{ "architectures": [ "CSGWukongForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "freeze_mm_mlp_adapter": false, "hidden_act": "silu", "hidden_size": 2048, "image_aspect_ratio": "pad", "initializer_range": 0.02, "intermediate_size": 5632, "max_position_embeddings": 2048, "mm_hidden_size": 1152, "mm_projector_lr": null, "mm_projector_type": "mlp2x_gelu", "mm_vision_tower": "/google/siglip-so400m-patch14-384", "model_type": "csg-vl-wukong", "num_attention_heads": 32, "num_hidden_layers": 22, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "tokenizer_model_max_length": 2048, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.39.0.dev0", "tune_mm_mlp_adapter": false, "use_cache": true, "use_mm_proj": true, "vocab_size": 32003 }