{ "architectures": [ "MolmoOlmo3ForConditionalGeneration" ], "auto_map": { "AutoConfig": "configuration_molmo_olmo3.MolmoOlmo3Config", "AutoModelForImageTextToText": "modeling_molmo_olmo3.MolmoOlmo3ForConditionalGeneration", "AutoImageProcessor": "image_processing_molmo_olmo3.MolmoOlmo3ImageProcessor", "AutoProcessor": "processing_molmo_olmo3.MolmoOlmo3Processor" }, "bos_token_id": 100257, "dtype": "float32", "eos_token_id": 100257, "image_col_token_id": 100281, "image_end_token_id": 100279, "image_prompt_token_id": 100282, "image_start_token_id": 100278, "image_token_id": 100280, "include_cls_token": true, "lm_head_vocab_size": 100352, "model_type": "molmo_olmo3", "projector_hidden_act": "silu", "projector_intermediate_size": 11008, "text_config": { "architectures": [ "Olmo3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "dtype": "bfloat16", "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "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", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 65536, "model_type": "olmo3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pad_token_id": 100277, "rms_norm_eps": 1e-06, "rope_scaling": { "attention_factor": 1.2079441541679836, "beta_fast": 32, "beta_slow": 1, "factor": 8.0, "original_max_position_embeddings": 8192, "rope_type": "yarn" }, "rope_theta": 500000, "sliding_window": 4096, "use_cache": true, "vocab_size": 100480 }, "text_hidden_size": 4096, "tie_word_embeddings": false, "transformers_version": "4.57.1", "vision_config": { "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 768, "image_size": 224, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-05, "model_type": "clip_vision_model", "num_attention_heads": 12, "num_channels": 3, "num_hidden_layers": 12, "patch_size": 16, "projection_dim": 512 }, "vision_feature_layer": -1, "vision_final_norm_attr": "norm", "vision_hidden_size": 768, "vision_strip_final_norm": false, "vision_tower_name_or_path": "amitha/clip-vit-b16-datacomp-medium", "vision_trust_remote_code": false }