Upload folder using huggingface_hub
Browse files- config.json +151 -3
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +25 -172
- recipe.yaml +6 -0
- tokenizer.json +0 -0
config.json
CHANGED
|
@@ -37,8 +37,156 @@
|
|
| 37 |
}
|
| 38 |
},
|
| 39 |
"format": "float-quantized",
|
| 40 |
-
"global_compression_ratio": 1.
|
| 41 |
-
"ignore": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
"kv_cache_scheme": null,
|
| 43 |
"quant_method": "compressed-tensors",
|
| 44 |
"quantization_status": "compressed"
|
|
@@ -134,7 +282,7 @@
|
|
| 134 |
},
|
| 135 |
"tie_word_embeddings": false,
|
| 136 |
"torch_dtype": "float16",
|
| 137 |
-
"transformers_version": "4.
|
| 138 |
"vision_config": {
|
| 139 |
"_name_or_path": "",
|
| 140 |
"add_cross_attention": false,
|
|
|
|
| 37 |
}
|
| 38 |
},
|
| 39 |
"format": "float-quantized",
|
| 40 |
+
"global_compression_ratio": 1.1620658104955142,
|
| 41 |
+
"ignore": [
|
| 42 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
|
| 43 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
|
| 44 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj",
|
| 45 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj",
|
| 46 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1",
|
| 47 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2",
|
| 48 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
|
| 49 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
|
| 50 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
|
| 51 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
|
| 52 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1",
|
| 53 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2",
|
| 54 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
|
| 55 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
|
| 56 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
|
| 57 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
|
| 58 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1",
|
| 59 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2",
|
| 60 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
|
| 61 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
|
| 62 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
|
| 63 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj",
|
| 64 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1",
|
| 65 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2",
|
| 66 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
|
| 67 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
|
| 68 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
|
| 69 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
|
| 70 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1",
|
| 71 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2",
|
| 72 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
|
| 73 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj",
|
| 74 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
|
| 75 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
|
| 76 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1",
|
| 77 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2",
|
| 78 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
|
| 79 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
|
| 80 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
|
| 81 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
|
| 82 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1",
|
| 83 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2",
|
| 84 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
|
| 85 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj",
|
| 86 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
|
| 87 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
|
| 88 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1",
|
| 89 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2",
|
| 90 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
|
| 91 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
|
| 92 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
|
| 93 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
|
| 94 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1",
|
| 95 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2",
|
| 96 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
|
| 97 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
|
| 98 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
|
| 99 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj",
|
| 100 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1",
|
| 101 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2",
|
| 102 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
|
| 103 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
|
| 104 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
|
| 105 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
|
| 106 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1",
|
| 107 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2",
|
| 108 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
|
| 109 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
|
| 110 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
|
| 111 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
|
| 112 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1",
|
| 113 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2",
|
| 114 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
|
| 115 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
|
| 116 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
|
| 117 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
|
| 118 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1",
|
| 119 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2",
|
| 120 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
|
| 121 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
|
| 122 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
|
| 123 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj",
|
| 124 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1",
|
| 125 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2",
|
| 126 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
|
| 127 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
|
| 128 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
|
| 129 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
|
| 130 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1",
|
| 131 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2",
|
| 132 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
|
| 133 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj",
|
| 134 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
|
| 135 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
|
| 136 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1",
|
| 137 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2",
|
| 138 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
|
| 139 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
|
| 140 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
|
| 141 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
|
| 142 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1",
|
| 143 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2",
|
| 144 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
|
| 145 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
|
| 146 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
|
| 147 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
|
| 148 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1",
|
| 149 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2",
|
| 150 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
|
| 151 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
|
| 152 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
|
| 153 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
|
| 154 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1",
|
| 155 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2",
|
| 156 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
|
| 157 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
|
| 158 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
|
| 159 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
|
| 160 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1",
|
| 161 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2",
|
| 162 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
|
| 163 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
|
| 164 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj",
|
| 165 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
|
| 166 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1",
|
| 167 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2",
|
| 168 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
|
| 169 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
|
| 170 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
|
| 171 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
|
| 172 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1",
|
| 173 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2",
|
| 174 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
|
| 175 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
|
| 176 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
|
| 177 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
|
| 178 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1",
|
| 179 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2",
|
| 180 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
|
| 181 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
|
| 182 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
|
| 183 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
|
| 184 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1",
|
| 185 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2",
|
| 186 |
+
"multi_modal_projector.linear_1",
|
| 187 |
+
"multi_modal_projector.linear_2",
|
| 188 |
+
"language_model.lm_head"
|
| 189 |
+
],
|
| 190 |
"kv_cache_scheme": null,
|
| 191 |
"quant_method": "compressed-tensors",
|
| 192 |
"quantization_status": "compressed"
|
|
|
|
| 282 |
},
|
| 283 |
"tie_word_embeddings": false,
|
| 284 |
"torch_dtype": "float16",
|
| 285 |
+
"transformers_version": "4.46.0.dev0",
|
| 286 |
"vision_config": {
|
| 287 |
"_name_or_path": "",
|
| 288 |
"add_cross_attention": false,
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 32001,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 32001,
|
| 6 |
+
"transformers_version": "4.46.0.dev0"
|
| 7 |
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:268d76718ad56c78a82041d6900aeb6f1433d1f1ad2bb8ec699db2ea245fe82f
|
| 3 |
+
size 4994840528
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1338d095934f809f61e79222634dfcaea711aa6fe2b6492d0fa7f709ad301125
|
| 3 |
+
size 2658849328
|
model.safetensors.index.json
CHANGED
|
@@ -1,10 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"language_model.lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
-
"language_model.lm_head.weight_scale": "model-00002-of-00002.safetensors",
|
| 8 |
"language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -214,38 +213,38 @@
|
|
| 214 |
"language_model.model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 215 |
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
"language_model.model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 217 |
-
"language_model.model.layers.20.input_layernorm.weight": "model-
|
| 218 |
-
"language_model.model.layers.20.mlp.down_proj.weight": "model-
|
| 219 |
-
"language_model.model.layers.20.mlp.down_proj.weight_scale": "model-
|
| 220 |
-
"language_model.model.layers.20.mlp.gate_proj.weight": "model-
|
| 221 |
-
"language_model.model.layers.20.mlp.gate_proj.weight_scale": "model-
|
| 222 |
-
"language_model.model.layers.20.mlp.up_proj.weight": "model-
|
| 223 |
-
"language_model.model.layers.20.mlp.up_proj.weight_scale": "model-
|
| 224 |
-
"language_model.model.layers.20.post_attention_layernorm.weight": "model-
|
| 225 |
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
"language_model.model.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 227 |
-
"language_model.model.layers.20.self_attn.o_proj.weight": "model-
|
| 228 |
-
"language_model.model.layers.20.self_attn.o_proj.weight_scale": "model-
|
| 229 |
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
"language_model.model.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 231 |
-
"language_model.model.layers.20.self_attn.v_proj.weight": "model-
|
| 232 |
-
"language_model.model.layers.20.self_attn.v_proj.weight_scale": "model-
|
| 233 |
"language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
"language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
"language_model.model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 236 |
-
"language_model.model.layers.21.mlp.gate_proj.weight": "model-
|
| 237 |
-
"language_model.model.layers.21.mlp.gate_proj.weight_scale": "model-
|
| 238 |
-
"language_model.model.layers.21.mlp.up_proj.weight": "model-
|
| 239 |
-
"language_model.model.layers.21.mlp.up_proj.weight_scale": "model-
|
| 240 |
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
-
"language_model.model.layers.21.self_attn.k_proj.weight": "model-
|
| 242 |
-
"language_model.model.layers.21.self_attn.k_proj.weight_scale": "model-
|
| 243 |
-
"language_model.model.layers.21.self_attn.o_proj.weight": "model-
|
| 244 |
-
"language_model.model.layers.21.self_attn.o_proj.weight_scale": "model-
|
| 245 |
-
"language_model.model.layers.21.self_attn.q_proj.weight": "model-
|
| 246 |
-
"language_model.model.layers.21.self_attn.q_proj.weight_scale": "model-
|
| 247 |
-
"language_model.model.layers.21.self_attn.v_proj.weight": "model-
|
| 248 |
-
"language_model.model.layers.21.self_attn.v_proj.weight_scale": "model-
|
| 249 |
"language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 250 |
"language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
"language_model.model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
|
@@ -521,10 +520,8 @@
|
|
| 521 |
"language_model.model.norm.weight": "model-00002-of-00002.safetensors",
|
| 522 |
"multi_modal_projector.linear_1.bias": "model-00001-of-00002.safetensors",
|
| 523 |
"multi_modal_projector.linear_1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
-
"multi_modal_projector.linear_1.weight_scale": "model-00001-of-00002.safetensors",
|
| 525 |
"multi_modal_projector.linear_2.bias": "model-00001-of-00002.safetensors",
|
| 526 |
"multi_modal_projector.linear_2.weight": "model-00001-of-00002.safetensors",
|
| 527 |
-
"multi_modal_projector.linear_2.weight_scale": "model-00001-of-00002.safetensors",
|
| 528 |
"vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00002.safetensors",
|
| 529 |
"vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
|
| 530 |
"vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
|
|
@@ -534,528 +531,384 @@
|
|
| 534 |
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 535 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 536 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 537 |
-
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 538 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 539 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 540 |
-
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 541 |
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 542 |
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 543 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 544 |
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 547 |
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 548 |
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 549 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 550 |
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 551 |
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 552 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 553 |
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 554 |
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 555 |
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 556 |
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 557 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 558 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 559 |
-
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 560 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 561 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 562 |
-
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 563 |
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 564 |
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 565 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 566 |
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 567 |
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 568 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 569 |
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 570 |
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 571 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 572 |
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 573 |
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 574 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 575 |
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 576 |
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 577 |
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 578 |
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 579 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 580 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 581 |
-
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 582 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 583 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 584 |
-
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 585 |
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 586 |
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 587 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 588 |
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 589 |
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 590 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 591 |
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 592 |
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 593 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 594 |
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 595 |
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 596 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 597 |
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 598 |
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 599 |
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 600 |
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 601 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 602 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 603 |
-
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 604 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 605 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 606 |
-
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 607 |
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 608 |
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 609 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 610 |
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 611 |
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 612 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 613 |
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 614 |
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 615 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 616 |
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 617 |
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 618 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 619 |
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 620 |
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 621 |
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 622 |
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 623 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 624 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 625 |
-
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 626 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 627 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 628 |
-
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 629 |
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 630 |
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 631 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 632 |
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 633 |
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 634 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 635 |
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 636 |
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 637 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 638 |
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 641 |
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 642 |
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 643 |
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 644 |
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 645 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 646 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 647 |
-
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 648 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 649 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 650 |
-
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 651 |
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 652 |
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 653 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 654 |
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 655 |
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 656 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 657 |
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 658 |
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 659 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 660 |
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 661 |
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 663 |
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 664 |
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 665 |
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 666 |
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 667 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 668 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 669 |
-
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 670 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 671 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 672 |
-
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 673 |
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 674 |
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 675 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 676 |
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 677 |
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 679 |
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 680 |
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 681 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 682 |
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 683 |
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 684 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 685 |
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 686 |
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 687 |
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 688 |
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 689 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 690 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 691 |
-
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 692 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 693 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 694 |
-
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 695 |
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 696 |
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 697 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 698 |
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 699 |
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 700 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 701 |
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 702 |
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 703 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 704 |
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 705 |
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 706 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 707 |
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 708 |
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 709 |
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 710 |
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 711 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 712 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 713 |
-
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 714 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 715 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 716 |
-
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 717 |
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 718 |
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 719 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 720 |
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 721 |
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 722 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 723 |
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 724 |
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 725 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 726 |
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 727 |
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 728 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 729 |
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 730 |
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 731 |
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 732 |
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 733 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 734 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 735 |
-
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 736 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 737 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 738 |
-
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 739 |
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 740 |
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 741 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 742 |
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 743 |
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 744 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 745 |
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 746 |
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 747 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 748 |
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 749 |
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 750 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 751 |
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 752 |
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 753 |
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 754 |
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 755 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 756 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 757 |
-
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 758 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 759 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 760 |
-
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 761 |
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 762 |
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 763 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 764 |
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 765 |
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 766 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 767 |
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 768 |
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 769 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 770 |
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 771 |
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 772 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 773 |
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 774 |
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 775 |
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 776 |
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 777 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 778 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 779 |
-
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 780 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 781 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 782 |
-
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 783 |
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 784 |
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 785 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 786 |
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 787 |
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 788 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 789 |
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 790 |
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 791 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 792 |
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 793 |
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 794 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 795 |
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 796 |
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 797 |
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 798 |
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 799 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 800 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 801 |
-
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 802 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 803 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 804 |
-
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 805 |
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 806 |
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 807 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 808 |
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 809 |
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 810 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 811 |
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 812 |
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 813 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 814 |
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 815 |
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 816 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 817 |
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 818 |
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 819 |
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 820 |
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 821 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 822 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 823 |
-
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 824 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 825 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 826 |
-
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 827 |
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 828 |
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 829 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 830 |
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 831 |
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 832 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 833 |
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 834 |
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 835 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 836 |
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 837 |
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 838 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 839 |
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 840 |
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 841 |
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 842 |
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 843 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 844 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 845 |
-
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 846 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 847 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 848 |
-
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 849 |
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 850 |
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 851 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 852 |
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 853 |
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 854 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 855 |
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 856 |
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 857 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 858 |
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 859 |
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 860 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 861 |
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 862 |
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 863 |
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 864 |
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 865 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 866 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 867 |
-
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 868 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 869 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 870 |
-
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 871 |
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 872 |
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 873 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 874 |
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 875 |
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 876 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 877 |
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 878 |
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 879 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 880 |
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 881 |
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 882 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 883 |
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 884 |
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 885 |
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 886 |
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 887 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 888 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 889 |
-
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 890 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 891 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 892 |
-
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 893 |
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 894 |
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 895 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 896 |
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 897 |
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 898 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 899 |
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 900 |
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 901 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 902 |
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 903 |
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 904 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 905 |
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 906 |
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 907 |
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 908 |
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 909 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 910 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 911 |
-
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 912 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 913 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 914 |
-
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 915 |
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 916 |
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 917 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 918 |
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 919 |
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 920 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 921 |
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 922 |
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 923 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 924 |
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 925 |
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 926 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 927 |
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 928 |
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 929 |
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 930 |
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 931 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 932 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 933 |
-
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 934 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 935 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 936 |
-
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 937 |
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 938 |
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 939 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 940 |
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 941 |
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 942 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 943 |
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 944 |
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 945 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 946 |
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 947 |
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 948 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 949 |
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 950 |
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 951 |
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 952 |
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 953 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 954 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 955 |
-
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 956 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 957 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 958 |
-
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 959 |
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 960 |
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 961 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 962 |
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 963 |
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 964 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 965 |
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 966 |
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 967 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 968 |
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 969 |
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 970 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 971 |
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 972 |
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 973 |
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 974 |
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 975 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 976 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 977 |
-
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 978 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 979 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 980 |
-
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 981 |
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 982 |
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 983 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 984 |
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 985 |
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 986 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 987 |
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 988 |
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 989 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 990 |
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 991 |
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 992 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 993 |
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 994 |
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 995 |
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 996 |
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 997 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 998 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 999 |
-
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 1000 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 1001 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 1002 |
-
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 1003 |
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 1004 |
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 1005 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1006 |
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 1007 |
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 1008 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1009 |
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 1010 |
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 1011 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1012 |
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 1013 |
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 1014 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1015 |
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 1016 |
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 1017 |
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 1018 |
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 1019 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 1020 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 1021 |
-
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 1022 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 1023 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 1024 |
-
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 1025 |
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 1026 |
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 1027 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1028 |
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 1029 |
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 1030 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1031 |
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 1032 |
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 1033 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1034 |
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 1035 |
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 1036 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1037 |
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 1038 |
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 1039 |
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 1040 |
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 1041 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 1042 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 1043 |
-
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight_scale": "model-00001-of-00002.safetensors",
|
| 1044 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 1045 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 1046 |
-
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight_scale": "model-00001-of-00002.safetensors",
|
| 1047 |
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 1048 |
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 1049 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1050 |
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 1051 |
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 1052 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1053 |
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 1054 |
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 1055 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1056 |
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 1057 |
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 1058 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1059 |
"vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 1060 |
"vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1061 |
"vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00002.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 7653568512
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"language_model.lm_head.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 7 |
"language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 213 |
"language_model.model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 214 |
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
"language_model.model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 216 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"language_model.model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 219 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"language_model.model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 221 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"language_model.model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 223 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
"language_model.model.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 226 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"language_model.model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 228 |
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
"language_model.model.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 230 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"language_model.model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 232 |
"language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
"language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
"language_model.model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 235 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"language_model.model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 237 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"language_model.model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 239 |
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"language_model.model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 242 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"language_model.model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 244 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"language_model.model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 246 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"language_model.model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 248 |
"language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
"language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
"language_model.model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
|
|
|
| 520 |
"language_model.model.norm.weight": "model-00002-of-00002.safetensors",
|
| 521 |
"multi_modal_projector.linear_1.bias": "model-00001-of-00002.safetensors",
|
| 522 |
"multi_modal_projector.linear_1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 523 |
"multi_modal_projector.linear_2.bias": "model-00001-of-00002.safetensors",
|
| 524 |
"multi_modal_projector.linear_2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 525 |
"vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00002.safetensors",
|
| 526 |
"vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
|
| 527 |
"vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 531 |
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 532 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 533 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 534 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 535 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 536 |
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 537 |
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 538 |
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 539 |
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 540 |
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 541 |
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 542 |
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 543 |
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 544 |
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 545 |
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 546 |
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 547 |
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 548 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 549 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 550 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 551 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 552 |
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 553 |
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 554 |
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 555 |
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 556 |
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 557 |
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 558 |
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 559 |
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 560 |
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 561 |
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 562 |
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 563 |
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 564 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 565 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 566 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 567 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 568 |
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 569 |
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 570 |
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 571 |
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 572 |
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 573 |
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 574 |
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 575 |
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 576 |
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 577 |
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 578 |
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 579 |
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 580 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 581 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 582 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 583 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 584 |
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 585 |
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 586 |
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 587 |
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 588 |
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 589 |
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 590 |
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 592 |
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 593 |
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 594 |
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 595 |
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 596 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 597 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 598 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 599 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 600 |
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 601 |
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 602 |
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 603 |
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 604 |
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 605 |
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 606 |
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 607 |
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 608 |
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 609 |
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 610 |
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 611 |
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 612 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 613 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 614 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 615 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 616 |
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 617 |
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 618 |
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 619 |
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 620 |
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 621 |
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 622 |
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 623 |
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 624 |
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 625 |
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 626 |
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 627 |
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 628 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 629 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 630 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 631 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 632 |
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 633 |
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 634 |
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 635 |
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 636 |
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 637 |
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 638 |
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 640 |
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 641 |
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 642 |
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 643 |
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 644 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 645 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 646 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 647 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 648 |
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 649 |
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 650 |
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 651 |
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 652 |
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 653 |
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 654 |
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 655 |
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 656 |
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 657 |
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 658 |
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 659 |
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 660 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 661 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 662 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 663 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 664 |
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 665 |
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 666 |
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 667 |
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 668 |
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 669 |
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 670 |
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 671 |
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 672 |
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 673 |
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 674 |
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 675 |
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 676 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 677 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 678 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 679 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 680 |
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 681 |
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 682 |
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 683 |
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 684 |
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 685 |
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 686 |
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 687 |
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 688 |
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 689 |
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 690 |
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 691 |
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 692 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 693 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 694 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 695 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 696 |
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 697 |
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 698 |
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 699 |
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 700 |
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 701 |
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 702 |
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 703 |
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 704 |
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 705 |
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 706 |
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 707 |
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 708 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 709 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 710 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 711 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 712 |
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 713 |
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 714 |
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 715 |
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 716 |
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 717 |
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 718 |
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 719 |
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 720 |
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 721 |
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 722 |
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 723 |
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 724 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 725 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 726 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 727 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 728 |
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 729 |
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 730 |
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 731 |
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 732 |
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 733 |
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 734 |
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 735 |
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 736 |
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 737 |
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 738 |
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 739 |
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 740 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 741 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 742 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 743 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 744 |
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 745 |
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 746 |
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 747 |
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 748 |
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 749 |
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 750 |
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 751 |
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 752 |
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 753 |
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 754 |
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 755 |
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 756 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 757 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 758 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 759 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 760 |
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 761 |
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 762 |
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 763 |
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 764 |
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 765 |
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 766 |
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 767 |
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 768 |
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 769 |
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 770 |
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 771 |
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 772 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 773 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 774 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 775 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 776 |
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 777 |
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 778 |
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 779 |
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 780 |
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 781 |
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 782 |
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 783 |
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 784 |
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 785 |
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 786 |
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 787 |
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 788 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 789 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 790 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 791 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 792 |
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 793 |
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 794 |
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 795 |
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 796 |
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 797 |
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 798 |
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 799 |
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 800 |
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 801 |
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 802 |
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 803 |
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 804 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 805 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 806 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 807 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 808 |
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 809 |
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 810 |
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 811 |
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 812 |
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 813 |
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 814 |
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 815 |
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 816 |
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 817 |
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 818 |
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 819 |
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 820 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 821 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 822 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 823 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 824 |
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 825 |
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 826 |
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 827 |
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 828 |
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 829 |
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 830 |
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 831 |
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 832 |
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 833 |
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 834 |
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 835 |
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 836 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 837 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 838 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 839 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 840 |
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 841 |
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 842 |
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 843 |
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 844 |
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 845 |
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 846 |
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 847 |
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 848 |
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 849 |
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 850 |
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 851 |
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 852 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 853 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 854 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 855 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 856 |
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 857 |
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 858 |
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 859 |
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 860 |
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 861 |
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 862 |
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 863 |
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 864 |
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 865 |
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 866 |
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 867 |
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 868 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 869 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 870 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 871 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 872 |
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 873 |
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 874 |
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 875 |
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 876 |
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 877 |
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 878 |
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 879 |
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 880 |
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 881 |
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 882 |
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 883 |
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 884 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 885 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 886 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 887 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 888 |
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 889 |
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 890 |
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 891 |
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 892 |
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 893 |
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 894 |
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 895 |
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 896 |
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 897 |
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 898 |
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 899 |
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 900 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 901 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 902 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 903 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 904 |
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 905 |
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 906 |
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 907 |
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 908 |
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 909 |
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 910 |
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 911 |
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 912 |
"vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 913 |
"vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 914 |
"vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00002.safetensors",
|
recipe.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
DEFAULT_stage:
|
| 2 |
+
DEFAULT_modifiers:
|
| 3 |
+
QuantizationModifier:
|
| 4 |
+
ignore: ['re:.*lm_head', 're:multi_modal_projector.*', 're:vision_tower.*']
|
| 5 |
+
targets: Linear
|
| 6 |
+
scheme: FP8_DYNAMIC
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|