cache": true,
  "use_mm_proj": true,
  "use_sliding_window": false,
  "vision_coef": 2.0,
  "vision_hidden_size": 1152,
  "vision_loss": "diffusion-loss",
  "vision_loss_mode": "query",
  "vision_tower_aux_token_len_list": [
    256
  ],
  "vocab_size": 151667
}