{ "architectures": [ "Blip2ForConditionalGeneration" ], "dtype": "bfloat16", "image_text_hidden_size": 256, "image_token_index": 151669, "initializer_factor": 1.0, "initializer_range": 0.02, "model_type": "blip-2", "num_query_tokens": 32, "qformer_config": { "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "cross_attention_frequency": 2, "dtype": "bfloat16", "encoder_hidden_size": 1408, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "blip_2_qformer", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "position_embedding_type": "absolute", "use_qformer_text_input": false, "vocab_size": 30522 }, "text_config": { "_name_or_path": "/home/alpha/vqwen-qformer/models/Qwen3-4B", "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 9728, "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", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 40960, "max_window_layers": 36, "model_type": "qwen3", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "pad_token_id": null, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 1000000, "rope_type": "default" }, "sliding_window": null, "tie_word_embeddings": true, "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }, "transformers_version": "5.9.0", "use_decoder_only_language_model": true, "vision_config": { "attention_dropout": 0.0, "dropout": 0.0, "dtype": "bfloat16", "hidden_act": "gelu", "hidden_size": 1408, "image_size": 224, "initializer_factor": 1.0, "initializer_range": 1e-10, "intermediate_size": 6144, "layer_norm_eps": 1e-06, "model_type": "blip_2_vision_model", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 39, "patch_size": 14, "projection_dim": 512, "qkv_bias": true } }