File size: 5,960 Bytes
531a115 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 |
{
"adapter_layer_norm_eps": 1e-06,
"alignment_activation_fn": "swiglu",
"alignment_intermediate_size": 49152,
"architectures": [
"AyaVisionForConditionalGeneration"
],
"bos_token_id": 5,
"downsample_factor": 2,
"eos_token_id": 255001,
"image_token_index": 255022,
"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",
"language_model.model.layers.31.mlp",
"language_model.model.layers.32.mlp",
"language_model.model.layers.33.mlp",
"language_model.model.layers.36.self_attn",
"language_model.model.layers.34.mlp",
"language_model.model.layers.35.mlp",
"language_model.model.layers.36.mlp",
"language_model.model.layers.37.self_attn",
"vision_tower.vision_model.encoder.layers.19.mlp",
"vision_tower.vision_model.encoder.layers.20.self_attn",
"vision_tower.vision_model.encoder.layers.19.self_attn",
"vision_tower.vision_model.encoder.layers.20.mlp",
"vision_tower.vision_model.encoder.layers.22.self_attn",
"vision_tower.vision_model.encoder.layers.25.self_attn",
"vision_tower.vision_model.encoder.layers.21.mlp",
"vision_tower.vision_model.encoder.layers.23.self_attn",
"language_model.model.layers.2.mlp",
"vision_tower.vision_model.encoder.layers.18.mlp",
"vision_tower.vision_model.encoder.layers.22.mlp",
"vision_tower.vision_model.encoder.layers.21.self_attn",
"vision_tower.vision_model.encoder.layers.24.self_attn",
"vision_tower.vision_model.encoder.layers.18.self_attn",
"vision_tower.vision_model.encoder.layers.23.mlp",
"language_model.model.layers.37.mlp",
"vision_tower.vision_model.encoder.layers.17.self_attn",
"vision_tower.vision_model.encoder.layers.17.mlp",
"vision_tower.vision_model.encoder.layers.16.mlp",
"vision_tower.vision_model.encoder.layers.24.mlp",
"vision_tower.vision_model.encoder.layers.16.self_attn",
"vision_tower.vision_model.encoder.layers.14.mlp",
"vision_tower.vision_model.encoder.layers.25.mlp",
"vision_tower.vision_model.encoder.layers.15.mlp",
"vision_tower.vision_model.encoder.layers.26.mlp",
"vision_tower.vision_model.encoder.layers.26.self_attn",
"vision_tower.vision_model.encoder.layers.15.self_attn",
"vision_tower.vision_model.encoder.layers.14.self_attn",
"multi_modal_projector",
"vision_tower.vision_model.encoder.layers.13.mlp",
"vision_tower.vision_model.encoder.layers.12.mlp",
"vision_tower.vision_model.encoder.layers.13.self_attn",
"vision_tower.vision_model.encoder.layers.11.mlp",
"vision_tower.vision_model.encoder.layers.12.self_attn",
"vision_tower.vision_model.encoder.layers.9.self_attn",
"vision_tower.vision_model.encoder.layers.11.self_attn",
"vision_tower.vision_model.encoder.layers.10.self_attn",
"language_model.model.layers.38.mlp",
"vision_tower.vision_model.encoder.layers.10.mlp",
"vision_tower.vision_model.encoder.layers.6.self_attn",
"vision_tower.vision_model.encoder.layers.7.self_attn",
"vision_tower.vision_model.encoder.layers.8.mlp",
"vision_tower.vision_model.encoder.layers.8.self_attn",
"vision_tower.vision_model.encoder.layers.7.mlp",
"vision_tower.vision_model.encoder.layers.9.mlp",
"vision_tower.vision_model.encoder.layers.5.self_attn",
"vision_tower.vision_model.encoder.layers.3.self_attn",
"vision_tower.vision_model.encoder.layers.6.mlp",
"vision_tower.vision_model.encoder.layers.4.self_attn",
"vision_tower.vision_model.encoder.layers.5.mlp",
"vision_tower.vision_model.encoder.layers.4.mlp",
"vision_tower.vision_model.encoder.layers.0.self_attn",
"vision_tower.vision_model.encoder.layers.3.mlp",
"vision_tower.vision_model.encoder.layers.2.self_attn",
"vision_tower.vision_model.encoder.layers.2.mlp",
"vision_tower.vision_model.encoder.layers.1.mlp",
"vision_tower.vision_model.encoder.layers.1.self_attn",
"vision_tower.vision_model.encoder.layers.0.mlp",
"language_model.model.layers.38.self_attn",
"language_model.model.layers.39.mlp"
],
"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,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 24576,
"layer_norm_eps": 1e-05,
"logit_scale": 0.0625,
"max_position_embeddings": 8192,
"model_type": "cohere",
"num_attention_heads": 64,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"rope_scaling": null,
"rope_theta": 4000000,
"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"
}
|