{ "architectures": [ "LlavaOnevisionForConditionalGeneration" ], "ignore_index": -100, "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": 151646, "model_type": "llava_onevision", "multimodal_projector_bias": true, "projector_hidden_act": "gelu", "text_config": { "_attn_implementation_autoset": true, "_name_or_path": "Qwen/Qwen2-7B-Instruct", "apply_compression": true, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "compression_policy": "CompressionPolicy", "eos_token_id": 151645, "group_size": 2.0, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_group_prob": 2.0, "max_position_embeddings": 32768, "max_sample_rate": 0.02, "max_window_layers": 28, "model_type": "qwen2", "num_attention_heads": 28, "num_frames": 8, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sample_mode_num": { "content": 1, "frame": 8, "token": 23 }, "segment_ratio": 0.125, "sliding_window": 4096, "torch_dtype": "bfloat16", "use_cache": false, "use_sliding_window": false, "vocab_size": 152128 }, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_image_newline_parameter": true, "video_token_index": 151647, "vision_aspect_ratio": "anyres_max_9", "vision_config": { "apply_compression": true, "attention_dropout": 0.0, "compression_policy": "CompressionPolicy", "group_size": 2.0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "image_size": 384, "intermediate_size": 4304, "layer_norm_eps": 1e-06, "max_group_prob": 2.0, "max_sample_rate": 0.02, "model_type": "siglip_vision_model", "num_attention_heads": 16, "num_channels": 3, "num_frames": 8, "num_hidden_layers": 26, "patch_size": 14, "sample_mode_num": { "content": 1, "frame": 8, "token": 23 }, "segment_ratio": 0.125, "torch_dtype": "bfloat16", "use_cache": false, "vision_use_head": false }, "vision_feature_layer": -1, "vision_feature_select_strategy": "full" }