{ "add_faster_video": false, "add_time_instruction": false, "architectures": [ "LlavaDreamForMaskedDiffusion" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_dream.DreamConfig", "AutoModel": "modeling_dream.DreamModel" }, "bos_token_id": 151643, "eos_token_id": 151643, "faster_token_stride": 10, "force_sample": false, "hidden_act": "silu", "hidden_size": 3584, "image_aspect_ratio": "anyres", "image_crop_resolution": null, "image_grid_pinpoints": [ [ 384, 768 ], [ 768, 384 ], [ 768, 768 ], [ 1152, 384 ], [ 384, 1152 ] ], "image_split_resolution": null, "initializer_range": 0.02, "intermediate_size": 18944, "mask_token_id": 151666, "max_position_embeddings": 131072, "max_window_layers": 28, "mm_hidden_size": 1152, "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": null, "mm_spatial_pool_mode": "bilinear", "mm_spatial_pool_stride": null, "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,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": "/data0/jacklishufan/siglip-so400m-patch14-384", "mm_vision_tower_lr": 2e-06, "model_type": "Dream", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "pad_token_id": 151643, "pos_skipping_range": 4096, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "tokenizer_model_max_length": 4096, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.50.3", "use_cache": false, "use_mm_proj": true, "use_mrope": false, "use_pos_skipping": false, "use_sliding_window": false, "vision_tower_pretrained": null, "vocab_size": 152064 }