{ "architectures": [ "TinyLlavaForConditionalGeneration" ], "cache_dir": null, "connector_type": "mlp2x_gelu", "hidden_size": 2048, "ignore_index": -100, "image_aspect_ratio": "square", "image_token_index": -200, "llm_model_name_or_path": "Qwen/Qwen2.5-3B", "model_type": "tinyllava", "num_queries": 128, "num_resampler_layers": 3, "pad_token": "<|endoftext|>", "pad_token_id": 151643, "resampler_hidden_size": 768, "text_config": { "_name_or_path": "Qwen/Qwen2.5-3B", "architectures": [ "Qwen2ForCausalLM" ], "bos_token_id": 151643, "eos_token_id": 151643, "hidden_size": 2048, "intermediate_size": 11008, "max_position_embeddings": 32768, "max_window_layers": 36, "model_type": "qwen2", "num_attention_heads": 16, "num_hidden_layers": 36, "num_key_value_heads": 2, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936 }, "tokenizer_model_max_length": 2048, "tokenizer_name_or_path": "Qwen/Qwen2.5-3B", "tokenizer_padding_side": "right", "tokenizer_use_fast": false, "torch_dtype": "bfloat16", "transformers_version": "4.40.1", "tune_type_connector": "full", "tune_type_llm": "full", "tune_type_vision_tower": "frozen", "tune_vision_tower_from_layer": 0, "use_cache": true, "vision_config": { "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "image_size": 384, "intermediate_size": 4304, "layer_norm_eps": 1e-06, "model_name_or_path": "google/siglip-so400m-patch14-384", "model_name_or_path2": "", "model_type": "siglip_vision_model", "num_attention_heads": 16, "num_hidden_layers": 27, "patch_size": 14 }, "vision_feature_layer": -2, "vision_feature_select_strategy": "patch", "vision_hidden_size": 1152, "vision_model_name_or_path": "google/siglip-so400m-patch14-384", "vision_model_name_or_path2": "", "vocab_size": 151936 }