{ "architectures": [ "Sa2VAChatModelQwen" ], "auto_map": { "AutoConfig": "configuration_sa2va_chat.Sa2VAChatConfigQwen", "AutoModel": "modeling_sa2va_qwen.Sa2VAChatModelQwen", "AutoModelForCausalLM": "modeling_sa2va_qwen.Sa2VAChatModelQwen" }, "dtype": "float32", "image_token_id": 151655, "model_type": "sa2va_chat", "template": "qwen_chat", "text_config": { "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, "max_position_embeddings": 262144, "model_type": "qwen3_vl_text", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_interleaved": true, "mrope_section": [ 24, 20, 20 ], "rope_type": "default" }, "rope_theta": 5000000, "use_cache": true, "vocab_size": 151674 }, "tie_word_embeddings": false, "transformers_version": "4.57.0", "video_token_id": 151656, "vision_config": { "deepstack_visual_indexes": [ 5, 11, 17 ], "depth": 24, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1024, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 4096, "model_type": "qwen3_vl", "num_heads": 16, "num_position_embeddings": 2304, "out_hidden_size": 2560, "patch_size": 16, "spatial_merge_size": 2, "temporal_patch_size": 2 }, "vision_end_token_id": 151653, "vision_start_token_id": 151652 }