{ "architectures": [ "LlavaOnevisionForConditionalGeneration" ], "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": 256000, "model_type": "llava_onevision", "multimodal_projector_bias": true, "projector_hidden_act": "gelu", "text_config": { "_name_or_path": "Unbabel/Tower-Plus-9B", "architectures": [ "Gemma2ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attn_logit_softcapping": 50.0, "cache_implementation": "hybrid", "eos_token_id": 107, "final_logit_softcapping": 30.0, "head_dim": 256, "hidden_act": "gelu_pytorch_tanh", "hidden_activation": "gelu_pytorch_tanh", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 14336, "layer_types": [ "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 8192, "model_type": "gemma2", "num_attention_heads": 16, "num_hidden_layers": 42, "num_key_value_heads": 8, "query_pre_attn_scalar": 224, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "torch_dtype": "bfloat16", "use_cache": false, "vocab_size": 256064 }, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.55.4", "use_image_newline_parameter": true, "video_token_index": 256001, "vision_aspect_ratio": "anyres_max_9", "vision_config": { "attention_dropout": 0.0, "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": 26, "patch_size": 14, "vision_use_head": false }, "vision_feature_layer": -1, "vision_feature_select_strategy": "full" }