Upload folder using huggingface_hub
Browse files- config.json +0 -162
- model-00001-of-00008.safetensors +2 -2
- model-00002-of-00008.safetensors +2 -2
- model-00003-of-00008.safetensors +2 -2
- model-00004-of-00008.safetensors +2 -2
- model-00005-of-00008.safetensors +2 -2
- model-00006-of-00008.safetensors +2 -2
- model-00007-of-00008.safetensors +2 -2
- model.safetensors.index.json +289 -127
- recipe.yaml +1 -1
config.json
CHANGED
|
@@ -52,168 +52,6 @@
|
|
| 52 |
"format": "float-quantized",
|
| 53 |
"global_compression_ratio": null,
|
| 54 |
"ignore": [
|
| 55 |
-
"visual.blocks.0.attn.qkv",
|
| 56 |
-
"visual.blocks.0.attn.proj",
|
| 57 |
-
"visual.blocks.0.mlp.gate_proj",
|
| 58 |
-
"visual.blocks.0.mlp.up_proj",
|
| 59 |
-
"visual.blocks.0.mlp.down_proj",
|
| 60 |
-
"visual.blocks.1.attn.qkv",
|
| 61 |
-
"visual.blocks.1.attn.proj",
|
| 62 |
-
"visual.blocks.1.mlp.gate_proj",
|
| 63 |
-
"visual.blocks.1.mlp.up_proj",
|
| 64 |
-
"visual.blocks.1.mlp.down_proj",
|
| 65 |
-
"visual.blocks.2.attn.qkv",
|
| 66 |
-
"visual.blocks.2.attn.proj",
|
| 67 |
-
"visual.blocks.2.mlp.gate_proj",
|
| 68 |
-
"visual.blocks.2.mlp.up_proj",
|
| 69 |
-
"visual.blocks.2.mlp.down_proj",
|
| 70 |
-
"visual.blocks.3.attn.qkv",
|
| 71 |
-
"visual.blocks.3.attn.proj",
|
| 72 |
-
"visual.blocks.3.mlp.gate_proj",
|
| 73 |
-
"visual.blocks.3.mlp.up_proj",
|
| 74 |
-
"visual.blocks.3.mlp.down_proj",
|
| 75 |
-
"visual.blocks.4.attn.qkv",
|
| 76 |
-
"visual.blocks.4.attn.proj",
|
| 77 |
-
"visual.blocks.4.mlp.gate_proj",
|
| 78 |
-
"visual.blocks.4.mlp.up_proj",
|
| 79 |
-
"visual.blocks.4.mlp.down_proj",
|
| 80 |
-
"visual.blocks.5.attn.qkv",
|
| 81 |
-
"visual.blocks.5.attn.proj",
|
| 82 |
-
"visual.blocks.5.mlp.gate_proj",
|
| 83 |
-
"visual.blocks.5.mlp.up_proj",
|
| 84 |
-
"visual.blocks.5.mlp.down_proj",
|
| 85 |
-
"visual.blocks.6.attn.qkv",
|
| 86 |
-
"visual.blocks.6.attn.proj",
|
| 87 |
-
"visual.blocks.6.mlp.gate_proj",
|
| 88 |
-
"visual.blocks.6.mlp.up_proj",
|
| 89 |
-
"visual.blocks.6.mlp.down_proj",
|
| 90 |
-
"visual.blocks.7.attn.qkv",
|
| 91 |
-
"visual.blocks.7.attn.proj",
|
| 92 |
-
"visual.blocks.7.mlp.gate_proj",
|
| 93 |
-
"visual.blocks.7.mlp.up_proj",
|
| 94 |
-
"visual.blocks.7.mlp.down_proj",
|
| 95 |
-
"visual.blocks.8.attn.qkv",
|
| 96 |
-
"visual.blocks.8.attn.proj",
|
| 97 |
-
"visual.blocks.8.mlp.gate_proj",
|
| 98 |
-
"visual.blocks.8.mlp.up_proj",
|
| 99 |
-
"visual.blocks.8.mlp.down_proj",
|
| 100 |
-
"visual.blocks.9.attn.qkv",
|
| 101 |
-
"visual.blocks.9.attn.proj",
|
| 102 |
-
"visual.blocks.9.mlp.gate_proj",
|
| 103 |
-
"visual.blocks.9.mlp.up_proj",
|
| 104 |
-
"visual.blocks.9.mlp.down_proj",
|
| 105 |
-
"visual.blocks.10.attn.qkv",
|
| 106 |
-
"visual.blocks.10.attn.proj",
|
| 107 |
-
"visual.blocks.10.mlp.gate_proj",
|
| 108 |
-
"visual.blocks.10.mlp.up_proj",
|
| 109 |
-
"visual.blocks.10.mlp.down_proj",
|
| 110 |
-
"visual.blocks.11.attn.qkv",
|
| 111 |
-
"visual.blocks.11.attn.proj",
|
| 112 |
-
"visual.blocks.11.mlp.gate_proj",
|
| 113 |
-
"visual.blocks.11.mlp.up_proj",
|
| 114 |
-
"visual.blocks.11.mlp.down_proj",
|
| 115 |
-
"visual.blocks.12.attn.qkv",
|
| 116 |
-
"visual.blocks.12.attn.proj",
|
| 117 |
-
"visual.blocks.12.mlp.gate_proj",
|
| 118 |
-
"visual.blocks.12.mlp.up_proj",
|
| 119 |
-
"visual.blocks.12.mlp.down_proj",
|
| 120 |
-
"visual.blocks.13.attn.qkv",
|
| 121 |
-
"visual.blocks.13.attn.proj",
|
| 122 |
-
"visual.blocks.13.mlp.gate_proj",
|
| 123 |
-
"visual.blocks.13.mlp.up_proj",
|
| 124 |
-
"visual.blocks.13.mlp.down_proj",
|
| 125 |
-
"visual.blocks.14.attn.qkv",
|
| 126 |
-
"visual.blocks.14.attn.proj",
|
| 127 |
-
"visual.blocks.14.mlp.gate_proj",
|
| 128 |
-
"visual.blocks.14.mlp.up_proj",
|
| 129 |
-
"visual.blocks.14.mlp.down_proj",
|
| 130 |
-
"visual.blocks.15.attn.qkv",
|
| 131 |
-
"visual.blocks.15.attn.proj",
|
| 132 |
-
"visual.blocks.15.mlp.gate_proj",
|
| 133 |
-
"visual.blocks.15.mlp.up_proj",
|
| 134 |
-
"visual.blocks.15.mlp.down_proj",
|
| 135 |
-
"visual.blocks.16.attn.qkv",
|
| 136 |
-
"visual.blocks.16.attn.proj",
|
| 137 |
-
"visual.blocks.16.mlp.gate_proj",
|
| 138 |
-
"visual.blocks.16.mlp.up_proj",
|
| 139 |
-
"visual.blocks.16.mlp.down_proj",
|
| 140 |
-
"visual.blocks.17.attn.qkv",
|
| 141 |
-
"visual.blocks.17.attn.proj",
|
| 142 |
-
"visual.blocks.17.mlp.gate_proj",
|
| 143 |
-
"visual.blocks.17.mlp.up_proj",
|
| 144 |
-
"visual.blocks.17.mlp.down_proj",
|
| 145 |
-
"visual.blocks.18.attn.qkv",
|
| 146 |
-
"visual.blocks.18.attn.proj",
|
| 147 |
-
"visual.blocks.18.mlp.gate_proj",
|
| 148 |
-
"visual.blocks.18.mlp.up_proj",
|
| 149 |
-
"visual.blocks.18.mlp.down_proj",
|
| 150 |
-
"visual.blocks.19.attn.qkv",
|
| 151 |
-
"visual.blocks.19.attn.proj",
|
| 152 |
-
"visual.blocks.19.mlp.gate_proj",
|
| 153 |
-
"visual.blocks.19.mlp.up_proj",
|
| 154 |
-
"visual.blocks.19.mlp.down_proj",
|
| 155 |
-
"visual.blocks.20.attn.qkv",
|
| 156 |
-
"visual.blocks.20.attn.proj",
|
| 157 |
-
"visual.blocks.20.mlp.gate_proj",
|
| 158 |
-
"visual.blocks.20.mlp.up_proj",
|
| 159 |
-
"visual.blocks.20.mlp.down_proj",
|
| 160 |
-
"visual.blocks.21.attn.qkv",
|
| 161 |
-
"visual.blocks.21.attn.proj",
|
| 162 |
-
"visual.blocks.21.mlp.gate_proj",
|
| 163 |
-
"visual.blocks.21.mlp.up_proj",
|
| 164 |
-
"visual.blocks.21.mlp.down_proj",
|
| 165 |
-
"visual.blocks.22.attn.qkv",
|
| 166 |
-
"visual.blocks.22.attn.proj",
|
| 167 |
-
"visual.blocks.22.mlp.gate_proj",
|
| 168 |
-
"visual.blocks.22.mlp.up_proj",
|
| 169 |
-
"visual.blocks.22.mlp.down_proj",
|
| 170 |
-
"visual.blocks.23.attn.qkv",
|
| 171 |
-
"visual.blocks.23.attn.proj",
|
| 172 |
-
"visual.blocks.23.mlp.gate_proj",
|
| 173 |
-
"visual.blocks.23.mlp.up_proj",
|
| 174 |
-
"visual.blocks.23.mlp.down_proj",
|
| 175 |
-
"visual.blocks.24.attn.qkv",
|
| 176 |
-
"visual.blocks.24.attn.proj",
|
| 177 |
-
"visual.blocks.24.mlp.gate_proj",
|
| 178 |
-
"visual.blocks.24.mlp.up_proj",
|
| 179 |
-
"visual.blocks.24.mlp.down_proj",
|
| 180 |
-
"visual.blocks.25.attn.qkv",
|
| 181 |
-
"visual.blocks.25.attn.proj",
|
| 182 |
-
"visual.blocks.25.mlp.gate_proj",
|
| 183 |
-
"visual.blocks.25.mlp.up_proj",
|
| 184 |
-
"visual.blocks.25.mlp.down_proj",
|
| 185 |
-
"visual.blocks.26.attn.qkv",
|
| 186 |
-
"visual.blocks.26.attn.proj",
|
| 187 |
-
"visual.blocks.26.mlp.gate_proj",
|
| 188 |
-
"visual.blocks.26.mlp.up_proj",
|
| 189 |
-
"visual.blocks.26.mlp.down_proj",
|
| 190 |
-
"visual.blocks.27.attn.qkv",
|
| 191 |
-
"visual.blocks.27.attn.proj",
|
| 192 |
-
"visual.blocks.27.mlp.gate_proj",
|
| 193 |
-
"visual.blocks.27.mlp.up_proj",
|
| 194 |
-
"visual.blocks.27.mlp.down_proj",
|
| 195 |
-
"visual.blocks.28.attn.qkv",
|
| 196 |
-
"visual.blocks.28.attn.proj",
|
| 197 |
-
"visual.blocks.28.mlp.gate_proj",
|
| 198 |
-
"visual.blocks.28.mlp.up_proj",
|
| 199 |
-
"visual.blocks.28.mlp.down_proj",
|
| 200 |
-
"visual.blocks.29.attn.qkv",
|
| 201 |
-
"visual.blocks.29.attn.proj",
|
| 202 |
-
"visual.blocks.29.mlp.gate_proj",
|
| 203 |
-
"visual.blocks.29.mlp.up_proj",
|
| 204 |
-
"visual.blocks.29.mlp.down_proj",
|
| 205 |
-
"visual.blocks.30.attn.qkv",
|
| 206 |
-
"visual.blocks.30.attn.proj",
|
| 207 |
-
"visual.blocks.30.mlp.gate_proj",
|
| 208 |
-
"visual.blocks.30.mlp.up_proj",
|
| 209 |
-
"visual.blocks.30.mlp.down_proj",
|
| 210 |
-
"visual.blocks.31.attn.qkv",
|
| 211 |
-
"visual.blocks.31.attn.proj",
|
| 212 |
-
"visual.blocks.31.mlp.gate_proj",
|
| 213 |
-
"visual.blocks.31.mlp.up_proj",
|
| 214 |
-
"visual.blocks.31.mlp.down_proj",
|
| 215 |
-
"visual.merger.mlp.0",
|
| 216 |
-
"visual.merger.mlp.2",
|
| 217 |
"lm_head"
|
| 218 |
],
|
| 219 |
"kv_cache_scheme": null,
|
|
|
|
| 52 |
"format": "float-quantized",
|
| 53 |
"global_compression_ratio": null,
|
| 54 |
"ignore": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
"lm_head"
|
| 56 |
],
|
| 57 |
"kv_cache_scheme": null,
|
model-00001-of-00008.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 sha256:3531038d3ab1495875f5f036edcc59016fa42bb56e65f832c43ee793b5155372
|
| 3 |
+
size 4892355856
|
model-00002-of-00008.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 sha256:4487f44ec59f9008edbac2871f4f4daeb85f81f9eb6a4860343b96523bb78e4c
|
| 3 |
+
size 4877702136
|
model-00003-of-00008.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 sha256:726d4573ba37e78117f99ec61b23787b20df8d8ed4dd498cbd030879749ce35b
|
| 3 |
+
size 4877702224
|
model-00004-of-00008.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 sha256:1bebc333febad4b94a9a358735ef62143e6f013245dcb792f50736a20a300e6d
|
| 3 |
+
size 4877702224
|
model-00005-of-00008.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:b79dfd105f75b72744321a18e373052828983663ca3a04e9b8ce37793af66b14
|
| 3 |
+
size 4877702224
|
model-00006-of-00008.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 sha256:026fa97c113a3dd9479517f6873938f33c7055dbeb8f9c48fc0547f0f4c3e4ac
|
| 3 |
+
size 4877702224
|
model-00007-of-00008.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:d68e4c7628a12d706b467220083cc8b51d5fb1c5aaec855d8eec9c76bbb0e711
|
| 3 |
+
size 4185374296
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00008-of-00008.safetensors",
|
|
@@ -119,14 +119,14 @@
|
|
| 119 |
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 120 |
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 121 |
"model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 122 |
-
"model.layers.14.input_layernorm.weight": "model-
|
| 123 |
-
"model.layers.14.mlp.down_proj.weight": "model-
|
| 124 |
-
"model.layers.14.mlp.down_proj.weight_scale": "model-
|
| 125 |
-
"model.layers.14.mlp.gate_proj.weight": "model-
|
| 126 |
-
"model.layers.14.mlp.gate_proj.weight_scale": "model-
|
| 127 |
-
"model.layers.14.mlp.up_proj.weight": "model-
|
| 128 |
-
"model.layers.14.mlp.up_proj.weight_scale": "model-
|
| 129 |
-
"model.layers.14.post_attention_layernorm.weight": "model-
|
| 130 |
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 131 |
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 132 |
"model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors",
|
|
@@ -141,22 +141,22 @@
|
|
| 141 |
"model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 142 |
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
| 143 |
"model.layers.15.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 144 |
-
"model.layers.15.mlp.gate_proj.weight": "model-
|
| 145 |
-
"model.layers.15.mlp.gate_proj.weight_scale": "model-
|
| 146 |
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
| 147 |
"model.layers.15.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 148 |
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 149 |
-
"model.layers.15.self_attn.k_proj.bias": "model-
|
| 150 |
-
"model.layers.15.self_attn.k_proj.weight": "model-
|
| 151 |
-
"model.layers.15.self_attn.k_proj.weight_scale": "model-
|
| 152 |
-
"model.layers.15.self_attn.o_proj.weight": "model-
|
| 153 |
-
"model.layers.15.self_attn.o_proj.weight_scale": "model-
|
| 154 |
-
"model.layers.15.self_attn.q_proj.bias": "model-
|
| 155 |
-
"model.layers.15.self_attn.q_proj.weight": "model-
|
| 156 |
-
"model.layers.15.self_attn.q_proj.weight_scale": "model-
|
| 157 |
-
"model.layers.15.self_attn.v_proj.bias": "model-
|
| 158 |
-
"model.layers.15.self_attn.v_proj.weight": "model-
|
| 159 |
-
"model.layers.15.self_attn.v_proj.weight_scale": "model-
|
| 160 |
"model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 161 |
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
| 162 |
"model.layers.16.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors",
|
|
@@ -328,14 +328,14 @@
|
|
| 328 |
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 329 |
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 330 |
"model.layers.23.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 331 |
-
"model.layers.24.input_layernorm.weight": "model-
|
| 332 |
-
"model.layers.24.mlp.down_proj.weight": "model-
|
| 333 |
-
"model.layers.24.mlp.down_proj.weight_scale": "model-
|
| 334 |
-
"model.layers.24.mlp.gate_proj.weight": "model-
|
| 335 |
-
"model.layers.24.mlp.gate_proj.weight_scale": "model-
|
| 336 |
-
"model.layers.24.mlp.up_proj.weight": "model-
|
| 337 |
-
"model.layers.24.mlp.up_proj.weight_scale": "model-
|
| 338 |
-
"model.layers.24.post_attention_layernorm.weight": "model-
|
| 339 |
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 340 |
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 341 |
"model.layers.24.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors",
|
|
@@ -350,22 +350,22 @@
|
|
| 350 |
"model.layers.25.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 351 |
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
| 352 |
"model.layers.25.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 353 |
-
"model.layers.25.mlp.gate_proj.weight": "model-
|
| 354 |
-
"model.layers.25.mlp.gate_proj.weight_scale": "model-
|
| 355 |
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
| 356 |
"model.layers.25.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 357 |
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 358 |
-
"model.layers.25.self_attn.k_proj.bias": "model-
|
| 359 |
-
"model.layers.25.self_attn.k_proj.weight": "model-
|
| 360 |
-
"model.layers.25.self_attn.k_proj.weight_scale": "model-
|
| 361 |
-
"model.layers.25.self_attn.o_proj.weight": "model-
|
| 362 |
-
"model.layers.25.self_attn.o_proj.weight_scale": "model-
|
| 363 |
-
"model.layers.25.self_attn.q_proj.bias": "model-
|
| 364 |
-
"model.layers.25.self_attn.q_proj.weight": "model-
|
| 365 |
-
"model.layers.25.self_attn.q_proj.weight_scale": "model-
|
| 366 |
-
"model.layers.25.self_attn.v_proj.bias": "model-
|
| 367 |
-
"model.layers.25.self_attn.v_proj.weight": "model-
|
| 368 |
-
"model.layers.25.self_attn.v_proj.weight_scale": "model-
|
| 369 |
"model.layers.26.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 370 |
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
| 371 |
"model.layers.26.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors",
|
|
@@ -537,14 +537,14 @@
|
|
| 537 |
"model.layers.33.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 538 |
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 539 |
"model.layers.33.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 540 |
-
"model.layers.34.input_layernorm.weight": "model-
|
| 541 |
-
"model.layers.34.mlp.down_proj.weight": "model-
|
| 542 |
-
"model.layers.34.mlp.down_proj.weight_scale": "model-
|
| 543 |
-
"model.layers.34.mlp.gate_proj.weight": "model-
|
| 544 |
-
"model.layers.34.mlp.gate_proj.weight_scale": "model-
|
| 545 |
-
"model.layers.34.mlp.up_proj.weight": "model-
|
| 546 |
-
"model.layers.34.mlp.up_proj.weight_scale": "model-
|
| 547 |
-
"model.layers.34.post_attention_layernorm.weight": "model-
|
| 548 |
"model.layers.34.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 549 |
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 550 |
"model.layers.34.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors",
|
|
@@ -559,22 +559,22 @@
|
|
| 559 |
"model.layers.35.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 560 |
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
| 561 |
"model.layers.35.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 562 |
-
"model.layers.35.mlp.gate_proj.weight": "model-
|
| 563 |
-
"model.layers.35.mlp.gate_proj.weight_scale": "model-
|
| 564 |
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
| 565 |
"model.layers.35.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 566 |
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 567 |
-
"model.layers.35.self_attn.k_proj.bias": "model-
|
| 568 |
-
"model.layers.35.self_attn.k_proj.weight": "model-
|
| 569 |
-
"model.layers.35.self_attn.k_proj.weight_scale": "model-
|
| 570 |
-
"model.layers.35.self_attn.o_proj.weight": "model-
|
| 571 |
-
"model.layers.35.self_attn.o_proj.weight_scale": "model-
|
| 572 |
-
"model.layers.35.self_attn.q_proj.bias": "model-
|
| 573 |
-
"model.layers.35.self_attn.q_proj.weight": "model-
|
| 574 |
-
"model.layers.35.self_attn.q_proj.weight_scale": "model-
|
| 575 |
-
"model.layers.35.self_attn.v_proj.bias": "model-
|
| 576 |
-
"model.layers.35.self_attn.v_proj.weight": "model-
|
| 577 |
-
"model.layers.35.self_attn.v_proj.weight_scale": "model-
|
| 578 |
"model.layers.36.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 579 |
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
| 580 |
"model.layers.36.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors",
|
|
@@ -651,14 +651,14 @@
|
|
| 651 |
"model.layers.39.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 652 |
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 653 |
"model.layers.39.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 654 |
-
"model.layers.4.input_layernorm.weight": "model-
|
| 655 |
-
"model.layers.4.mlp.down_proj.weight": "model-
|
| 656 |
-
"model.layers.4.mlp.down_proj.weight_scale": "model-
|
| 657 |
-
"model.layers.4.mlp.gate_proj.weight": "model-
|
| 658 |
-
"model.layers.4.mlp.gate_proj.weight_scale": "model-
|
| 659 |
-
"model.layers.4.mlp.up_proj.weight": "model-
|
| 660 |
-
"model.layers.4.mlp.up_proj.weight_scale": "model-
|
| 661 |
-
"model.layers.4.post_attention_layernorm.weight": "model-
|
| 662 |
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
| 663 |
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
| 664 |
"model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00008.safetensors",
|
|
@@ -746,14 +746,14 @@
|
|
| 746 |
"model.layers.43.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 747 |
"model.layers.43.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 748 |
"model.layers.43.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 749 |
-
"model.layers.44.input_layernorm.weight": "model-
|
| 750 |
-
"model.layers.44.mlp.down_proj.weight": "model-
|
| 751 |
-
"model.layers.44.mlp.down_proj.weight_scale": "model-
|
| 752 |
-
"model.layers.44.mlp.gate_proj.weight": "model-
|
| 753 |
-
"model.layers.44.mlp.gate_proj.weight_scale": "model-
|
| 754 |
-
"model.layers.44.mlp.up_proj.weight": "model-
|
| 755 |
-
"model.layers.44.mlp.up_proj.weight_scale": "model-
|
| 756 |
-
"model.layers.44.post_attention_layernorm.weight": "model-
|
| 757 |
"model.layers.44.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 758 |
"model.layers.44.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 759 |
"model.layers.44.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors",
|
|
@@ -768,22 +768,22 @@
|
|
| 768 |
"model.layers.45.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 769 |
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
| 770 |
"model.layers.45.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 771 |
-
"model.layers.45.mlp.gate_proj.weight": "model-
|
| 772 |
-
"model.layers.45.mlp.gate_proj.weight_scale": "model-
|
| 773 |
"model.layers.45.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
| 774 |
"model.layers.45.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 775 |
"model.layers.45.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 776 |
-
"model.layers.45.self_attn.k_proj.bias": "model-
|
| 777 |
-
"model.layers.45.self_attn.k_proj.weight": "model-
|
| 778 |
-
"model.layers.45.self_attn.k_proj.weight_scale": "model-
|
| 779 |
-
"model.layers.45.self_attn.o_proj.weight": "model-
|
| 780 |
-
"model.layers.45.self_attn.o_proj.weight_scale": "model-
|
| 781 |
-
"model.layers.45.self_attn.q_proj.bias": "model-
|
| 782 |
-
"model.layers.45.self_attn.q_proj.weight": "model-
|
| 783 |
-
"model.layers.45.self_attn.q_proj.weight_scale": "model-
|
| 784 |
-
"model.layers.45.self_attn.v_proj.bias": "model-
|
| 785 |
-
"model.layers.45.self_attn.v_proj.weight": "model-
|
| 786 |
-
"model.layers.45.self_attn.v_proj.weight_scale": "model-
|
| 787 |
"model.layers.46.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 788 |
"model.layers.46.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
| 789 |
"model.layers.46.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors",
|
|
@@ -863,22 +863,22 @@
|
|
| 863 |
"model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 864 |
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
| 865 |
"model.layers.5.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 866 |
-
"model.layers.5.mlp.gate_proj.weight": "model-
|
| 867 |
-
"model.layers.5.mlp.gate_proj.weight_scale": "model-
|
| 868 |
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
| 869 |
"model.layers.5.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 870 |
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 871 |
-
"model.layers.5.self_attn.k_proj.bias": "model-
|
| 872 |
-
"model.layers.5.self_attn.k_proj.weight": "model-
|
| 873 |
-
"model.layers.5.self_attn.k_proj.weight_scale": "model-
|
| 874 |
-
"model.layers.5.self_attn.o_proj.weight": "model-
|
| 875 |
-
"model.layers.5.self_attn.o_proj.weight_scale": "model-
|
| 876 |
-
"model.layers.5.self_attn.q_proj.bias": "model-
|
| 877 |
-
"model.layers.5.self_attn.q_proj.weight": "model-
|
| 878 |
-
"model.layers.5.self_attn.q_proj.weight_scale": "model-
|
| 879 |
-
"model.layers.5.self_attn.v_proj.bias": "model-
|
| 880 |
-
"model.layers.5.self_attn.v_proj.weight": "model-
|
| 881 |
-
"model.layers.5.self_attn.v_proj.weight_scale": "model-
|
| 882 |
"model.layers.50.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 883 |
"model.layers.50.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
| 884 |
"model.layers.50.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors",
|
|
@@ -955,14 +955,14 @@
|
|
| 955 |
"model.layers.53.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
| 956 |
"model.layers.53.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
| 957 |
"model.layers.53.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 958 |
-
"model.layers.54.input_layernorm.weight": "model-
|
| 959 |
-
"model.layers.54.mlp.down_proj.weight": "model-
|
| 960 |
-
"model.layers.54.mlp.down_proj.weight_scale": "model-
|
| 961 |
-
"model.layers.54.mlp.gate_proj.weight": "model-
|
| 962 |
-
"model.layers.54.mlp.gate_proj.weight_scale": "model-
|
| 963 |
-
"model.layers.54.mlp.up_proj.weight": "model-
|
| 964 |
-
"model.layers.54.mlp.up_proj.weight_scale": "model-
|
| 965 |
-
"model.layers.54.post_attention_layernorm.weight": "model-
|
| 966 |
"model.layers.54.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
| 967 |
"model.layers.54.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
| 968 |
"model.layers.54.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors",
|
|
@@ -977,22 +977,22 @@
|
|
| 977 |
"model.layers.55.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
| 978 |
"model.layers.55.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
| 979 |
"model.layers.55.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors",
|
| 980 |
-
"model.layers.55.mlp.gate_proj.weight": "model-
|
| 981 |
-
"model.layers.55.mlp.gate_proj.weight_scale": "model-
|
| 982 |
"model.layers.55.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
| 983 |
"model.layers.55.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors",
|
| 984 |
"model.layers.55.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
| 985 |
-
"model.layers.55.self_attn.k_proj.bias": "model-
|
| 986 |
-
"model.layers.55.self_attn.k_proj.weight": "model-
|
| 987 |
-
"model.layers.55.self_attn.k_proj.weight_scale": "model-
|
| 988 |
-
"model.layers.55.self_attn.o_proj.weight": "model-
|
| 989 |
-
"model.layers.55.self_attn.o_proj.weight_scale": "model-
|
| 990 |
-
"model.layers.55.self_attn.q_proj.bias": "model-
|
| 991 |
-
"model.layers.55.self_attn.q_proj.weight": "model-
|
| 992 |
-
"model.layers.55.self_attn.q_proj.weight_scale": "model-
|
| 993 |
-
"model.layers.55.self_attn.v_proj.bias": "model-
|
| 994 |
-
"model.layers.55.self_attn.v_proj.weight": "model-
|
| 995 |
-
"model.layers.55.self_attn.v_proj.weight_scale": "model-
|
| 996 |
"model.layers.56.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
| 997 |
"model.layers.56.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
| 998 |
"model.layers.56.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors",
|
|
@@ -1224,393 +1224,555 @@
|
|
| 1224 |
"model.norm.weight": "model-00007-of-00008.safetensors",
|
| 1225 |
"visual.blocks.0.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1226 |
"visual.blocks.0.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1227 |
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1228 |
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1229 |
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1230 |
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1231 |
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1232 |
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1233 |
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1234 |
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1235 |
"visual.blocks.0.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1236 |
"visual.blocks.0.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1237 |
"visual.blocks.1.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1238 |
"visual.blocks.1.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1239 |
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1240 |
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1241 |
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1242 |
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1243 |
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1244 |
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1245 |
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1246 |
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1247 |
"visual.blocks.1.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1248 |
"visual.blocks.1.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1249 |
"visual.blocks.10.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1250 |
"visual.blocks.10.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1251 |
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1252 |
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1253 |
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1254 |
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1255 |
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1256 |
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1257 |
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1258 |
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1259 |
"visual.blocks.10.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1260 |
"visual.blocks.10.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1261 |
"visual.blocks.11.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1262 |
"visual.blocks.11.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1263 |
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1264 |
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1265 |
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1266 |
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1267 |
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1268 |
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1269 |
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1270 |
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1271 |
"visual.blocks.11.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1272 |
"visual.blocks.11.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1273 |
"visual.blocks.12.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1274 |
"visual.blocks.12.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1275 |
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1276 |
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1277 |
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1278 |
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1279 |
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1280 |
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1281 |
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1282 |
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1283 |
"visual.blocks.12.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1284 |
"visual.blocks.12.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1285 |
"visual.blocks.13.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1286 |
"visual.blocks.13.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1287 |
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1288 |
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1289 |
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1290 |
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1291 |
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1292 |
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1293 |
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1294 |
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1295 |
"visual.blocks.13.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1296 |
"visual.blocks.13.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1297 |
"visual.blocks.14.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1298 |
"visual.blocks.14.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1299 |
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1300 |
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1301 |
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1302 |
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1303 |
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1304 |
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1305 |
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1306 |
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1307 |
"visual.blocks.14.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1308 |
"visual.blocks.14.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1309 |
"visual.blocks.15.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1310 |
"visual.blocks.15.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1311 |
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1312 |
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1313 |
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1314 |
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1315 |
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1316 |
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1317 |
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1318 |
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1319 |
"visual.blocks.15.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1320 |
"visual.blocks.15.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1321 |
"visual.blocks.16.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1322 |
"visual.blocks.16.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1323 |
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1324 |
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1325 |
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1326 |
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1327 |
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1328 |
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1329 |
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1330 |
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1331 |
"visual.blocks.16.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1332 |
"visual.blocks.16.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1333 |
"visual.blocks.17.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1334 |
"visual.blocks.17.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1335 |
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1336 |
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1337 |
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1338 |
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1339 |
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1340 |
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1341 |
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1342 |
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1343 |
"visual.blocks.17.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1344 |
"visual.blocks.17.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1345 |
"visual.blocks.18.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1346 |
"visual.blocks.18.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1347 |
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1348 |
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1349 |
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1350 |
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1351 |
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1352 |
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1353 |
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1354 |
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1355 |
"visual.blocks.18.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1356 |
"visual.blocks.18.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1357 |
"visual.blocks.19.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1358 |
"visual.blocks.19.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1359 |
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1360 |
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1361 |
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1362 |
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1363 |
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1364 |
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1365 |
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1366 |
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1367 |
"visual.blocks.19.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1368 |
"visual.blocks.19.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1369 |
"visual.blocks.2.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1370 |
"visual.blocks.2.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1371 |
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1372 |
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1373 |
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1374 |
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1375 |
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1376 |
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1377 |
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1378 |
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1379 |
"visual.blocks.2.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1380 |
"visual.blocks.2.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1381 |
"visual.blocks.20.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1382 |
"visual.blocks.20.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1383 |
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1384 |
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1385 |
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1386 |
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1387 |
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1388 |
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1389 |
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1390 |
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1391 |
"visual.blocks.20.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1392 |
"visual.blocks.20.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1393 |
"visual.blocks.21.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1394 |
"visual.blocks.21.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1395 |
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1396 |
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1397 |
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1398 |
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1399 |
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1400 |
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1401 |
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1402 |
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1403 |
"visual.blocks.21.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1404 |
"visual.blocks.21.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1405 |
"visual.blocks.22.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1406 |
"visual.blocks.22.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1407 |
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1408 |
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1409 |
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1410 |
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1411 |
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1412 |
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1413 |
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1414 |
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1415 |
"visual.blocks.22.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1416 |
"visual.blocks.22.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1417 |
"visual.blocks.23.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1418 |
"visual.blocks.23.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1419 |
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1420 |
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1421 |
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1422 |
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1423 |
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1424 |
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1425 |
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1426 |
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1427 |
"visual.blocks.23.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1428 |
"visual.blocks.23.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1429 |
"visual.blocks.24.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1430 |
"visual.blocks.24.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1431 |
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1432 |
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1433 |
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1434 |
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1435 |
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1436 |
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1437 |
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1438 |
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1439 |
"visual.blocks.24.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1440 |
"visual.blocks.24.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1441 |
"visual.blocks.25.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1442 |
"visual.blocks.25.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1443 |
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1444 |
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1445 |
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1446 |
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1447 |
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1448 |
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1449 |
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1450 |
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1451 |
"visual.blocks.25.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1452 |
"visual.blocks.25.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1453 |
"visual.blocks.26.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1454 |
"visual.blocks.26.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1455 |
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1456 |
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1457 |
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1458 |
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1459 |
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1460 |
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1461 |
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1462 |
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1463 |
"visual.blocks.26.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1464 |
"visual.blocks.26.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1465 |
"visual.blocks.27.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1466 |
"visual.blocks.27.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1467 |
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1468 |
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1469 |
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1470 |
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1471 |
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1472 |
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1473 |
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1474 |
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1475 |
"visual.blocks.27.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1476 |
"visual.blocks.27.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1477 |
"visual.blocks.28.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1478 |
"visual.blocks.28.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1479 |
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1480 |
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1481 |
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1482 |
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1483 |
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1484 |
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1485 |
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1486 |
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1487 |
"visual.blocks.28.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1488 |
"visual.blocks.28.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1489 |
"visual.blocks.29.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1490 |
"visual.blocks.29.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1491 |
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1492 |
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1493 |
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1494 |
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1495 |
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1496 |
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1497 |
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1498 |
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1499 |
"visual.blocks.29.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1500 |
"visual.blocks.29.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1501 |
"visual.blocks.3.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1502 |
"visual.blocks.3.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1503 |
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1504 |
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1505 |
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1506 |
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1507 |
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1508 |
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1509 |
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1510 |
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1511 |
"visual.blocks.3.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1512 |
"visual.blocks.3.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1513 |
"visual.blocks.30.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1514 |
"visual.blocks.30.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1515 |
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1516 |
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1517 |
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1518 |
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1519 |
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1520 |
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1521 |
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1522 |
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1523 |
"visual.blocks.30.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1524 |
"visual.blocks.30.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1525 |
"visual.blocks.31.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1526 |
"visual.blocks.31.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1527 |
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1528 |
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1529 |
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1530 |
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1531 |
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1532 |
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1533 |
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1534 |
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1535 |
"visual.blocks.31.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1536 |
"visual.blocks.31.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1537 |
"visual.blocks.4.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1538 |
"visual.blocks.4.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1539 |
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1540 |
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1541 |
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1542 |
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1543 |
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1544 |
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1545 |
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1546 |
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1547 |
"visual.blocks.4.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1548 |
"visual.blocks.4.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1549 |
"visual.blocks.5.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1550 |
"visual.blocks.5.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1551 |
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1552 |
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1553 |
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1554 |
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1555 |
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1556 |
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1557 |
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1558 |
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1559 |
"visual.blocks.5.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1560 |
"visual.blocks.5.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1561 |
"visual.blocks.6.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1562 |
"visual.blocks.6.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1563 |
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1564 |
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1565 |
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1566 |
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1567 |
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1568 |
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1569 |
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1570 |
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1571 |
"visual.blocks.6.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1572 |
"visual.blocks.6.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1573 |
"visual.blocks.7.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1574 |
"visual.blocks.7.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1575 |
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1576 |
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1577 |
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1578 |
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1579 |
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1580 |
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1581 |
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1582 |
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1583 |
"visual.blocks.7.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1584 |
"visual.blocks.7.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1585 |
"visual.blocks.8.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1586 |
"visual.blocks.8.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1587 |
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1588 |
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1589 |
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1590 |
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1591 |
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1592 |
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1593 |
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1594 |
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1595 |
"visual.blocks.8.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1596 |
"visual.blocks.8.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1597 |
"visual.blocks.9.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1598 |
"visual.blocks.9.attn.proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1599 |
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1600 |
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1601 |
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1602 |
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1603 |
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1604 |
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1605 |
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1606 |
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1607 |
"visual.blocks.9.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1608 |
"visual.blocks.9.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1609 |
"visual.merger.ln_q.weight": "model-00001-of-00008.safetensors",
|
| 1610 |
"visual.merger.mlp.0.bias": "model-00001-of-00008.safetensors",
|
| 1611 |
"visual.merger.mlp.0.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1612 |
"visual.merger.mlp.2.bias": "model-00001-of-00008.safetensors",
|
| 1613 |
"visual.merger.mlp.2.weight": "model-00001-of-00008.safetensors",
|
|
|
|
| 1614 |
"visual.patch_embed.proj.weight": "model-00001-of-00008.safetensors"
|
| 1615 |
}
|
| 1616 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 35023176192
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00008-of-00008.safetensors",
|
|
|
|
| 119 |
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 120 |
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 121 |
"model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 122 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 123 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
| 124 |
+
"model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 125 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
| 126 |
+
"model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 127 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
| 128 |
+
"model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 129 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 130 |
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 131 |
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 132 |
"model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors",
|
|
|
|
| 141 |
"model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 142 |
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
| 143 |
"model.layers.15.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 144 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
| 145 |
+
"model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 146 |
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
| 147 |
"model.layers.15.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 148 |
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 149 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 150 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 151 |
+
"model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 152 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 153 |
+
"model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 154 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 155 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 156 |
+
"model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 157 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 158 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 159 |
+
"model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 160 |
"model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 161 |
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
| 162 |
"model.layers.16.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors",
|
|
|
|
| 328 |
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 329 |
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 330 |
"model.layers.23.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 331 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 332 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
| 333 |
+
"model.layers.24.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 334 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
| 335 |
+
"model.layers.24.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 336 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
| 337 |
+
"model.layers.24.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 338 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 339 |
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 340 |
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 341 |
"model.layers.24.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors",
|
|
|
|
| 350 |
"model.layers.25.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 351 |
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
| 352 |
"model.layers.25.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 353 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
| 354 |
+
"model.layers.25.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 355 |
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
| 356 |
"model.layers.25.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 357 |
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 358 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 359 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 360 |
+
"model.layers.25.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 361 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
| 362 |
+
"model.layers.25.self_attn.o_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 363 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
| 364 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
| 365 |
+
"model.layers.25.self_attn.q_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 366 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 367 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 368 |
+
"model.layers.25.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors",
|
| 369 |
"model.layers.26.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 370 |
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
| 371 |
"model.layers.26.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors",
|
|
|
|
| 537 |
"model.layers.33.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 538 |
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 539 |
"model.layers.33.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 540 |
+
"model.layers.34.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 541 |
+
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
| 542 |
+
"model.layers.34.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 543 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
| 544 |
+
"model.layers.34.mlp.gate_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 545 |
+
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
| 546 |
+
"model.layers.34.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 547 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 548 |
"model.layers.34.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 549 |
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 550 |
"model.layers.34.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors",
|
|
|
|
| 559 |
"model.layers.35.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 560 |
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
| 561 |
"model.layers.35.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 562 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
| 563 |
+
"model.layers.35.mlp.gate_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 564 |
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
| 565 |
"model.layers.35.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 566 |
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 567 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 568 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 569 |
+
"model.layers.35.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 570 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
| 571 |
+
"model.layers.35.self_attn.o_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 572 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
| 573 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
| 574 |
+
"model.layers.35.self_attn.q_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 575 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 576 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 577 |
+
"model.layers.35.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors",
|
| 578 |
"model.layers.36.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 579 |
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
| 580 |
"model.layers.36.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors",
|
|
|
|
| 651 |
"model.layers.39.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 652 |
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 653 |
"model.layers.39.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 654 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
| 655 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 656 |
+
"model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 657 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 658 |
+
"model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 659 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 660 |
+
"model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 661 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
| 662 |
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
| 663 |
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
| 664 |
"model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00008.safetensors",
|
|
|
|
| 746 |
"model.layers.43.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 747 |
"model.layers.43.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 748 |
"model.layers.43.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 749 |
+
"model.layers.44.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 750 |
+
"model.layers.44.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
| 751 |
+
"model.layers.44.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 752 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
| 753 |
+
"model.layers.44.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 754 |
+
"model.layers.44.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
| 755 |
+
"model.layers.44.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 756 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 757 |
"model.layers.44.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 758 |
"model.layers.44.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 759 |
"model.layers.44.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors",
|
|
|
|
| 768 |
"model.layers.45.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 769 |
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
| 770 |
"model.layers.45.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 771 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
| 772 |
+
"model.layers.45.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 773 |
"model.layers.45.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
| 774 |
"model.layers.45.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 775 |
"model.layers.45.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 776 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 777 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 778 |
+
"model.layers.45.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 779 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
| 780 |
+
"model.layers.45.self_attn.o_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 781 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
| 782 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
| 783 |
+
"model.layers.45.self_attn.q_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 784 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 785 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 786 |
+
"model.layers.45.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors",
|
| 787 |
"model.layers.46.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 788 |
"model.layers.46.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
| 789 |
"model.layers.46.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors",
|
|
|
|
| 863 |
"model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 864 |
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
| 865 |
"model.layers.5.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 866 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 867 |
+
"model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 868 |
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
| 869 |
"model.layers.5.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors",
|
| 870 |
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 871 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
| 872 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
| 873 |
+
"model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 874 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
| 875 |
+
"model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 876 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
| 877 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
| 878 |
+
"model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 879 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
| 880 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
| 881 |
+
"model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 882 |
"model.layers.50.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 883 |
"model.layers.50.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
| 884 |
"model.layers.50.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors",
|
|
|
|
| 955 |
"model.layers.53.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
| 956 |
"model.layers.53.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
| 957 |
"model.layers.53.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 958 |
+
"model.layers.54.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 959 |
+
"model.layers.54.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
| 960 |
+
"model.layers.54.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 961 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
| 962 |
+
"model.layers.54.mlp.gate_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 963 |
+
"model.layers.54.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
| 964 |
+
"model.layers.54.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 965 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 966 |
"model.layers.54.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
| 967 |
"model.layers.54.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
| 968 |
"model.layers.54.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors",
|
|
|
|
| 977 |
"model.layers.55.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
| 978 |
"model.layers.55.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
| 979 |
"model.layers.55.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors",
|
| 980 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
| 981 |
+
"model.layers.55.mlp.gate_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 982 |
"model.layers.55.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
| 983 |
"model.layers.55.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors",
|
| 984 |
"model.layers.55.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
| 985 |
+
"model.layers.55.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
| 986 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
| 987 |
+
"model.layers.55.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 988 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
| 989 |
+
"model.layers.55.self_attn.o_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 990 |
+
"model.layers.55.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
| 991 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
| 992 |
+
"model.layers.55.self_attn.q_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 993 |
+
"model.layers.55.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
| 994 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
| 995 |
+
"model.layers.55.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors",
|
| 996 |
"model.layers.56.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
| 997 |
"model.layers.56.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
| 998 |
"model.layers.56.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors",
|
|
|
|
| 1224 |
"model.norm.weight": "model-00007-of-00008.safetensors",
|
| 1225 |
"visual.blocks.0.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1226 |
"visual.blocks.0.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1227 |
+
"visual.blocks.0.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1228 |
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1229 |
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1230 |
+
"visual.blocks.0.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1231 |
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1232 |
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1233 |
+
"visual.blocks.0.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1234 |
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1235 |
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1236 |
+
"visual.blocks.0.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1237 |
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1238 |
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1239 |
+
"visual.blocks.0.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1240 |
"visual.blocks.0.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1241 |
"visual.blocks.0.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1242 |
"visual.blocks.1.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1243 |
"visual.blocks.1.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1244 |
+
"visual.blocks.1.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1245 |
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1246 |
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1247 |
+
"visual.blocks.1.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1248 |
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1249 |
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1250 |
+
"visual.blocks.1.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1251 |
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1252 |
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1253 |
+
"visual.blocks.1.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1254 |
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1255 |
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1256 |
+
"visual.blocks.1.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1257 |
"visual.blocks.1.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1258 |
"visual.blocks.1.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1259 |
"visual.blocks.10.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1260 |
"visual.blocks.10.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1261 |
+
"visual.blocks.10.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1262 |
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1263 |
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1264 |
+
"visual.blocks.10.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1265 |
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1266 |
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1267 |
+
"visual.blocks.10.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1268 |
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1269 |
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1270 |
+
"visual.blocks.10.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1271 |
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1272 |
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1273 |
+
"visual.blocks.10.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1274 |
"visual.blocks.10.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1275 |
"visual.blocks.10.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1276 |
"visual.blocks.11.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1277 |
"visual.blocks.11.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1278 |
+
"visual.blocks.11.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1279 |
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1280 |
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1281 |
+
"visual.blocks.11.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1282 |
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1283 |
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1284 |
+
"visual.blocks.11.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1285 |
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1286 |
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1287 |
+
"visual.blocks.11.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1288 |
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1289 |
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1290 |
+
"visual.blocks.11.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1291 |
"visual.blocks.11.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1292 |
"visual.blocks.11.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1293 |
"visual.blocks.12.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1294 |
"visual.blocks.12.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1295 |
+
"visual.blocks.12.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1296 |
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1297 |
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1298 |
+
"visual.blocks.12.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1299 |
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1300 |
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1301 |
+
"visual.blocks.12.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1302 |
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1303 |
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1304 |
+
"visual.blocks.12.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1305 |
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1306 |
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1307 |
+
"visual.blocks.12.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1308 |
"visual.blocks.12.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1309 |
"visual.blocks.12.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1310 |
"visual.blocks.13.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1311 |
"visual.blocks.13.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1312 |
+
"visual.blocks.13.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1313 |
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1314 |
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1315 |
+
"visual.blocks.13.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1316 |
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1317 |
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1318 |
+
"visual.blocks.13.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1319 |
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1320 |
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1321 |
+
"visual.blocks.13.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1322 |
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1323 |
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1324 |
+
"visual.blocks.13.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1325 |
"visual.blocks.13.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1326 |
"visual.blocks.13.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1327 |
"visual.blocks.14.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1328 |
"visual.blocks.14.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1329 |
+
"visual.blocks.14.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1330 |
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1331 |
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1332 |
+
"visual.blocks.14.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1333 |
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1334 |
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1335 |
+
"visual.blocks.14.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1336 |
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1337 |
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1338 |
+
"visual.blocks.14.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1339 |
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1340 |
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1341 |
+
"visual.blocks.14.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1342 |
"visual.blocks.14.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1343 |
"visual.blocks.14.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1344 |
"visual.blocks.15.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1345 |
"visual.blocks.15.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1346 |
+
"visual.blocks.15.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1347 |
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1348 |
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1349 |
+
"visual.blocks.15.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1350 |
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1351 |
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1352 |
+
"visual.blocks.15.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1353 |
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1354 |
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1355 |
+
"visual.blocks.15.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1356 |
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1357 |
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1358 |
+
"visual.blocks.15.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1359 |
"visual.blocks.15.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1360 |
"visual.blocks.15.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1361 |
"visual.blocks.16.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1362 |
"visual.blocks.16.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1363 |
+
"visual.blocks.16.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1364 |
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1365 |
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1366 |
+
"visual.blocks.16.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1367 |
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1368 |
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1369 |
+
"visual.blocks.16.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1370 |
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1371 |
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1372 |
+
"visual.blocks.16.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1373 |
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1374 |
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1375 |
+
"visual.blocks.16.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1376 |
"visual.blocks.16.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1377 |
"visual.blocks.16.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1378 |
"visual.blocks.17.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1379 |
"visual.blocks.17.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1380 |
+
"visual.blocks.17.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1381 |
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1382 |
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1383 |
+
"visual.blocks.17.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1384 |
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1385 |
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1386 |
+
"visual.blocks.17.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1387 |
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1388 |
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1389 |
+
"visual.blocks.17.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1390 |
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1391 |
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1392 |
+
"visual.blocks.17.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1393 |
"visual.blocks.17.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1394 |
"visual.blocks.17.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1395 |
"visual.blocks.18.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1396 |
"visual.blocks.18.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1397 |
+
"visual.blocks.18.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1398 |
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1399 |
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1400 |
+
"visual.blocks.18.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1401 |
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1402 |
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1403 |
+
"visual.blocks.18.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1404 |
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1405 |
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1406 |
+
"visual.blocks.18.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1407 |
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1408 |
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1409 |
+
"visual.blocks.18.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1410 |
"visual.blocks.18.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1411 |
"visual.blocks.18.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1412 |
"visual.blocks.19.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1413 |
"visual.blocks.19.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1414 |
+
"visual.blocks.19.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1415 |
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1416 |
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1417 |
+
"visual.blocks.19.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1418 |
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1419 |
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1420 |
+
"visual.blocks.19.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1421 |
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1422 |
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1423 |
+
"visual.blocks.19.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1424 |
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1425 |
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1426 |
+
"visual.blocks.19.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1427 |
"visual.blocks.19.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1428 |
"visual.blocks.19.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1429 |
"visual.blocks.2.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1430 |
"visual.blocks.2.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1431 |
+
"visual.blocks.2.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1432 |
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1433 |
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1434 |
+
"visual.blocks.2.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1435 |
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1436 |
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1437 |
+
"visual.blocks.2.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1438 |
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1439 |
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1440 |
+
"visual.blocks.2.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1441 |
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1442 |
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1443 |
+
"visual.blocks.2.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1444 |
"visual.blocks.2.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1445 |
"visual.blocks.2.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1446 |
"visual.blocks.20.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1447 |
"visual.blocks.20.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1448 |
+
"visual.blocks.20.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1449 |
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1450 |
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1451 |
+
"visual.blocks.20.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1452 |
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1453 |
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1454 |
+
"visual.blocks.20.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1455 |
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1456 |
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1457 |
+
"visual.blocks.20.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1458 |
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1459 |
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1460 |
+
"visual.blocks.20.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1461 |
"visual.blocks.20.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1462 |
"visual.blocks.20.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1463 |
"visual.blocks.21.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1464 |
"visual.blocks.21.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1465 |
+
"visual.blocks.21.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1466 |
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1467 |
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1468 |
+
"visual.blocks.21.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1469 |
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1470 |
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1471 |
+
"visual.blocks.21.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1472 |
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1473 |
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1474 |
+
"visual.blocks.21.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1475 |
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1476 |
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1477 |
+
"visual.blocks.21.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1478 |
"visual.blocks.21.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1479 |
"visual.blocks.21.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1480 |
"visual.blocks.22.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1481 |
"visual.blocks.22.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1482 |
+
"visual.blocks.22.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1483 |
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1484 |
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1485 |
+
"visual.blocks.22.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1486 |
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1487 |
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1488 |
+
"visual.blocks.22.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1489 |
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1490 |
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1491 |
+
"visual.blocks.22.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1492 |
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1493 |
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1494 |
+
"visual.blocks.22.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1495 |
"visual.blocks.22.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1496 |
"visual.blocks.22.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1497 |
"visual.blocks.23.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1498 |
"visual.blocks.23.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1499 |
+
"visual.blocks.23.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1500 |
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1501 |
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1502 |
+
"visual.blocks.23.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1503 |
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1504 |
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1505 |
+
"visual.blocks.23.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1506 |
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1507 |
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1508 |
+
"visual.blocks.23.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1509 |
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1510 |
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1511 |
+
"visual.blocks.23.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1512 |
"visual.blocks.23.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1513 |
"visual.blocks.23.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1514 |
"visual.blocks.24.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1515 |
"visual.blocks.24.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1516 |
+
"visual.blocks.24.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1517 |
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1518 |
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1519 |
+
"visual.blocks.24.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1520 |
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1521 |
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1522 |
+
"visual.blocks.24.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1523 |
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1524 |
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1525 |
+
"visual.blocks.24.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1526 |
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1527 |
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1528 |
+
"visual.blocks.24.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1529 |
"visual.blocks.24.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1530 |
"visual.blocks.24.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1531 |
"visual.blocks.25.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1532 |
"visual.blocks.25.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1533 |
+
"visual.blocks.25.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1534 |
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1535 |
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1536 |
+
"visual.blocks.25.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1537 |
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1538 |
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1539 |
+
"visual.blocks.25.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1540 |
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1541 |
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1542 |
+
"visual.blocks.25.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1543 |
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1544 |
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1545 |
+
"visual.blocks.25.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1546 |
"visual.blocks.25.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1547 |
"visual.blocks.25.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1548 |
"visual.blocks.26.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1549 |
"visual.blocks.26.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1550 |
+
"visual.blocks.26.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1551 |
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1552 |
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1553 |
+
"visual.blocks.26.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1554 |
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1555 |
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1556 |
+
"visual.blocks.26.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1557 |
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1558 |
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1559 |
+
"visual.blocks.26.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1560 |
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1561 |
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1562 |
+
"visual.blocks.26.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1563 |
"visual.blocks.26.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1564 |
"visual.blocks.26.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1565 |
"visual.blocks.27.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1566 |
"visual.blocks.27.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1567 |
+
"visual.blocks.27.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1568 |
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1569 |
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1570 |
+
"visual.blocks.27.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1571 |
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1572 |
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1573 |
+
"visual.blocks.27.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1574 |
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1575 |
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1576 |
+
"visual.blocks.27.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1577 |
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1578 |
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1579 |
+
"visual.blocks.27.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1580 |
"visual.blocks.27.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1581 |
"visual.blocks.27.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1582 |
"visual.blocks.28.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1583 |
"visual.blocks.28.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1584 |
+
"visual.blocks.28.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1585 |
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1586 |
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1587 |
+
"visual.blocks.28.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1588 |
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1589 |
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1590 |
+
"visual.blocks.28.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1591 |
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1592 |
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1593 |
+
"visual.blocks.28.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1594 |
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1595 |
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1596 |
+
"visual.blocks.28.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1597 |
"visual.blocks.28.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1598 |
"visual.blocks.28.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1599 |
"visual.blocks.29.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1600 |
"visual.blocks.29.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1601 |
+
"visual.blocks.29.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1602 |
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1603 |
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1604 |
+
"visual.blocks.29.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1605 |
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1606 |
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1607 |
+
"visual.blocks.29.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1608 |
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1609 |
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1610 |
+
"visual.blocks.29.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1611 |
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1612 |
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1613 |
+
"visual.blocks.29.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1614 |
"visual.blocks.29.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1615 |
"visual.blocks.29.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1616 |
"visual.blocks.3.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1617 |
"visual.blocks.3.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1618 |
+
"visual.blocks.3.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1619 |
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1620 |
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1621 |
+
"visual.blocks.3.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1622 |
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1623 |
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1624 |
+
"visual.blocks.3.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1625 |
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1626 |
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1627 |
+
"visual.blocks.3.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1628 |
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1629 |
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1630 |
+
"visual.blocks.3.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1631 |
"visual.blocks.3.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1632 |
"visual.blocks.3.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1633 |
"visual.blocks.30.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1634 |
"visual.blocks.30.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1635 |
+
"visual.blocks.30.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1636 |
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1637 |
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1638 |
+
"visual.blocks.30.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1639 |
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1640 |
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1641 |
+
"visual.blocks.30.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1642 |
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1643 |
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1644 |
+
"visual.blocks.30.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1645 |
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1646 |
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1647 |
+
"visual.blocks.30.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1648 |
"visual.blocks.30.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1649 |
"visual.blocks.30.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1650 |
"visual.blocks.31.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1651 |
"visual.blocks.31.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1652 |
+
"visual.blocks.31.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1653 |
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1654 |
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1655 |
+
"visual.blocks.31.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1656 |
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1657 |
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1658 |
+
"visual.blocks.31.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1659 |
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1660 |
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1661 |
+
"visual.blocks.31.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1662 |
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1663 |
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1664 |
+
"visual.blocks.31.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1665 |
"visual.blocks.31.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1666 |
"visual.blocks.31.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1667 |
"visual.blocks.4.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1668 |
"visual.blocks.4.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1669 |
+
"visual.blocks.4.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1670 |
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1671 |
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1672 |
+
"visual.blocks.4.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1673 |
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1674 |
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1675 |
+
"visual.blocks.4.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1676 |
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1677 |
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1678 |
+
"visual.blocks.4.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1679 |
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1680 |
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1681 |
+
"visual.blocks.4.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1682 |
"visual.blocks.4.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1683 |
"visual.blocks.4.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1684 |
"visual.blocks.5.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1685 |
"visual.blocks.5.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1686 |
+
"visual.blocks.5.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1687 |
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1688 |
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1689 |
+
"visual.blocks.5.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1690 |
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1691 |
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1692 |
+
"visual.blocks.5.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1693 |
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1694 |
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1695 |
+
"visual.blocks.5.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1696 |
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1697 |
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1698 |
+
"visual.blocks.5.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1699 |
"visual.blocks.5.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1700 |
"visual.blocks.5.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1701 |
"visual.blocks.6.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1702 |
"visual.blocks.6.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1703 |
+
"visual.blocks.6.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1704 |
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1705 |
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1706 |
+
"visual.blocks.6.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1707 |
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1708 |
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1709 |
+
"visual.blocks.6.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1710 |
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1711 |
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1712 |
+
"visual.blocks.6.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1713 |
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1714 |
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1715 |
+
"visual.blocks.6.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1716 |
"visual.blocks.6.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1717 |
"visual.blocks.6.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1718 |
"visual.blocks.7.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1719 |
"visual.blocks.7.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1720 |
+
"visual.blocks.7.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1721 |
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1722 |
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1723 |
+
"visual.blocks.7.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1724 |
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1725 |
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1726 |
+
"visual.blocks.7.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1727 |
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1728 |
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1729 |
+
"visual.blocks.7.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1730 |
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1731 |
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1732 |
+
"visual.blocks.7.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1733 |
"visual.blocks.7.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1734 |
"visual.blocks.7.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1735 |
"visual.blocks.8.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1736 |
"visual.blocks.8.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1737 |
+
"visual.blocks.8.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1738 |
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1739 |
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1740 |
+
"visual.blocks.8.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1741 |
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1742 |
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1743 |
+
"visual.blocks.8.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1744 |
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1745 |
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1746 |
+
"visual.blocks.8.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1747 |
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1748 |
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1749 |
+
"visual.blocks.8.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1750 |
"visual.blocks.8.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1751 |
"visual.blocks.8.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1752 |
"visual.blocks.9.attn.proj.bias": "model-00001-of-00008.safetensors",
|
| 1753 |
"visual.blocks.9.attn.proj.weight": "model-00001-of-00008.safetensors",
|
| 1754 |
+
"visual.blocks.9.attn.proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1755 |
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00008.safetensors",
|
| 1756 |
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00008.safetensors",
|
| 1757 |
+
"visual.blocks.9.attn.qkv.weight_scale": "model-00001-of-00008.safetensors",
|
| 1758 |
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00008.safetensors",
|
| 1759 |
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 1760 |
+
"visual.blocks.9.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1761 |
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00008.safetensors",
|
| 1762 |
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 1763 |
+
"visual.blocks.9.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1764 |
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00008.safetensors",
|
| 1765 |
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 1766 |
+
"visual.blocks.9.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors",
|
| 1767 |
"visual.blocks.9.norm1.weight": "model-00001-of-00008.safetensors",
|
| 1768 |
"visual.blocks.9.norm2.weight": "model-00001-of-00008.safetensors",
|
| 1769 |
"visual.merger.ln_q.weight": "model-00001-of-00008.safetensors",
|
| 1770 |
"visual.merger.mlp.0.bias": "model-00001-of-00008.safetensors",
|
| 1771 |
"visual.merger.mlp.0.weight": "model-00001-of-00008.safetensors",
|
| 1772 |
+
"visual.merger.mlp.0.weight_scale": "model-00001-of-00008.safetensors",
|
| 1773 |
"visual.merger.mlp.2.bias": "model-00001-of-00008.safetensors",
|
| 1774 |
"visual.merger.mlp.2.weight": "model-00001-of-00008.safetensors",
|
| 1775 |
+
"visual.merger.mlp.2.weight_scale": "model-00001-of-00008.safetensors",
|
| 1776 |
"visual.patch_embed.proj.weight": "model-00001-of-00008.safetensors"
|
| 1777 |
}
|
| 1778 |
}
|
recipe.yaml
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
default_stage:
|
| 2 |
default_modifiers:
|
| 3 |
QuantizationModifier:
|
| 4 |
-
ignore: [lm_head, 're:
|
| 5 |
targets: [Linear]
|
| 6 |
scheme: FP8_DYNAMIC
|
|
|
|
| 1 |
default_stage:
|
| 2 |
default_modifiers:
|
| 3 |
QuantizationModifier:
|
| 4 |
+
ignore: ['re:.*lm_head', 're:vision_tower.*', 're:multi_modal_projector.*']
|
| 5 |
targets: [Linear]
|
| 6 |
scheme: FP8_DYNAMIC
|