{ "adapter_layer_norm_eps": 1e-06, "alignment_activation_fn": "swiglu", "alignment_intermediate_size": 28672, "architectures": [ "AyaVisionForConditionalGeneration" ], "bos_token_id": 5, "downsample_factor": 2, "eos_token_id": 255001, "image_token_index": 255036, "max_splits_per_img": 12, "model_type": "aya_vision", "pad_token_id": 0, "projector_hidden_act": "gelu", "quantization_config": { "_load_in_4bit": true, "_load_in_8bit": false, "bnb_4bit_compute_dtype": "bfloat16", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "nf4", "bnb_4bit_use_double_quant": true, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": [ "lm_head", "multi_modal_projector", "merger", "modality_projection" ], "llm_int8_threshold": 6.0, "load_in_4bit": true, "load_in_8bit": false, "quant_method": "bitsandbytes" }, "text_config": { "attention_bias": false, "attention_dropout": 0.0, "cache_implementation": "hybrid", "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "layer_norm_eps": 1e-05, "logit_scale": 0.25, "max_position_embeddings": 8192, "model_type": "cohere2", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rope_scaling": null, "rope_theta": 50000, "sliding_window": 4096, "sliding_window_pattern": 4, "torch_dtype": "bfloat16", "use_cache": true, "use_qk_norm": false, "vocab_size": 256000 }, "torch_dtype": "bfloat16", "transformers_version": "4.50.0.dev0", "unsloth_fixed": true, "vision_config": { "attention_dropout": 0.0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "image_size": 364, "intermediate_size": 4304, "layer_norm_eps": 1e-06, "model_type": "siglip_vision_model", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 27, "patch_size": 14, "torch_dtype": "bfloat16", "vision_use_head": false }, "vision_feature_layer": -1, "vision_feature_select_strategy": "full" }