{ "ada_dlm_loss_ratio": null, "ada_perm_ratio_global": null, "ada_perm_ratio_per_block": null, "adaptive_mask_rate": false, "add_faster_video": false, "add_time_instruction": false, "ar_loss_weight": 1.0, "architectures": [ "NemotronLabsDiffusionImageForMaskedDiffusion" ], "attention_bias": false, "attention_dropout": 0.0, "attn_implementation": null, "auto_map": { "AutoConfig": "configuration_nemotron_labs_diffusion_image.NemotronLabsDiffusionImageConfig", "AutoModel": "modeling_nemotron_labs_diffusion_image.NemotronLabsDiffusionImageForMaskedDiffusion", "AutoModelForCausalLM": "modeling_nemotron_labs_diffusion_image.NemotronLabsDiffusionImageForMaskedDiffusion" }, "block_size": 32, "bos_token_id": 1, "d_model": 4096, "d_model_gen": 4096, "diff_loss_weight": 1, "dlm_arch": "encoder", "dlm_loss_weight": null, "dlm_paradigm": "bidirectional", "dlm_type": "llada", "downsample": true, "dp_varying_mask_ratio": false, "dtype": "bfloat16", "dual_tower": true, "dual_tower_layers": 16, "enable_self_spec": false, "enforce_mask": false, "eos_token_id": 11, "faster_token_stride": 10, "flip_ratio": 0.2, "force_sample": false, "gen_edit_loss_weight": 0.2, "global_loss_avg": false, "group_ce_weight": "{16384:0.2}", "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "image_aspect_ratio": "t2i_only", "image_crop_resolution": null, "image_grid_pinpoints": [ [384, 768], [768, 384], [768, 768], [1152, 384], [384, 1152] ], "image_split_resolution": null, "include_bias": false, "initializer_range": 0.02, "intermediate_size": 14336, "mask_token_id": 100, "max_position_embeddings": 262144, "mlp_bias": false, "mlp_hidden_size_gen": 14336, "mm_hidden_size": 3584, "mm_newline_position": "grid", "mm_patch_merge_type": "spatial_unpad", "mm_pooler_ratio": 2, "mm_projector_lr": null, "mm_projector_type": "mlp2x_gelu", "mm_resampler_type": "none", "mm_spatial_pool_mode": "conv", "mm_spatial_pool_out_channels": 3584, "mm_spatial_pool_stride": 1, "mm_tunable_parts": "mm_language_model", "mm_use_im_patch_token": false, "mm_use_im_start_end": false, "mm_vision_select_feature": "patch", "mm_vision_select_layer": -2, "mm_vision_tower": null, "mm_vision_tower_lr": null, "mm_vqvae": "emu3_vqvae", "model_type": "nemotron_labs_diffusion_image", "multi_sampling": null, "num_ar_layers": 0, "num_attention_heads": 32, "num_diffusion_layers": 0, "num_hidden_layers": 34, "num_key_value_heads": 8, "num_skip_loss_tokens": 0, "pad_token_id": 11, "pos_skipping_range": 4096, "prefix_ratio": 0.8, "prompt_drop_rate": 0.1, "random_length_prob": 0, "rms_norm_eps": 1e-05, "rope_parameters": { "beta_fast": 32.0, "beta_slow": 1.0, "factor": 16.0, "llama_4_scaling_beta": 0.1, "mscale": 1.0, "mscale_all_dim": 1.0, "original_max_position_embeddings": 16384, "rope_theta": 1000000.0, "rope_type": "yarn", "type": "yarn" }, "rope_scaling": { "beta_fast": 32.0, "beta_slow": 1.0, "factor": 16.0, "llama_4_scaling_beta": 0.1, "mscale": 1.0, "mscale_all_dim": 1.0, "original_max_position_embeddings": 16384, "rope_theta": 1000000.0, "rope_type": "yarn", "type": "yarn" }, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "tok_mask_half_life_ratio": null, "tokenizer_model_max_length": 4096, "tokenizer_padding_side": "right", "transformers_version": "4.57.6", "use_cache": false, "use_mm_proj": false, "use_pos_skipping": false, "vision_tower_pretrained": null, "vocab_size": 132101 }