{ "architectures": [ "BunnyQwenForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_llava_qwen2.LlavaQwen2Config", "AutoModelForCausalLM": "modeling_llava_qwen2.LlavaQwen2ForCausalLM" }, "eos_token_id": 151645, "freeze_mm_mlp_adapter": false, "hidden_act": "silu", "hidden_size": 8192, "image_aspect_ratio": "pad", "initializer_range": 0.02, "intermediate_size": 29568, "language_model": "cognitivecomputations/dolphin-2.9.2-qwen2-72b", "max_position_embeddings": 131072, "max_window_layers": 28, "mm_hidden_size": 1152, "mm_projector_lr": null, "mm_projector_type": "mlp2x_gelu", "mm_vision_tower": "google/siglip-so400m-patch14-384", "model_type": "llava-qwen2", "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "quantization": { "group_size": 64, "bits": 4 }, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": 4096, "tie_word_embeddings": false, "tokenizer_model_max_length": 4096, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.41.2", "tune_mm_mlp_adapter": false, "use_cache": true, "use_mm_proj": true, "use_sliding_window": false, "vision_config": { "intermediate_size": 4352 }, "vocab_size": 152064 }