{ "architectures": [ "DeepseekVLModel" ], "dtype": "float32", "image_token_id": 3, "model_type": "deepseek_vl", "pad_token_id": 100001, "text_config": { "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 100000, "eos_token_id": 100001, "head_dim": 16, "hidden_act": "gelu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 32, "max_position_embeddings": 512, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 100001, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 100016 }, "tie_word_embeddings": false, "transformers_version": "5.16.0.dev0", "vision_config": { "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "image_size": 8, "intermediate_size": 32, "layer_norm_eps": 1e-06, "model_type": "siglip_vision_model", "num_attention_heads": 2, "num_channels": 3, "num_hidden_layers": 2, "patch_size": 4, "vision_use_head": false } }