{ "architectures": [ "LlavaOnevisionForConditionalGeneration" ], "auto_map": { "AutoConfig": "_configuration_llava_onevision_kormo.LlavaOnevisionKORMoConfig" }, "bos_token_id": 125030, "dtype": "float32", "eos_token_id": 125040, "image_grid_pinpoints": [ [ 384, 384 ], [ 384, 768 ], [ 384, 1152 ], [ 384, 1536 ], [ 384, 1920 ], [ 384, 2304 ], [ 768, 384 ], [ 768, 768 ], [ 768, 1152 ], [ 768, 1536 ], [ 768, 1920 ], [ 768, 2304 ], [ 1152, 384 ], [ 1152, 768 ], [ 1152, 1152 ], [ 1152, 1536 ], [ 1152, 1920 ], [ 1152, 2304 ], [ 1536, 384 ], [ 1536, 768 ], [ 1536, 1152 ], [ 1536, 1536 ], [ 1536, 1920 ], [ 1536, 2304 ], [ 1920, 384 ], [ 1920, 768 ], [ 1920, 1152 ], [ 1920, 1536 ], [ 1920, 1920 ], [ 1920, 2304 ], [ 2304, 384 ], [ 2304, 768 ], [ 2304, 1152 ], [ 2304, 1536 ], [ 2304, 1920 ], [ 2304, 2304 ] ], "image_token_index": 125041, "model_type": "llava_onevision", "multimodal_projector_bias": true, "pad_token_id": 125032, "projector_hidden_act": "gelu", "text_config": { "_name_or_path": "KORMo-Team/KORMo-10B-sft", "architectures": [ "KORMoForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "_configuration_kormo.KORMoConfig", "AutoModel": "_modeling_kormo.KORMoModel", "AutoModelForCausalLM": "_modeling_kormo.KORMoForCausalLM" }, "bos_token_id": 125030, "dtype": "float32", "eos_token_id": 125040, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 16384, "mask_type": null, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "kormo", "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 125032, "pretrain_tp": 1, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 8000000.0, "tie_word_embeddins": false, "use_cache": true, "vocab_size": 125184 }, "tie_word_embeddings": false, "transformers_version": "4.57.6", "video_token_index": 125042, "vision_aspect_ratio": "anyres_max_9", "vision_config": { "attention_dropout": 0.0, "dtype": "float32", "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "image_size": 384, "intermediate_size": 4304, "layer_norm_eps": 1e-06, "model_type": "siglip_vision_model", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 27, "patch_size": 14, "vision_use_head": false }, "vision_feature_layer": -1, "vision_feature_select_strategy": "full" }