{ "architectures": [ "IsaacForConditionalGeneration" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "modular_isaac.IsaacConfig", "AutoModelForCausalLM": "modular_isaac.IsaacForConditionalGeneration" }, "bos_token_id": 151643, "dtype": "float32", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 6144, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 40960, "max_sequence_length": 16384, "max_window_layers": 28, "model_type": "isaac", "num_attention_heads": 16, "num_hidden_layers": 28, "num_key_value_heads": 8, "pixel_shuffle_scale": 2, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_interleaved": true, "mrope_section": null, "rope_type": "default" }, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "transformers_version": "4.56.1", "use_cache": true, "use_sliding_window": false, "video_patch_size": 16, "vision_config": { "attention_dropout": 0.0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "image_size": 256, "intermediate_size": 4304, "layer_norm_eps": 1e-06, "model_type": "pixel_shuffle_siglip2", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 27, "num_patches": 256, "patch_size": 16, "pixel_shuffle_scale_factor": 2 }, "vision_max_num_patches": 6144, "vision_min_num_patches": 256, "vision_token": "", "vocab_size": 151936 }