Update config.json
Browse files- config.json +215 -171
config.json
CHANGED
|
@@ -3,18 +3,19 @@
|
|
| 3 |
"Gemma3ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
"boi_token_index": 255999,
|
|
|
|
|
|
|
| 6 |
"eoi_token_index": 256000,
|
| 7 |
-
"eos_token_id":
|
| 8 |
-
1,
|
| 9 |
-
106
|
| 10 |
-
],
|
| 11 |
"image_token_index": 262144,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"mm_tokens_per_image": 256,
|
| 14 |
"model_type": "gemma3",
|
|
|
|
| 15 |
"quantization_config": {
|
| 16 |
"config_groups": {
|
| 17 |
"group_0": {
|
|
|
|
| 18 |
"input_activations": {
|
| 19 |
"actorder": null,
|
| 20 |
"block_structure": null,
|
|
@@ -46,187 +47,228 @@
|
|
| 46 |
}
|
| 47 |
},
|
| 48 |
"format": "float-quantized",
|
| 49 |
-
"global_compression_ratio":
|
| 50 |
"ignore": [
|
| 51 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
|
| 52 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
|
| 53 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj",
|
| 54 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj",
|
| 55 |
-
"vision_tower.vision_model.encoder.layers.0.mlp.fc1",
|
| 56 |
-
"vision_tower.vision_model.encoder.layers.0.mlp.fc2",
|
| 57 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
|
| 58 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
|
| 59 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
|
| 60 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
|
| 61 |
-
"vision_tower.vision_model.encoder.layers.1.mlp.fc1",
|
| 62 |
-
"vision_tower.vision_model.encoder.layers.1.mlp.fc2",
|
| 63 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
|
| 64 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
|
| 65 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
|
| 66 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
|
| 67 |
-
"vision_tower.vision_model.encoder.layers.2.mlp.fc1",
|
| 68 |
-
"vision_tower.vision_model.encoder.layers.2.mlp.fc2",
|
| 69 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
|
| 70 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
|
| 71 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
|
| 72 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj",
|
| 73 |
-
"vision_tower.vision_model.encoder.layers.3.mlp.fc1",
|
| 74 |
-
"vision_tower.vision_model.encoder.layers.3.mlp.fc2",
|
| 75 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
|
| 76 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
|
| 77 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
|
| 78 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
|
| 79 |
-
"vision_tower.vision_model.encoder.layers.4.mlp.fc1",
|
| 80 |
-
"vision_tower.vision_model.encoder.layers.4.mlp.fc2",
|
| 81 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
|
| 82 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj",
|
| 83 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
|
| 84 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
|
| 85 |
-
"vision_tower.vision_model.encoder.layers.5.mlp.fc1",
|
| 86 |
-
"vision_tower.vision_model.encoder.layers.5.mlp.fc2",
|
| 87 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
|
| 88 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
|
| 89 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
|
| 90 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
|
| 91 |
-
"vision_tower.vision_model.encoder.layers.6.mlp.fc1",
|
| 92 |
-
"vision_tower.vision_model.encoder.layers.6.mlp.fc2",
|
| 93 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
|
| 94 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj",
|
| 95 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
|
| 96 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
|
| 97 |
-
"vision_tower.vision_model.encoder.layers.7.mlp.fc1",
|
| 98 |
-
"vision_tower.vision_model.encoder.layers.7.mlp.fc2",
|
| 99 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
|
| 100 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
|
| 101 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
|
| 102 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
|
| 103 |
-
"vision_tower.vision_model.encoder.layers.8.mlp.fc1",
|
| 104 |
-
"vision_tower.vision_model.encoder.layers.8.mlp.fc2",
|
| 105 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
|
| 106 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
|
| 107 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
|
| 108 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj",
|
| 109 |
-
"vision_tower.vision_model.encoder.layers.9.mlp.fc1",
|
| 110 |
-
"vision_tower.vision_model.encoder.layers.9.mlp.fc2",
|
| 111 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
|
| 112 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
|
| 113 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
|
| 114 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
|
| 115 |
-
"vision_tower.vision_model.encoder.layers.10.mlp.fc1",
|
| 116 |
-
"vision_tower.vision_model.encoder.layers.10.mlp.fc2",
|
| 117 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
|
| 118 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
|
| 119 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
|
| 120 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
|
| 121 |
-
"vision_tower.vision_model.encoder.layers.11.mlp.fc1",
|
| 122 |
-
"vision_tower.vision_model.encoder.layers.11.mlp.fc2",
|
| 123 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
|
| 124 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
|
| 125 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
|
| 126 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
|
| 127 |
-
"vision_tower.vision_model.encoder.layers.12.mlp.fc1",
|
| 128 |
-
"vision_tower.vision_model.encoder.layers.12.mlp.fc2",
|
| 129 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
|
| 130 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
|
| 131 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
|
| 132 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj",
|
| 133 |
-
"vision_tower.vision_model.encoder.layers.13.mlp.fc1",
|
| 134 |
-
"vision_tower.vision_model.encoder.layers.13.mlp.fc2",
|
| 135 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
|
| 136 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
|
| 137 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
|
| 138 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
|
| 139 |
-
"vision_tower.vision_model.encoder.layers.14.mlp.fc1",
|
| 140 |
-
"vision_tower.vision_model.encoder.layers.14.mlp.fc2",
|
| 141 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
|
| 142 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj",
|
| 143 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
|
| 144 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
|
| 145 |
-
"vision_tower.vision_model.encoder.layers.15.mlp.fc1",
|
| 146 |
-
"vision_tower.vision_model.encoder.layers.15.mlp.fc2",
|
| 147 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
|
| 148 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
|
| 149 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
|
| 150 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
|
| 151 |
-
"vision_tower.vision_model.encoder.layers.16.mlp.fc1",
|
| 152 |
-
"vision_tower.vision_model.encoder.layers.16.mlp.fc2",
|
| 153 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
|
| 154 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
|
| 155 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
|
| 156 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
|
| 157 |
-
"vision_tower.vision_model.encoder.layers.17.mlp.fc1",
|
| 158 |
-
"vision_tower.vision_model.encoder.layers.17.mlp.fc2",
|
| 159 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
|
| 160 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
|
| 161 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
|
| 162 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
|
| 163 |
-
"vision_tower.vision_model.encoder.layers.18.mlp.fc1",
|
| 164 |
-
"vision_tower.vision_model.encoder.layers.18.mlp.fc2",
|
| 165 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
|
| 166 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
|
| 167 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
|
| 168 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
|
| 169 |
-
"vision_tower.vision_model.encoder.layers.19.mlp.fc1",
|
| 170 |
-
"vision_tower.vision_model.encoder.layers.19.mlp.fc2",
|
| 171 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
|
| 172 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
|
| 173 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj",
|
| 174 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
|
| 175 |
-
"vision_tower.vision_model.encoder.layers.20.mlp.fc1",
|
| 176 |
-
"vision_tower.vision_model.encoder.layers.20.mlp.fc2",
|
| 177 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
|
| 178 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
|
| 179 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
|
| 180 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
|
| 181 |
-
"vision_tower.vision_model.encoder.layers.21.mlp.fc1",
|
| 182 |
-
"vision_tower.vision_model.encoder.layers.21.mlp.fc2",
|
| 183 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
|
| 184 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
|
| 185 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
|
| 186 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
|
| 187 |
-
"vision_tower.vision_model.encoder.layers.22.mlp.fc1",
|
| 188 |
-
"vision_tower.vision_model.encoder.layers.22.mlp.fc2",
|
| 189 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
|
| 190 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
|
| 191 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
|
| 192 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
|
| 193 |
-
"vision_tower.vision_model.encoder.layers.23.mlp.fc1",
|
| 194 |
-
"vision_tower.vision_model.encoder.layers.23.mlp.fc2",
|
| 195 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj",
|
| 196 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj",
|
| 197 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj",
|
| 198 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj",
|
| 199 |
-
"vision_tower.vision_model.encoder.layers.24.mlp.fc1",
|
| 200 |
-
"vision_tower.vision_model.encoder.layers.24.mlp.fc2",
|
| 201 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj",
|
| 202 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj",
|
| 203 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj",
|
| 204 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj",
|
| 205 |
-
"vision_tower.vision_model.encoder.layers.25.mlp.fc1",
|
| 206 |
-
"vision_tower.vision_model.encoder.layers.25.mlp.fc2",
|
| 207 |
-
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj",
|
| 208 |
-
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj",
|
| 209 |
-
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj",
|
| 210 |
-
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj",
|
| 211 |
-
"vision_tower.vision_model.encoder.layers.26.mlp.fc1",
|
| 212 |
-
"vision_tower.vision_model.encoder.layers.26.mlp.fc2",
|
| 213 |
-
"
|
| 214 |
],
|
| 215 |
"kv_cache_scheme": null,
|
| 216 |
"quant_method": "compressed-tensors",
|
| 217 |
-
"quantization_status": "compressed"
|
|
|
|
|
|
|
|
|
|
| 218 |
},
|
| 219 |
"text_config": {
|
|
|
|
| 220 |
"attention_bias": false,
|
| 221 |
"attention_dropout": 0.0,
|
| 222 |
"attn_logit_softcapping": null,
|
| 223 |
"cache_implementation": "hybrid",
|
|
|
|
| 224 |
"final_logit_softcapping": null,
|
| 225 |
"head_dim": 256,
|
| 226 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 227 |
"hidden_size": 2560,
|
| 228 |
"initializer_range": 0.02,
|
| 229 |
"intermediate_size": 10240,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 230 |
"max_position_embeddings": 131072,
|
| 231 |
"model_type": "gemma3_text",
|
| 232 |
"num_attention_heads": 8,
|
|
@@ -242,13 +284,15 @@
|
|
| 242 |
"rope_theta": 1000000.0,
|
| 243 |
"sliding_window": 1024,
|
| 244 |
"sliding_window_pattern": 6,
|
|
|
|
| 245 |
"use_cache": true,
|
| 246 |
"vocab_size": 262208
|
| 247 |
},
|
| 248 |
-
"
|
| 249 |
-
"
|
| 250 |
"vision_config": {
|
| 251 |
"attention_dropout": 0.0,
|
|
|
|
| 252 |
"hidden_act": "gelu_pytorch_tanh",
|
| 253 |
"hidden_size": 1152,
|
| 254 |
"image_size": 896,
|
|
|
|
| 3 |
"Gemma3ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
"boi_token_index": 255999,
|
| 6 |
+
"bos_token_id": 2,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
"eoi_token_index": 256000,
|
| 9 |
+
"eos_token_id": 106,
|
|
|
|
|
|
|
|
|
|
| 10 |
"image_token_index": 262144,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"mm_tokens_per_image": 256,
|
| 13 |
"model_type": "gemma3",
|
| 14 |
+
"pad_token_id": 0,
|
| 15 |
"quantization_config": {
|
| 16 |
"config_groups": {
|
| 17 |
"group_0": {
|
| 18 |
+
"format": "float-quantized",
|
| 19 |
"input_activations": {
|
| 20 |
"actorder": null,
|
| 21 |
"block_structure": null,
|
|
|
|
| 47 |
}
|
| 48 |
},
|
| 49 |
"format": "float-quantized",
|
| 50 |
+
"global_compression_ratio": null,
|
| 51 |
"ignore": [
|
| 52 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
|
| 53 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
|
| 54 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj",
|
| 55 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj",
|
| 56 |
+
"model.vision_tower.vision_model.encoder.layers.0.mlp.fc1",
|
| 57 |
+
"model.vision_tower.vision_model.encoder.layers.0.mlp.fc2",
|
| 58 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
|
| 59 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
|
| 60 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
|
| 61 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
|
| 62 |
+
"model.vision_tower.vision_model.encoder.layers.1.mlp.fc1",
|
| 63 |
+
"model.vision_tower.vision_model.encoder.layers.1.mlp.fc2",
|
| 64 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
|
| 65 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
|
| 66 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
|
| 67 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
|
| 68 |
+
"model.vision_tower.vision_model.encoder.layers.2.mlp.fc1",
|
| 69 |
+
"model.vision_tower.vision_model.encoder.layers.2.mlp.fc2",
|
| 70 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
|
| 71 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
|
| 72 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
|
| 73 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj",
|
| 74 |
+
"model.vision_tower.vision_model.encoder.layers.3.mlp.fc1",
|
| 75 |
+
"model.vision_tower.vision_model.encoder.layers.3.mlp.fc2",
|
| 76 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
|
| 77 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
|
| 78 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
|
| 79 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
|
| 80 |
+
"model.vision_tower.vision_model.encoder.layers.4.mlp.fc1",
|
| 81 |
+
"model.vision_tower.vision_model.encoder.layers.4.mlp.fc2",
|
| 82 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
|
| 83 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj",
|
| 84 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
|
| 85 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
|
| 86 |
+
"model.vision_tower.vision_model.encoder.layers.5.mlp.fc1",
|
| 87 |
+
"model.vision_tower.vision_model.encoder.layers.5.mlp.fc2",
|
| 88 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
|
| 89 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
|
| 90 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
|
| 91 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
|
| 92 |
+
"model.vision_tower.vision_model.encoder.layers.6.mlp.fc1",
|
| 93 |
+
"model.vision_tower.vision_model.encoder.layers.6.mlp.fc2",
|
| 94 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
|
| 95 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj",
|
| 96 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
|
| 97 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
|
| 98 |
+
"model.vision_tower.vision_model.encoder.layers.7.mlp.fc1",
|
| 99 |
+
"model.vision_tower.vision_model.encoder.layers.7.mlp.fc2",
|
| 100 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
|
| 101 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
|
| 102 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
|
| 103 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
|
| 104 |
+
"model.vision_tower.vision_model.encoder.layers.8.mlp.fc1",
|
| 105 |
+
"model.vision_tower.vision_model.encoder.layers.8.mlp.fc2",
|
| 106 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
|
| 107 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
|
| 108 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
|
| 109 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj",
|
| 110 |
+
"model.vision_tower.vision_model.encoder.layers.9.mlp.fc1",
|
| 111 |
+
"model.vision_tower.vision_model.encoder.layers.9.mlp.fc2",
|
| 112 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
|
| 113 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
|
| 114 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
|
| 115 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
|
| 116 |
+
"model.vision_tower.vision_model.encoder.layers.10.mlp.fc1",
|
| 117 |
+
"model.vision_tower.vision_model.encoder.layers.10.mlp.fc2",
|
| 118 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
|
| 119 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
|
| 120 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
|
| 121 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
|
| 122 |
+
"model.vision_tower.vision_model.encoder.layers.11.mlp.fc1",
|
| 123 |
+
"model.vision_tower.vision_model.encoder.layers.11.mlp.fc2",
|
| 124 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
|
| 125 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
|
| 126 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
|
| 127 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
|
| 128 |
+
"model.vision_tower.vision_model.encoder.layers.12.mlp.fc1",
|
| 129 |
+
"model.vision_tower.vision_model.encoder.layers.12.mlp.fc2",
|
| 130 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
|
| 131 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
|
| 132 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
|
| 133 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj",
|
| 134 |
+
"model.vision_tower.vision_model.encoder.layers.13.mlp.fc1",
|
| 135 |
+
"model.vision_tower.vision_model.encoder.layers.13.mlp.fc2",
|
| 136 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
|
| 137 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
|
| 138 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
|
| 139 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
|
| 140 |
+
"model.vision_tower.vision_model.encoder.layers.14.mlp.fc1",
|
| 141 |
+
"model.vision_tower.vision_model.encoder.layers.14.mlp.fc2",
|
| 142 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
|
| 143 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj",
|
| 144 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
|
| 145 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
|
| 146 |
+
"model.vision_tower.vision_model.encoder.layers.15.mlp.fc1",
|
| 147 |
+
"model.vision_tower.vision_model.encoder.layers.15.mlp.fc2",
|
| 148 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
|
| 149 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
|
| 150 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
|
| 151 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
|
| 152 |
+
"model.vision_tower.vision_model.encoder.layers.16.mlp.fc1",
|
| 153 |
+
"model.vision_tower.vision_model.encoder.layers.16.mlp.fc2",
|
| 154 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
|
| 155 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
|
| 156 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
|
| 157 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
|
| 158 |
+
"model.vision_tower.vision_model.encoder.layers.17.mlp.fc1",
|
| 159 |
+
"model.vision_tower.vision_model.encoder.layers.17.mlp.fc2",
|
| 160 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
|
| 161 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
|
| 162 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
|
| 163 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
|
| 164 |
+
"model.vision_tower.vision_model.encoder.layers.18.mlp.fc1",
|
| 165 |
+
"model.vision_tower.vision_model.encoder.layers.18.mlp.fc2",
|
| 166 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
|
| 167 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
|
| 168 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
|
| 169 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
|
| 170 |
+
"model.vision_tower.vision_model.encoder.layers.19.mlp.fc1",
|
| 171 |
+
"model.vision_tower.vision_model.encoder.layers.19.mlp.fc2",
|
| 172 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
|
| 173 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
|
| 174 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj",
|
| 175 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
|
| 176 |
+
"model.vision_tower.vision_model.encoder.layers.20.mlp.fc1",
|
| 177 |
+
"model.vision_tower.vision_model.encoder.layers.20.mlp.fc2",
|
| 178 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
|
| 179 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
|
| 180 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
|
| 181 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
|
| 182 |
+
"model.vision_tower.vision_model.encoder.layers.21.mlp.fc1",
|
| 183 |
+
"model.vision_tower.vision_model.encoder.layers.21.mlp.fc2",
|
| 184 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
|
| 185 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
|
| 186 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
|
| 187 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
|
| 188 |
+
"model.vision_tower.vision_model.encoder.layers.22.mlp.fc1",
|
| 189 |
+
"model.vision_tower.vision_model.encoder.layers.22.mlp.fc2",
|
| 190 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
|
| 191 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
|
| 192 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
|
| 193 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
|
| 194 |
+
"model.vision_tower.vision_model.encoder.layers.23.mlp.fc1",
|
| 195 |
+
"model.vision_tower.vision_model.encoder.layers.23.mlp.fc2",
|
| 196 |
+
"model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj",
|
| 197 |
+
"model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj",
|
| 198 |
+
"model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj",
|
| 199 |
+
"model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj",
|
| 200 |
+
"model.vision_tower.vision_model.encoder.layers.24.mlp.fc1",
|
| 201 |
+
"model.vision_tower.vision_model.encoder.layers.24.mlp.fc2",
|
| 202 |
+
"model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj",
|
| 203 |
+
"model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj",
|
| 204 |
+
"model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj",
|
| 205 |
+
"model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj",
|
| 206 |
+
"model.vision_tower.vision_model.encoder.layers.25.mlp.fc1",
|
| 207 |
+
"model.vision_tower.vision_model.encoder.layers.25.mlp.fc2",
|
| 208 |
+
"model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj",
|
| 209 |
+
"model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj",
|
| 210 |
+
"model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj",
|
| 211 |
+
"model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj",
|
| 212 |
+
"model.vision_tower.vision_model.encoder.layers.26.mlp.fc1",
|
| 213 |
+
"model.vision_tower.vision_model.encoder.layers.26.mlp.fc2",
|
| 214 |
+
"lm_head"
|
| 215 |
],
|
| 216 |
"kv_cache_scheme": null,
|
| 217 |
"quant_method": "compressed-tensors",
|
| 218 |
+
"quantization_status": "compressed",
|
| 219 |
+
"sparsity_config": {},
|
| 220 |
+
"transform_config": {},
|
| 221 |
+
"version": "0.12.3.a20251114"
|
| 222 |
},
|
| 223 |
"text_config": {
|
| 224 |
+
"_sliding_window_pattern": 6,
|
| 225 |
"attention_bias": false,
|
| 226 |
"attention_dropout": 0.0,
|
| 227 |
"attn_logit_softcapping": null,
|
| 228 |
"cache_implementation": "hybrid",
|
| 229 |
+
"dtype": "bfloat16",
|
| 230 |
"final_logit_softcapping": null,
|
| 231 |
"head_dim": 256,
|
| 232 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 233 |
"hidden_size": 2560,
|
| 234 |
"initializer_range": 0.02,
|
| 235 |
"intermediate_size": 10240,
|
| 236 |
+
"layer_types": [
|
| 237 |
+
"sliding_attention",
|
| 238 |
+
"sliding_attention",
|
| 239 |
+
"sliding_attention",
|
| 240 |
+
"sliding_attention",
|
| 241 |
+
"sliding_attention",
|
| 242 |
+
"full_attention",
|
| 243 |
+
"sliding_attention",
|
| 244 |
+
"sliding_attention",
|
| 245 |
+
"sliding_attention",
|
| 246 |
+
"sliding_attention",
|
| 247 |
+
"sliding_attention",
|
| 248 |
+
"full_attention",
|
| 249 |
+
"sliding_attention",
|
| 250 |
+
"sliding_attention",
|
| 251 |
+
"sliding_attention",
|
| 252 |
+
"sliding_attention",
|
| 253 |
+
"sliding_attention",
|
| 254 |
+
"full_attention",
|
| 255 |
+
"sliding_attention",
|
| 256 |
+
"sliding_attention",
|
| 257 |
+
"sliding_attention",
|
| 258 |
+
"sliding_attention",
|
| 259 |
+
"sliding_attention",
|
| 260 |
+
"full_attention",
|
| 261 |
+
"sliding_attention",
|
| 262 |
+
"sliding_attention",
|
| 263 |
+
"sliding_attention",
|
| 264 |
+
"sliding_attention",
|
| 265 |
+
"sliding_attention",
|
| 266 |
+
"full_attention",
|
| 267 |
+
"sliding_attention",
|
| 268 |
+
"sliding_attention",
|
| 269 |
+
"sliding_attention",
|
| 270 |
+
"sliding_attention"
|
| 271 |
+
],
|
| 272 |
"max_position_embeddings": 131072,
|
| 273 |
"model_type": "gemma3_text",
|
| 274 |
"num_attention_heads": 8,
|
|
|
|
| 284 |
"rope_theta": 1000000.0,
|
| 285 |
"sliding_window": 1024,
|
| 286 |
"sliding_window_pattern": 6,
|
| 287 |
+
"use_bidirectional_attention": false,
|
| 288 |
"use_cache": true,
|
| 289 |
"vocab_size": 262208
|
| 290 |
},
|
| 291 |
+
"transformers_version": "4.57.1",
|
| 292 |
+
"unsloth_fixed": true,
|
| 293 |
"vision_config": {
|
| 294 |
"attention_dropout": 0.0,
|
| 295 |
+
"dtype": "bfloat16",
|
| 296 |
"hidden_act": "gelu_pytorch_tanh",
|
| 297 |
"hidden_size": 1152,
|
| 298 |
"image_size": 896,
|