Upload folder using huggingface_hub
Browse files- README.md +2 -2
- model-00001-of-00004.safetensors +2 -2
- model-00002-of-00004.safetensors +2 -2
- model-00003-of-00004.safetensors +2 -2
- model.safetensors.index.json +82 -82
README.md
CHANGED
|
@@ -30,8 +30,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
| 30 |
import torch
|
| 31 |
|
| 32 |
# Instantiate model and tokenizer
|
| 33 |
-
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-7B-
|
| 34 |
-
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-7B-
|
| 35 |
|
| 36 |
# Format the input as a chat template
|
| 37 |
user_turn_1 = "In one season a flower blooms three times. In one year, there is one blooming season. How many times do two flowers bloom in two years? Please include your logic."
|
|
|
|
| 30 |
import torch
|
| 31 |
|
| 32 |
# Instantiate model and tokenizer
|
| 33 |
+
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-7B-instruct")
|
| 34 |
+
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-7B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)
|
| 35 |
|
| 36 |
# Format the input as a chat template
|
| 37 |
user_turn_1 = "In one season a flower blooms three times. In one year, there is one blooming season. How many times do two flowers bloom in two years? Please include your logic."
|
model-00001-of-00004.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 sha256:8fb157a960ba1569c04c4d2e141d75b49fa081dd3639534cc2ef1c1d644e0272
|
| 3 |
+
size 4917529456
|
model-00002-of-00004.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 sha256:877a5e24da880f00d15f1a2c190df9883f0fae33139b548bae62012c7cc73f3c
|
| 3 |
+
size 4968641192
|
model-00003-of-00004.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 sha256:7d40e600ea6b9b3553b5af4cdde461fca9d0fc4b99d0f08d66488c642215733e
|
| 3 |
+
size 4934769784
|
model.safetensors.index.json
CHANGED
|
@@ -93,7 +93,7 @@
|
|
| 93 |
"model.mamba_layers.0.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 94 |
"model.mamba_layers.0.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 95 |
"model.mamba_layers.0.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 96 |
-
"model.mamba_layers.0.mamba.in_proj.
|
| 97 |
"model.mamba_layers.0.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 98 |
"model.mamba_layers.0.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 99 |
"model.mamba_layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -102,7 +102,7 @@
|
|
| 102 |
"model.mamba_layers.1.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 103 |
"model.mamba_layers.1.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 104 |
"model.mamba_layers.1.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 105 |
-
"model.mamba_layers.1.mamba.in_proj.
|
| 106 |
"model.mamba_layers.1.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 107 |
"model.mamba_layers.1.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 108 |
"model.mamba_layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -111,7 +111,7 @@
|
|
| 111 |
"model.mamba_layers.10.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 112 |
"model.mamba_layers.10.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 113 |
"model.mamba_layers.10.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 114 |
-
"model.mamba_layers.10.mamba.in_proj.
|
| 115 |
"model.mamba_layers.10.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 116 |
"model.mamba_layers.10.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 117 |
"model.mamba_layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -120,7 +120,7 @@
|
|
| 120 |
"model.mamba_layers.11.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 121 |
"model.mamba_layers.11.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 122 |
"model.mamba_layers.11.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 123 |
-
"model.mamba_layers.11.mamba.in_proj.
|
| 124 |
"model.mamba_layers.11.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 125 |
"model.mamba_layers.11.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 126 |
"model.mamba_layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -129,7 +129,7 @@
|
|
| 129 |
"model.mamba_layers.12.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 130 |
"model.mamba_layers.12.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 131 |
"model.mamba_layers.12.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 132 |
-
"model.mamba_layers.12.mamba.in_proj.
|
| 133 |
"model.mamba_layers.12.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 134 |
"model.mamba_layers.12.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 135 |
"model.mamba_layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -138,7 +138,7 @@
|
|
| 138 |
"model.mamba_layers.13.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 139 |
"model.mamba_layers.13.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 140 |
"model.mamba_layers.13.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 141 |
-
"model.mamba_layers.13.mamba.in_proj.
|
| 142 |
"model.mamba_layers.13.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 143 |
"model.mamba_layers.13.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
"model.mamba_layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -147,7 +147,7 @@
|
|
| 147 |
"model.mamba_layers.14.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 148 |
"model.mamba_layers.14.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 149 |
"model.mamba_layers.14.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 150 |
-
"model.mamba_layers.14.mamba.in_proj.
|
| 151 |
"model.mamba_layers.14.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 152 |
"model.mamba_layers.14.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 153 |
"model.mamba_layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -156,7 +156,7 @@
|
|
| 156 |
"model.mamba_layers.15.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 157 |
"model.mamba_layers.15.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 158 |
"model.mamba_layers.15.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 159 |
-
"model.mamba_layers.15.mamba.in_proj.
|
| 160 |
"model.mamba_layers.15.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 161 |
"model.mamba_layers.15.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 162 |
"model.mamba_layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -165,7 +165,7 @@
|
|
| 165 |
"model.mamba_layers.16.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 166 |
"model.mamba_layers.16.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 167 |
"model.mamba_layers.16.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 168 |
-
"model.mamba_layers.16.mamba.in_proj.
|
| 169 |
"model.mamba_layers.16.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 170 |
"model.mamba_layers.16.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 171 |
"model.mamba_layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -174,7 +174,7 @@
|
|
| 174 |
"model.mamba_layers.17.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 175 |
"model.mamba_layers.17.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 176 |
"model.mamba_layers.17.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 177 |
-
"model.mamba_layers.17.mamba.in_proj.
|
| 178 |
"model.mamba_layers.17.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 179 |
"model.mamba_layers.17.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 180 |
"model.mamba_layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -183,7 +183,7 @@
|
|
| 183 |
"model.mamba_layers.18.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 184 |
"model.mamba_layers.18.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 185 |
"model.mamba_layers.18.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 186 |
-
"model.mamba_layers.18.mamba.in_proj.
|
| 187 |
"model.mamba_layers.18.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 188 |
"model.mamba_layers.18.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 189 |
"model.mamba_layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -192,7 +192,7 @@
|
|
| 192 |
"model.mamba_layers.19.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 193 |
"model.mamba_layers.19.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 194 |
"model.mamba_layers.19.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 195 |
-
"model.mamba_layers.19.mamba.in_proj.
|
| 196 |
"model.mamba_layers.19.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 197 |
"model.mamba_layers.19.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 198 |
"model.mamba_layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -201,7 +201,7 @@
|
|
| 201 |
"model.mamba_layers.2.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 202 |
"model.mamba_layers.2.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 203 |
"model.mamba_layers.2.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 204 |
-
"model.mamba_layers.2.mamba.in_proj.
|
| 205 |
"model.mamba_layers.2.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 206 |
"model.mamba_layers.2.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 207 |
"model.mamba_layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -210,7 +210,7 @@
|
|
| 210 |
"model.mamba_layers.20.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 211 |
"model.mamba_layers.20.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 212 |
"model.mamba_layers.20.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 213 |
-
"model.mamba_layers.20.mamba.in_proj.
|
| 214 |
"model.mamba_layers.20.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 215 |
"model.mamba_layers.20.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 216 |
"model.mamba_layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -219,7 +219,7 @@
|
|
| 219 |
"model.mamba_layers.21.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 220 |
"model.mamba_layers.21.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 221 |
"model.mamba_layers.21.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 222 |
-
"model.mamba_layers.21.mamba.in_proj.
|
| 223 |
"model.mamba_layers.21.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 224 |
"model.mamba_layers.21.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 225 |
"model.mamba_layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -228,7 +228,7 @@
|
|
| 228 |
"model.mamba_layers.22.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 229 |
"model.mamba_layers.22.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 230 |
"model.mamba_layers.22.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 231 |
-
"model.mamba_layers.22.mamba.in_proj.
|
| 232 |
"model.mamba_layers.22.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 233 |
"model.mamba_layers.22.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 234 |
"model.mamba_layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -237,7 +237,7 @@
|
|
| 237 |
"model.mamba_layers.23.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 238 |
"model.mamba_layers.23.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 239 |
"model.mamba_layers.23.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 240 |
-
"model.mamba_layers.23.mamba.in_proj.
|
| 241 |
"model.mamba_layers.23.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 242 |
"model.mamba_layers.23.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 243 |
"model.mamba_layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -246,7 +246,7 @@
|
|
| 246 |
"model.mamba_layers.24.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 247 |
"model.mamba_layers.24.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 248 |
"model.mamba_layers.24.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 249 |
-
"model.mamba_layers.24.mamba.in_proj.
|
| 250 |
"model.mamba_layers.24.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 251 |
"model.mamba_layers.24.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 252 |
"model.mamba_layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -255,7 +255,7 @@
|
|
| 255 |
"model.mamba_layers.25.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 256 |
"model.mamba_layers.25.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 257 |
"model.mamba_layers.25.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 258 |
-
"model.mamba_layers.25.mamba.in_proj.
|
| 259 |
"model.mamba_layers.25.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 260 |
"model.mamba_layers.25.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 261 |
"model.mamba_layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -264,7 +264,7 @@
|
|
| 264 |
"model.mamba_layers.26.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 265 |
"model.mamba_layers.26.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 266 |
"model.mamba_layers.26.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 267 |
-
"model.mamba_layers.26.mamba.in_proj.
|
| 268 |
"model.mamba_layers.26.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 269 |
"model.mamba_layers.26.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 270 |
"model.mamba_layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -273,7 +273,7 @@
|
|
| 273 |
"model.mamba_layers.27.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 274 |
"model.mamba_layers.27.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 275 |
"model.mamba_layers.27.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 276 |
-
"model.mamba_layers.27.mamba.in_proj.
|
| 277 |
"model.mamba_layers.27.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 278 |
"model.mamba_layers.27.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 279 |
"model.mamba_layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -282,7 +282,7 @@
|
|
| 282 |
"model.mamba_layers.28.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 283 |
"model.mamba_layers.28.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 284 |
"model.mamba_layers.28.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 285 |
-
"model.mamba_layers.28.mamba.in_proj.
|
| 286 |
"model.mamba_layers.28.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 287 |
"model.mamba_layers.28.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 288 |
"model.mamba_layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -291,7 +291,7 @@
|
|
| 291 |
"model.mamba_layers.29.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 292 |
"model.mamba_layers.29.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 293 |
"model.mamba_layers.29.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 294 |
-
"model.mamba_layers.29.mamba.in_proj.
|
| 295 |
"model.mamba_layers.29.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 296 |
"model.mamba_layers.29.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 297 |
"model.mamba_layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -300,7 +300,7 @@
|
|
| 300 |
"model.mamba_layers.3.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 301 |
"model.mamba_layers.3.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 302 |
"model.mamba_layers.3.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 303 |
-
"model.mamba_layers.3.mamba.in_proj.
|
| 304 |
"model.mamba_layers.3.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 305 |
"model.mamba_layers.3.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 306 |
"model.mamba_layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -309,7 +309,7 @@
|
|
| 309 |
"model.mamba_layers.30.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 310 |
"model.mamba_layers.30.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 311 |
"model.mamba_layers.30.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 312 |
-
"model.mamba_layers.30.mamba.in_proj.
|
| 313 |
"model.mamba_layers.30.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 314 |
"model.mamba_layers.30.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 315 |
"model.mamba_layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -318,7 +318,7 @@
|
|
| 318 |
"model.mamba_layers.31.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 319 |
"model.mamba_layers.31.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 320 |
"model.mamba_layers.31.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 321 |
-
"model.mamba_layers.31.mamba.in_proj.
|
| 322 |
"model.mamba_layers.31.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 323 |
"model.mamba_layers.31.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
"model.mamba_layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -327,7 +327,7 @@
|
|
| 327 |
"model.mamba_layers.32.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 328 |
"model.mamba_layers.32.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 329 |
"model.mamba_layers.32.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 330 |
-
"model.mamba_layers.32.mamba.in_proj.
|
| 331 |
"model.mamba_layers.32.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 332 |
"model.mamba_layers.32.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 333 |
"model.mamba_layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -336,7 +336,7 @@
|
|
| 336 |
"model.mamba_layers.33.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 337 |
"model.mamba_layers.33.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 338 |
"model.mamba_layers.33.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 339 |
-
"model.mamba_layers.33.mamba.in_proj.
|
| 340 |
"model.mamba_layers.33.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 341 |
"model.mamba_layers.33.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 342 |
"model.mamba_layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -345,7 +345,7 @@
|
|
| 345 |
"model.mamba_layers.34.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 346 |
"model.mamba_layers.34.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 347 |
"model.mamba_layers.34.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 348 |
-
"model.mamba_layers.34.mamba.in_proj.
|
| 349 |
"model.mamba_layers.34.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 350 |
"model.mamba_layers.34.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 351 |
"model.mamba_layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -354,7 +354,7 @@
|
|
| 354 |
"model.mamba_layers.35.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 355 |
"model.mamba_layers.35.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 356 |
"model.mamba_layers.35.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 357 |
-
"model.mamba_layers.35.mamba.in_proj.
|
| 358 |
"model.mamba_layers.35.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 359 |
"model.mamba_layers.35.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 360 |
"model.mamba_layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -363,7 +363,7 @@
|
|
| 363 |
"model.mamba_layers.36.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 364 |
"model.mamba_layers.36.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 365 |
"model.mamba_layers.36.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 366 |
-
"model.mamba_layers.36.mamba.in_proj.
|
| 367 |
"model.mamba_layers.36.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 368 |
"model.mamba_layers.36.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 369 |
"model.mamba_layers.37.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -372,7 +372,7 @@
|
|
| 372 |
"model.mamba_layers.37.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 373 |
"model.mamba_layers.37.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 374 |
"model.mamba_layers.37.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 375 |
-
"model.mamba_layers.37.mamba.in_proj.
|
| 376 |
"model.mamba_layers.37.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 377 |
"model.mamba_layers.37.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 378 |
"model.mamba_layers.38.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -381,7 +381,7 @@
|
|
| 381 |
"model.mamba_layers.38.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 382 |
"model.mamba_layers.38.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 383 |
"model.mamba_layers.38.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 384 |
-
"model.mamba_layers.38.mamba.in_proj.
|
| 385 |
"model.mamba_layers.38.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 386 |
"model.mamba_layers.38.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 387 |
"model.mamba_layers.39.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -390,7 +390,7 @@
|
|
| 390 |
"model.mamba_layers.39.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 391 |
"model.mamba_layers.39.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 392 |
"model.mamba_layers.39.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 393 |
-
"model.mamba_layers.39.mamba.in_proj.
|
| 394 |
"model.mamba_layers.39.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
"model.mamba_layers.39.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
"model.mamba_layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -399,7 +399,7 @@
|
|
| 399 |
"model.mamba_layers.4.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 400 |
"model.mamba_layers.4.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 401 |
"model.mamba_layers.4.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 402 |
-
"model.mamba_layers.4.mamba.in_proj.
|
| 403 |
"model.mamba_layers.4.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 404 |
"model.mamba_layers.4.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 405 |
"model.mamba_layers.40.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -408,7 +408,7 @@
|
|
| 408 |
"model.mamba_layers.40.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 409 |
"model.mamba_layers.40.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 410 |
"model.mamba_layers.40.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 411 |
-
"model.mamba_layers.40.mamba.in_proj.
|
| 412 |
"model.mamba_layers.40.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 413 |
"model.mamba_layers.40.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 414 |
"model.mamba_layers.41.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -417,7 +417,7 @@
|
|
| 417 |
"model.mamba_layers.41.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 418 |
"model.mamba_layers.41.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 419 |
"model.mamba_layers.41.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 420 |
-
"model.mamba_layers.41.mamba.in_proj.
|
| 421 |
"model.mamba_layers.41.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 422 |
"model.mamba_layers.41.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 423 |
"model.mamba_layers.42.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -426,7 +426,7 @@
|
|
| 426 |
"model.mamba_layers.42.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 427 |
"model.mamba_layers.42.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 428 |
"model.mamba_layers.42.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 429 |
-
"model.mamba_layers.42.mamba.in_proj.
|
| 430 |
"model.mamba_layers.42.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 431 |
"model.mamba_layers.42.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 432 |
"model.mamba_layers.43.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -435,7 +435,7 @@
|
|
| 435 |
"model.mamba_layers.43.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 436 |
"model.mamba_layers.43.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 437 |
"model.mamba_layers.43.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 438 |
-
"model.mamba_layers.43.mamba.in_proj.
|
| 439 |
"model.mamba_layers.43.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 440 |
"model.mamba_layers.43.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 441 |
"model.mamba_layers.44.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -444,7 +444,7 @@
|
|
| 444 |
"model.mamba_layers.44.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 445 |
"model.mamba_layers.44.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 446 |
"model.mamba_layers.44.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 447 |
-
"model.mamba_layers.44.mamba.in_proj.
|
| 448 |
"model.mamba_layers.44.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 449 |
"model.mamba_layers.44.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 450 |
"model.mamba_layers.45.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -453,7 +453,7 @@
|
|
| 453 |
"model.mamba_layers.45.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 454 |
"model.mamba_layers.45.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 455 |
"model.mamba_layers.45.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 456 |
-
"model.mamba_layers.45.mamba.in_proj.
|
| 457 |
"model.mamba_layers.45.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 458 |
"model.mamba_layers.45.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 459 |
"model.mamba_layers.46.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -462,7 +462,7 @@
|
|
| 462 |
"model.mamba_layers.46.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 463 |
"model.mamba_layers.46.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 464 |
"model.mamba_layers.46.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 465 |
-
"model.mamba_layers.46.mamba.in_proj.
|
| 466 |
"model.mamba_layers.46.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 467 |
"model.mamba_layers.46.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 468 |
"model.mamba_layers.47.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -471,7 +471,7 @@
|
|
| 471 |
"model.mamba_layers.47.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 472 |
"model.mamba_layers.47.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 473 |
"model.mamba_layers.47.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 474 |
-
"model.mamba_layers.47.mamba.in_proj.
|
| 475 |
"model.mamba_layers.47.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 476 |
"model.mamba_layers.47.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 477 |
"model.mamba_layers.48.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -480,7 +480,7 @@
|
|
| 480 |
"model.mamba_layers.48.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 481 |
"model.mamba_layers.48.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 482 |
"model.mamba_layers.48.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 483 |
-
"model.mamba_layers.48.mamba.in_proj.
|
| 484 |
"model.mamba_layers.48.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 485 |
"model.mamba_layers.48.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 486 |
"model.mamba_layers.49.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -489,7 +489,7 @@
|
|
| 489 |
"model.mamba_layers.49.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 490 |
"model.mamba_layers.49.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 491 |
"model.mamba_layers.49.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 492 |
-
"model.mamba_layers.49.mamba.in_proj.
|
| 493 |
"model.mamba_layers.49.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 494 |
"model.mamba_layers.49.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 495 |
"model.mamba_layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -498,7 +498,7 @@
|
|
| 498 |
"model.mamba_layers.5.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 499 |
"model.mamba_layers.5.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 500 |
"model.mamba_layers.5.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 501 |
-
"model.mamba_layers.5.mamba.in_proj.
|
| 502 |
"model.mamba_layers.5.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 503 |
"model.mamba_layers.5.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 504 |
"model.mamba_layers.50.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
@@ -507,7 +507,7 @@
|
|
| 507 |
"model.mamba_layers.50.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 508 |
"model.mamba_layers.50.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 509 |
"model.mamba_layers.50.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 510 |
-
"model.mamba_layers.50.mamba.in_proj.
|
| 511 |
"model.mamba_layers.50.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 512 |
"model.mamba_layers.50.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 513 |
"model.mamba_layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -516,7 +516,7 @@
|
|
| 516 |
"model.mamba_layers.51.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 517 |
"model.mamba_layers.51.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 518 |
"model.mamba_layers.51.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 519 |
-
"model.mamba_layers.51.mamba.in_proj.
|
| 520 |
"model.mamba_layers.51.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 521 |
"model.mamba_layers.51.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 522 |
"model.mamba_layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -525,7 +525,7 @@
|
|
| 525 |
"model.mamba_layers.52.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 526 |
"model.mamba_layers.52.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 527 |
"model.mamba_layers.52.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 528 |
-
"model.mamba_layers.52.mamba.in_proj.
|
| 529 |
"model.mamba_layers.52.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 530 |
"model.mamba_layers.52.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 531 |
"model.mamba_layers.53.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -534,7 +534,7 @@
|
|
| 534 |
"model.mamba_layers.53.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 535 |
"model.mamba_layers.53.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 536 |
"model.mamba_layers.53.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 537 |
-
"model.mamba_layers.53.mamba.in_proj.
|
| 538 |
"model.mamba_layers.53.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 539 |
"model.mamba_layers.53.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 540 |
"model.mamba_layers.54.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -543,7 +543,7 @@
|
|
| 543 |
"model.mamba_layers.54.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 544 |
"model.mamba_layers.54.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 545 |
"model.mamba_layers.54.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 546 |
-
"model.mamba_layers.54.mamba.in_proj.
|
| 547 |
"model.mamba_layers.54.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 548 |
"model.mamba_layers.54.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 549 |
"model.mamba_layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -552,7 +552,7 @@
|
|
| 552 |
"model.mamba_layers.55.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 553 |
"model.mamba_layers.55.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 554 |
"model.mamba_layers.55.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 555 |
-
"model.mamba_layers.55.mamba.in_proj.
|
| 556 |
"model.mamba_layers.55.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 557 |
"model.mamba_layers.55.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 558 |
"model.mamba_layers.56.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -561,7 +561,7 @@
|
|
| 561 |
"model.mamba_layers.56.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 562 |
"model.mamba_layers.56.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 563 |
"model.mamba_layers.56.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 564 |
-
"model.mamba_layers.56.mamba.in_proj.
|
| 565 |
"model.mamba_layers.56.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 566 |
"model.mamba_layers.56.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 567 |
"model.mamba_layers.57.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -570,7 +570,7 @@
|
|
| 570 |
"model.mamba_layers.57.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 571 |
"model.mamba_layers.57.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 572 |
"model.mamba_layers.57.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 573 |
-
"model.mamba_layers.57.mamba.in_proj.
|
| 574 |
"model.mamba_layers.57.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 575 |
"model.mamba_layers.57.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 576 |
"model.mamba_layers.58.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -579,7 +579,7 @@
|
|
| 579 |
"model.mamba_layers.58.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 580 |
"model.mamba_layers.58.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 581 |
"model.mamba_layers.58.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 582 |
-
"model.mamba_layers.58.mamba.in_proj.
|
| 583 |
"model.mamba_layers.58.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 584 |
"model.mamba_layers.58.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 585 |
"model.mamba_layers.59.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -588,7 +588,7 @@
|
|
| 588 |
"model.mamba_layers.59.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 589 |
"model.mamba_layers.59.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 590 |
"model.mamba_layers.59.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 591 |
-
"model.mamba_layers.59.mamba.in_proj.
|
| 592 |
"model.mamba_layers.59.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 593 |
"model.mamba_layers.59.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 594 |
"model.mamba_layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -597,7 +597,7 @@
|
|
| 597 |
"model.mamba_layers.6.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 598 |
"model.mamba_layers.6.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 599 |
"model.mamba_layers.6.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 600 |
-
"model.mamba_layers.6.mamba.in_proj.
|
| 601 |
"model.mamba_layers.6.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 602 |
"model.mamba_layers.6.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 603 |
"model.mamba_layers.60.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -606,7 +606,7 @@
|
|
| 606 |
"model.mamba_layers.60.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 607 |
"model.mamba_layers.60.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 608 |
"model.mamba_layers.60.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 609 |
-
"model.mamba_layers.60.mamba.in_proj.
|
| 610 |
"model.mamba_layers.60.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 611 |
"model.mamba_layers.60.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 612 |
"model.mamba_layers.61.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -615,7 +615,7 @@
|
|
| 615 |
"model.mamba_layers.61.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 616 |
"model.mamba_layers.61.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 617 |
"model.mamba_layers.61.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 618 |
-
"model.mamba_layers.61.mamba.in_proj.
|
| 619 |
"model.mamba_layers.61.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 620 |
"model.mamba_layers.61.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 621 |
"model.mamba_layers.62.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -624,7 +624,7 @@
|
|
| 624 |
"model.mamba_layers.62.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 625 |
"model.mamba_layers.62.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 626 |
"model.mamba_layers.62.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 627 |
-
"model.mamba_layers.62.mamba.in_proj.
|
| 628 |
"model.mamba_layers.62.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 629 |
"model.mamba_layers.62.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 630 |
"model.mamba_layers.63.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -633,7 +633,7 @@
|
|
| 633 |
"model.mamba_layers.63.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 634 |
"model.mamba_layers.63.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 635 |
"model.mamba_layers.63.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 636 |
-
"model.mamba_layers.63.mamba.in_proj.
|
| 637 |
"model.mamba_layers.63.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 638 |
"model.mamba_layers.63.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 639 |
"model.mamba_layers.64.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -642,7 +642,7 @@
|
|
| 642 |
"model.mamba_layers.64.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 643 |
"model.mamba_layers.64.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 644 |
"model.mamba_layers.64.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 645 |
-
"model.mamba_layers.64.mamba.in_proj.
|
| 646 |
"model.mamba_layers.64.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 647 |
"model.mamba_layers.64.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 648 |
"model.mamba_layers.65.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -651,7 +651,7 @@
|
|
| 651 |
"model.mamba_layers.65.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 652 |
"model.mamba_layers.65.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 653 |
"model.mamba_layers.65.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 654 |
-
"model.mamba_layers.65.mamba.in_proj.
|
| 655 |
"model.mamba_layers.65.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 656 |
"model.mamba_layers.65.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 657 |
"model.mamba_layers.66.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -660,7 +660,7 @@
|
|
| 660 |
"model.mamba_layers.66.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 661 |
"model.mamba_layers.66.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 662 |
"model.mamba_layers.66.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 663 |
-
"model.mamba_layers.66.mamba.in_proj.
|
| 664 |
"model.mamba_layers.66.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 665 |
"model.mamba_layers.66.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 666 |
"model.mamba_layers.67.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -669,7 +669,7 @@
|
|
| 669 |
"model.mamba_layers.67.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 670 |
"model.mamba_layers.67.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 671 |
"model.mamba_layers.67.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 672 |
-
"model.mamba_layers.67.mamba.in_proj.
|
| 673 |
"model.mamba_layers.67.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 674 |
"model.mamba_layers.67.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 675 |
"model.mamba_layers.68.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -678,7 +678,7 @@
|
|
| 678 |
"model.mamba_layers.68.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 679 |
"model.mamba_layers.68.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 680 |
"model.mamba_layers.68.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 681 |
-
"model.mamba_layers.68.mamba.in_proj.
|
| 682 |
"model.mamba_layers.68.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 683 |
"model.mamba_layers.68.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 684 |
"model.mamba_layers.69.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -687,7 +687,7 @@
|
|
| 687 |
"model.mamba_layers.69.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 688 |
"model.mamba_layers.69.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 689 |
"model.mamba_layers.69.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 690 |
-
"model.mamba_layers.69.mamba.in_proj.
|
| 691 |
"model.mamba_layers.69.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 692 |
"model.mamba_layers.69.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 693 |
"model.mamba_layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -696,7 +696,7 @@
|
|
| 696 |
"model.mamba_layers.7.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 697 |
"model.mamba_layers.7.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 698 |
"model.mamba_layers.7.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 699 |
-
"model.mamba_layers.7.mamba.in_proj.
|
| 700 |
"model.mamba_layers.7.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 701 |
"model.mamba_layers.7.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 702 |
"model.mamba_layers.70.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -705,7 +705,7 @@
|
|
| 705 |
"model.mamba_layers.70.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 706 |
"model.mamba_layers.70.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 707 |
"model.mamba_layers.70.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 708 |
-
"model.mamba_layers.70.mamba.in_proj.
|
| 709 |
"model.mamba_layers.70.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 710 |
"model.mamba_layers.70.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 711 |
"model.mamba_layers.71.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -714,7 +714,7 @@
|
|
| 714 |
"model.mamba_layers.71.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 715 |
"model.mamba_layers.71.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 716 |
"model.mamba_layers.71.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 717 |
-
"model.mamba_layers.71.mamba.in_proj.
|
| 718 |
"model.mamba_layers.71.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 719 |
"model.mamba_layers.71.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 720 |
"model.mamba_layers.72.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -723,7 +723,7 @@
|
|
| 723 |
"model.mamba_layers.72.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 724 |
"model.mamba_layers.72.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 725 |
"model.mamba_layers.72.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 726 |
-
"model.mamba_layers.72.mamba.in_proj.
|
| 727 |
"model.mamba_layers.72.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 728 |
"model.mamba_layers.72.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 729 |
"model.mamba_layers.73.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -732,7 +732,7 @@
|
|
| 732 |
"model.mamba_layers.73.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 733 |
"model.mamba_layers.73.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 734 |
"model.mamba_layers.73.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 735 |
-
"model.mamba_layers.73.mamba.in_proj.
|
| 736 |
"model.mamba_layers.73.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 737 |
"model.mamba_layers.73.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 738 |
"model.mamba_layers.74.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -741,7 +741,7 @@
|
|
| 741 |
"model.mamba_layers.74.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 742 |
"model.mamba_layers.74.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 743 |
"model.mamba_layers.74.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 744 |
-
"model.mamba_layers.74.mamba.in_proj.
|
| 745 |
"model.mamba_layers.74.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 746 |
"model.mamba_layers.74.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 747 |
"model.mamba_layers.75.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -750,7 +750,7 @@
|
|
| 750 |
"model.mamba_layers.75.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 751 |
"model.mamba_layers.75.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 752 |
"model.mamba_layers.75.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 753 |
-
"model.mamba_layers.75.mamba.in_proj.
|
| 754 |
"model.mamba_layers.75.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 755 |
"model.mamba_layers.75.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 756 |
"model.mamba_layers.76.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -759,7 +759,7 @@
|
|
| 759 |
"model.mamba_layers.76.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 760 |
"model.mamba_layers.76.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 761 |
"model.mamba_layers.76.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 762 |
-
"model.mamba_layers.76.mamba.in_proj.
|
| 763 |
"model.mamba_layers.76.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 764 |
"model.mamba_layers.76.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 765 |
"model.mamba_layers.77.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -768,7 +768,7 @@
|
|
| 768 |
"model.mamba_layers.77.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 769 |
"model.mamba_layers.77.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 770 |
"model.mamba_layers.77.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 771 |
-
"model.mamba_layers.77.mamba.in_proj.
|
| 772 |
"model.mamba_layers.77.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 773 |
"model.mamba_layers.77.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 774 |
"model.mamba_layers.78.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -777,7 +777,7 @@
|
|
| 777 |
"model.mamba_layers.78.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 778 |
"model.mamba_layers.78.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 779 |
"model.mamba_layers.78.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 780 |
-
"model.mamba_layers.78.mamba.in_proj.
|
| 781 |
"model.mamba_layers.78.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 782 |
"model.mamba_layers.78.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 783 |
"model.mamba_layers.79.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -786,7 +786,7 @@
|
|
| 786 |
"model.mamba_layers.79.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 787 |
"model.mamba_layers.79.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 788 |
"model.mamba_layers.79.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 789 |
-
"model.mamba_layers.79.mamba.in_proj.
|
| 790 |
"model.mamba_layers.79.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 791 |
"model.mamba_layers.79.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 792 |
"model.mamba_layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -795,7 +795,7 @@
|
|
| 795 |
"model.mamba_layers.8.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 796 |
"model.mamba_layers.8.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 797 |
"model.mamba_layers.8.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 798 |
-
"model.mamba_layers.8.mamba.in_proj.
|
| 799 |
"model.mamba_layers.8.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 800 |
"model.mamba_layers.8.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 801 |
"model.mamba_layers.80.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
@@ -804,7 +804,7 @@
|
|
| 804 |
"model.mamba_layers.80.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 805 |
"model.mamba_layers.80.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 806 |
"model.mamba_layers.80.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 807 |
-
"model.mamba_layers.80.mamba.in_proj.
|
| 808 |
"model.mamba_layers.80.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 809 |
"model.mamba_layers.80.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 810 |
"model.mamba_layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
@@ -813,8 +813,8 @@
|
|
| 813 |
"model.mamba_layers.9.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 814 |
"model.mamba_layers.9.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 815 |
"model.mamba_layers.9.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 816 |
-
"model.mamba_layers.9.mamba.in_proj.
|
| 817 |
"model.mamba_layers.9.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 818 |
"model.mamba_layers.9.mamba.out_proj.weight": "model-00001-of-00004.safetensors"
|
| 819 |
}
|
| 820 |
-
}
|
|
|
|
| 93 |
"model.mamba_layers.0.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 94 |
"model.mamba_layers.0.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 95 |
"model.mamba_layers.0.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 96 |
+
"model.mamba_layers.0.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 97 |
"model.mamba_layers.0.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 98 |
"model.mamba_layers.0.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 99 |
"model.mamba_layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 102 |
"model.mamba_layers.1.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 103 |
"model.mamba_layers.1.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 104 |
"model.mamba_layers.1.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 105 |
+
"model.mamba_layers.1.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 106 |
"model.mamba_layers.1.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 107 |
"model.mamba_layers.1.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 108 |
"model.mamba_layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 111 |
"model.mamba_layers.10.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 112 |
"model.mamba_layers.10.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 113 |
"model.mamba_layers.10.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 114 |
+
"model.mamba_layers.10.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 115 |
"model.mamba_layers.10.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 116 |
"model.mamba_layers.10.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 117 |
"model.mamba_layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 120 |
"model.mamba_layers.11.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 121 |
"model.mamba_layers.11.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 122 |
"model.mamba_layers.11.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 123 |
+
"model.mamba_layers.11.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 124 |
"model.mamba_layers.11.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 125 |
"model.mamba_layers.11.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 126 |
"model.mamba_layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 129 |
"model.mamba_layers.12.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 130 |
"model.mamba_layers.12.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 131 |
"model.mamba_layers.12.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 132 |
+
"model.mamba_layers.12.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 133 |
"model.mamba_layers.12.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 134 |
"model.mamba_layers.12.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 135 |
"model.mamba_layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 138 |
"model.mamba_layers.13.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 139 |
"model.mamba_layers.13.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 140 |
"model.mamba_layers.13.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 141 |
+
"model.mamba_layers.13.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 142 |
"model.mamba_layers.13.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 143 |
"model.mamba_layers.13.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
"model.mamba_layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 147 |
"model.mamba_layers.14.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 148 |
"model.mamba_layers.14.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 149 |
"model.mamba_layers.14.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.mamba_layers.14.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
"model.mamba_layers.14.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 152 |
"model.mamba_layers.14.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 153 |
"model.mamba_layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 156 |
"model.mamba_layers.15.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 157 |
"model.mamba_layers.15.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 158 |
"model.mamba_layers.15.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.mamba_layers.15.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
"model.mamba_layers.15.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 161 |
"model.mamba_layers.15.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 162 |
"model.mamba_layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 165 |
"model.mamba_layers.16.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 166 |
"model.mamba_layers.16.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 167 |
"model.mamba_layers.16.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 168 |
+
"model.mamba_layers.16.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 169 |
"model.mamba_layers.16.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 170 |
"model.mamba_layers.16.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 171 |
"model.mamba_layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 174 |
"model.mamba_layers.17.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 175 |
"model.mamba_layers.17.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 176 |
"model.mamba_layers.17.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 177 |
+
"model.mamba_layers.17.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 178 |
"model.mamba_layers.17.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 179 |
"model.mamba_layers.17.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 180 |
"model.mamba_layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 183 |
"model.mamba_layers.18.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 184 |
"model.mamba_layers.18.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 185 |
"model.mamba_layers.18.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 186 |
+
"model.mamba_layers.18.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 187 |
"model.mamba_layers.18.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 188 |
"model.mamba_layers.18.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 189 |
"model.mamba_layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 192 |
"model.mamba_layers.19.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 193 |
"model.mamba_layers.19.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 194 |
"model.mamba_layers.19.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 195 |
+
"model.mamba_layers.19.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 196 |
"model.mamba_layers.19.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 197 |
"model.mamba_layers.19.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 198 |
"model.mamba_layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 201 |
"model.mamba_layers.2.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 202 |
"model.mamba_layers.2.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 203 |
"model.mamba_layers.2.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 204 |
+
"model.mamba_layers.2.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 205 |
"model.mamba_layers.2.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 206 |
"model.mamba_layers.2.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 207 |
"model.mamba_layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 210 |
"model.mamba_layers.20.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 211 |
"model.mamba_layers.20.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 212 |
"model.mamba_layers.20.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 213 |
+
"model.mamba_layers.20.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 214 |
"model.mamba_layers.20.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 215 |
"model.mamba_layers.20.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 216 |
"model.mamba_layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 219 |
"model.mamba_layers.21.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 220 |
"model.mamba_layers.21.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 221 |
"model.mamba_layers.21.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 222 |
+
"model.mamba_layers.21.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 223 |
"model.mamba_layers.21.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 224 |
"model.mamba_layers.21.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 225 |
"model.mamba_layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 228 |
"model.mamba_layers.22.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 229 |
"model.mamba_layers.22.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 230 |
"model.mamba_layers.22.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 231 |
+
"model.mamba_layers.22.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 232 |
"model.mamba_layers.22.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 233 |
"model.mamba_layers.22.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 234 |
"model.mamba_layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 237 |
"model.mamba_layers.23.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 238 |
"model.mamba_layers.23.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 239 |
"model.mamba_layers.23.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 240 |
+
"model.mamba_layers.23.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 241 |
"model.mamba_layers.23.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 242 |
"model.mamba_layers.23.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 243 |
"model.mamba_layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 246 |
"model.mamba_layers.24.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 247 |
"model.mamba_layers.24.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 248 |
"model.mamba_layers.24.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 249 |
+
"model.mamba_layers.24.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 250 |
"model.mamba_layers.24.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 251 |
"model.mamba_layers.24.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 252 |
"model.mamba_layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 255 |
"model.mamba_layers.25.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 256 |
"model.mamba_layers.25.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 257 |
"model.mamba_layers.25.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 258 |
+
"model.mamba_layers.25.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 259 |
"model.mamba_layers.25.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 260 |
"model.mamba_layers.25.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 261 |
"model.mamba_layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 264 |
"model.mamba_layers.26.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 265 |
"model.mamba_layers.26.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 266 |
"model.mamba_layers.26.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 267 |
+
"model.mamba_layers.26.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 268 |
"model.mamba_layers.26.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 269 |
"model.mamba_layers.26.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 270 |
"model.mamba_layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 273 |
"model.mamba_layers.27.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 274 |
"model.mamba_layers.27.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 275 |
"model.mamba_layers.27.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 276 |
+
"model.mamba_layers.27.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 277 |
"model.mamba_layers.27.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 278 |
"model.mamba_layers.27.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 279 |
"model.mamba_layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 282 |
"model.mamba_layers.28.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 283 |
"model.mamba_layers.28.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 284 |
"model.mamba_layers.28.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 285 |
+
"model.mamba_layers.28.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 286 |
"model.mamba_layers.28.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 287 |
"model.mamba_layers.28.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 288 |
"model.mamba_layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 291 |
"model.mamba_layers.29.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 292 |
"model.mamba_layers.29.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 293 |
"model.mamba_layers.29.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 294 |
+
"model.mamba_layers.29.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 295 |
"model.mamba_layers.29.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 296 |
"model.mamba_layers.29.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 297 |
"model.mamba_layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 300 |
"model.mamba_layers.3.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 301 |
"model.mamba_layers.3.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 302 |
"model.mamba_layers.3.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 303 |
+
"model.mamba_layers.3.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 304 |
"model.mamba_layers.3.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 305 |
"model.mamba_layers.3.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 306 |
"model.mamba_layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 309 |
"model.mamba_layers.30.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 310 |
"model.mamba_layers.30.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 311 |
"model.mamba_layers.30.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 312 |
+
"model.mamba_layers.30.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 313 |
"model.mamba_layers.30.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 314 |
"model.mamba_layers.30.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 315 |
"model.mamba_layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 318 |
"model.mamba_layers.31.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 319 |
"model.mamba_layers.31.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 320 |
"model.mamba_layers.31.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 321 |
+
"model.mamba_layers.31.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 322 |
"model.mamba_layers.31.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 323 |
"model.mamba_layers.31.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
"model.mamba_layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 327 |
"model.mamba_layers.32.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 328 |
"model.mamba_layers.32.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 329 |
"model.mamba_layers.32.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 330 |
+
"model.mamba_layers.32.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 331 |
"model.mamba_layers.32.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 332 |
"model.mamba_layers.32.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 333 |
"model.mamba_layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 336 |
"model.mamba_layers.33.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 337 |
"model.mamba_layers.33.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 338 |
"model.mamba_layers.33.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 339 |
+
"model.mamba_layers.33.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
"model.mamba_layers.33.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 341 |
"model.mamba_layers.33.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 342 |
"model.mamba_layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 345 |
"model.mamba_layers.34.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 346 |
"model.mamba_layers.34.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 347 |
"model.mamba_layers.34.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 348 |
+
"model.mamba_layers.34.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 349 |
"model.mamba_layers.34.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 350 |
"model.mamba_layers.34.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 351 |
"model.mamba_layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 354 |
"model.mamba_layers.35.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 355 |
"model.mamba_layers.35.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 356 |
"model.mamba_layers.35.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 357 |
+
"model.mamba_layers.35.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 358 |
"model.mamba_layers.35.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 359 |
"model.mamba_layers.35.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 360 |
"model.mamba_layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 363 |
"model.mamba_layers.36.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 364 |
"model.mamba_layers.36.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 365 |
"model.mamba_layers.36.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 366 |
+
"model.mamba_layers.36.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 367 |
"model.mamba_layers.36.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 368 |
"model.mamba_layers.36.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 369 |
"model.mamba_layers.37.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 372 |
"model.mamba_layers.37.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 373 |
"model.mamba_layers.37.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 374 |
"model.mamba_layers.37.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.mamba_layers.37.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 376 |
"model.mamba_layers.37.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 377 |
"model.mamba_layers.37.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 378 |
"model.mamba_layers.38.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 381 |
"model.mamba_layers.38.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 382 |
"model.mamba_layers.38.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 383 |
"model.mamba_layers.38.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.mamba_layers.38.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 385 |
"model.mamba_layers.38.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 386 |
"model.mamba_layers.38.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 387 |
"model.mamba_layers.39.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 390 |
"model.mamba_layers.39.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 391 |
"model.mamba_layers.39.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 392 |
"model.mamba_layers.39.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.mamba_layers.39.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 394 |
"model.mamba_layers.39.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
"model.mamba_layers.39.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
"model.mamba_layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 399 |
"model.mamba_layers.4.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 400 |
"model.mamba_layers.4.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 401 |
"model.mamba_layers.4.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.mamba_layers.4.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 403 |
"model.mamba_layers.4.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 404 |
"model.mamba_layers.4.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 405 |
"model.mamba_layers.40.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 408 |
"model.mamba_layers.40.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 409 |
"model.mamba_layers.40.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 410 |
"model.mamba_layers.40.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 411 |
+
"model.mamba_layers.40.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 412 |
"model.mamba_layers.40.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 413 |
"model.mamba_layers.40.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 414 |
"model.mamba_layers.41.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 417 |
"model.mamba_layers.41.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 418 |
"model.mamba_layers.41.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 419 |
"model.mamba_layers.41.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 420 |
+
"model.mamba_layers.41.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 421 |
"model.mamba_layers.41.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 422 |
"model.mamba_layers.41.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 423 |
"model.mamba_layers.42.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 426 |
"model.mamba_layers.42.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 427 |
"model.mamba_layers.42.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 428 |
"model.mamba_layers.42.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 429 |
+
"model.mamba_layers.42.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 430 |
"model.mamba_layers.42.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 431 |
"model.mamba_layers.42.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 432 |
"model.mamba_layers.43.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 435 |
"model.mamba_layers.43.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 436 |
"model.mamba_layers.43.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 437 |
"model.mamba_layers.43.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 438 |
+
"model.mamba_layers.43.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 439 |
"model.mamba_layers.43.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 440 |
"model.mamba_layers.43.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 441 |
"model.mamba_layers.44.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 444 |
"model.mamba_layers.44.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 445 |
"model.mamba_layers.44.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 446 |
"model.mamba_layers.44.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 447 |
+
"model.mamba_layers.44.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 448 |
"model.mamba_layers.44.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 449 |
"model.mamba_layers.44.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 450 |
"model.mamba_layers.45.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 453 |
"model.mamba_layers.45.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 454 |
"model.mamba_layers.45.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 455 |
"model.mamba_layers.45.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 456 |
+
"model.mamba_layers.45.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 457 |
"model.mamba_layers.45.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 458 |
"model.mamba_layers.45.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 459 |
"model.mamba_layers.46.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 462 |
"model.mamba_layers.46.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 463 |
"model.mamba_layers.46.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 464 |
"model.mamba_layers.46.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 465 |
+
"model.mamba_layers.46.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 466 |
"model.mamba_layers.46.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 467 |
"model.mamba_layers.46.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 468 |
"model.mamba_layers.47.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 471 |
"model.mamba_layers.47.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 472 |
"model.mamba_layers.47.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 473 |
"model.mamba_layers.47.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 474 |
+
"model.mamba_layers.47.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 475 |
"model.mamba_layers.47.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 476 |
"model.mamba_layers.47.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 477 |
"model.mamba_layers.48.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 480 |
"model.mamba_layers.48.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 481 |
"model.mamba_layers.48.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 482 |
"model.mamba_layers.48.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 483 |
+
"model.mamba_layers.48.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 484 |
"model.mamba_layers.48.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 485 |
"model.mamba_layers.48.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 486 |
"model.mamba_layers.49.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 489 |
"model.mamba_layers.49.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 490 |
"model.mamba_layers.49.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 491 |
"model.mamba_layers.49.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 492 |
+
"model.mamba_layers.49.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 493 |
"model.mamba_layers.49.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 494 |
"model.mamba_layers.49.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 495 |
"model.mamba_layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 498 |
"model.mamba_layers.5.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 499 |
"model.mamba_layers.5.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 500 |
"model.mamba_layers.5.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 501 |
+
"model.mamba_layers.5.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 502 |
"model.mamba_layers.5.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 503 |
"model.mamba_layers.5.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 504 |
"model.mamba_layers.50.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 507 |
"model.mamba_layers.50.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 508 |
"model.mamba_layers.50.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 509 |
"model.mamba_layers.50.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 510 |
+
"model.mamba_layers.50.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 511 |
"model.mamba_layers.50.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 512 |
"model.mamba_layers.50.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 513 |
"model.mamba_layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 516 |
"model.mamba_layers.51.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
| 517 |
"model.mamba_layers.51.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 518 |
"model.mamba_layers.51.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
| 519 |
+
"model.mamba_layers.51.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
| 520 |
"model.mamba_layers.51.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
| 521 |
"model.mamba_layers.51.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 522 |
"model.mamba_layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 525 |
"model.mamba_layers.52.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 526 |
"model.mamba_layers.52.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 527 |
"model.mamba_layers.52.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 528 |
+
"model.mamba_layers.52.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 529 |
"model.mamba_layers.52.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 530 |
"model.mamba_layers.52.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 531 |
"model.mamba_layers.53.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 534 |
"model.mamba_layers.53.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 535 |
"model.mamba_layers.53.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 536 |
"model.mamba_layers.53.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 537 |
+
"model.mamba_layers.53.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 538 |
"model.mamba_layers.53.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 539 |
"model.mamba_layers.53.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 540 |
"model.mamba_layers.54.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 543 |
"model.mamba_layers.54.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 544 |
"model.mamba_layers.54.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 545 |
"model.mamba_layers.54.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 546 |
+
"model.mamba_layers.54.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 547 |
"model.mamba_layers.54.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 548 |
"model.mamba_layers.54.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 549 |
"model.mamba_layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 552 |
"model.mamba_layers.55.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 553 |
"model.mamba_layers.55.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 554 |
"model.mamba_layers.55.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 555 |
+
"model.mamba_layers.55.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 556 |
"model.mamba_layers.55.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 557 |
"model.mamba_layers.55.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 558 |
"model.mamba_layers.56.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 561 |
"model.mamba_layers.56.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 562 |
"model.mamba_layers.56.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 563 |
"model.mamba_layers.56.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 564 |
+
"model.mamba_layers.56.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 565 |
"model.mamba_layers.56.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 566 |
"model.mamba_layers.56.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 567 |
"model.mamba_layers.57.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 570 |
"model.mamba_layers.57.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 571 |
"model.mamba_layers.57.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 572 |
"model.mamba_layers.57.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 573 |
+
"model.mamba_layers.57.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 574 |
"model.mamba_layers.57.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 575 |
"model.mamba_layers.57.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 576 |
"model.mamba_layers.58.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 579 |
"model.mamba_layers.58.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 580 |
"model.mamba_layers.58.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 581 |
"model.mamba_layers.58.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 582 |
+
"model.mamba_layers.58.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 583 |
"model.mamba_layers.58.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 584 |
"model.mamba_layers.58.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 585 |
"model.mamba_layers.59.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 588 |
"model.mamba_layers.59.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 589 |
"model.mamba_layers.59.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 590 |
"model.mamba_layers.59.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 591 |
+
"model.mamba_layers.59.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 592 |
"model.mamba_layers.59.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 593 |
"model.mamba_layers.59.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 594 |
"model.mamba_layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 597 |
"model.mamba_layers.6.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 598 |
"model.mamba_layers.6.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 599 |
"model.mamba_layers.6.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 600 |
+
"model.mamba_layers.6.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 601 |
"model.mamba_layers.6.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 602 |
"model.mamba_layers.6.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 603 |
"model.mamba_layers.60.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 606 |
"model.mamba_layers.60.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 607 |
"model.mamba_layers.60.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 608 |
"model.mamba_layers.60.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 609 |
+
"model.mamba_layers.60.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 610 |
"model.mamba_layers.60.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 611 |
"model.mamba_layers.60.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 612 |
"model.mamba_layers.61.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 615 |
"model.mamba_layers.61.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 616 |
"model.mamba_layers.61.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 617 |
"model.mamba_layers.61.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 618 |
+
"model.mamba_layers.61.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 619 |
"model.mamba_layers.61.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 620 |
"model.mamba_layers.61.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 621 |
"model.mamba_layers.62.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 624 |
"model.mamba_layers.62.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 625 |
"model.mamba_layers.62.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 626 |
"model.mamba_layers.62.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 627 |
+
"model.mamba_layers.62.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 628 |
"model.mamba_layers.62.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 629 |
"model.mamba_layers.62.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 630 |
"model.mamba_layers.63.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 633 |
"model.mamba_layers.63.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 634 |
"model.mamba_layers.63.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 635 |
"model.mamba_layers.63.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 636 |
+
"model.mamba_layers.63.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 637 |
"model.mamba_layers.63.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 638 |
"model.mamba_layers.63.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 639 |
"model.mamba_layers.64.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 642 |
"model.mamba_layers.64.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 643 |
"model.mamba_layers.64.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 644 |
"model.mamba_layers.64.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 645 |
+
"model.mamba_layers.64.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 646 |
"model.mamba_layers.64.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 647 |
"model.mamba_layers.64.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 648 |
"model.mamba_layers.65.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 651 |
"model.mamba_layers.65.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 652 |
"model.mamba_layers.65.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 653 |
"model.mamba_layers.65.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 654 |
+
"model.mamba_layers.65.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 655 |
"model.mamba_layers.65.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 656 |
"model.mamba_layers.65.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 657 |
"model.mamba_layers.66.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 660 |
"model.mamba_layers.66.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 661 |
"model.mamba_layers.66.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 662 |
"model.mamba_layers.66.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 663 |
+
"model.mamba_layers.66.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 664 |
"model.mamba_layers.66.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 665 |
"model.mamba_layers.66.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 666 |
"model.mamba_layers.67.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 669 |
"model.mamba_layers.67.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 670 |
"model.mamba_layers.67.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 671 |
"model.mamba_layers.67.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 672 |
+
"model.mamba_layers.67.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 673 |
"model.mamba_layers.67.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 674 |
"model.mamba_layers.67.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 675 |
"model.mamba_layers.68.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 678 |
"model.mamba_layers.68.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 679 |
"model.mamba_layers.68.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 680 |
"model.mamba_layers.68.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 681 |
+
"model.mamba_layers.68.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 682 |
"model.mamba_layers.68.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 683 |
"model.mamba_layers.68.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 684 |
"model.mamba_layers.69.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 687 |
"model.mamba_layers.69.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 688 |
"model.mamba_layers.69.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 689 |
"model.mamba_layers.69.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 690 |
+
"model.mamba_layers.69.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 691 |
"model.mamba_layers.69.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 692 |
"model.mamba_layers.69.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 693 |
"model.mamba_layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 696 |
"model.mamba_layers.7.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 697 |
"model.mamba_layers.7.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 698 |
"model.mamba_layers.7.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 699 |
+
"model.mamba_layers.7.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 700 |
"model.mamba_layers.7.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 701 |
"model.mamba_layers.7.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 702 |
"model.mamba_layers.70.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 705 |
"model.mamba_layers.70.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 706 |
"model.mamba_layers.70.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 707 |
"model.mamba_layers.70.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 708 |
+
"model.mamba_layers.70.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 709 |
"model.mamba_layers.70.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 710 |
"model.mamba_layers.70.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 711 |
"model.mamba_layers.71.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 714 |
"model.mamba_layers.71.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 715 |
"model.mamba_layers.71.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 716 |
"model.mamba_layers.71.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 717 |
+
"model.mamba_layers.71.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 718 |
"model.mamba_layers.71.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 719 |
"model.mamba_layers.71.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 720 |
"model.mamba_layers.72.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 723 |
"model.mamba_layers.72.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 724 |
"model.mamba_layers.72.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 725 |
"model.mamba_layers.72.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 726 |
+
"model.mamba_layers.72.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 727 |
"model.mamba_layers.72.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 728 |
"model.mamba_layers.72.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 729 |
"model.mamba_layers.73.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 732 |
"model.mamba_layers.73.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 733 |
"model.mamba_layers.73.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 734 |
"model.mamba_layers.73.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 735 |
+
"model.mamba_layers.73.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 736 |
"model.mamba_layers.73.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 737 |
"model.mamba_layers.73.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 738 |
"model.mamba_layers.74.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 741 |
"model.mamba_layers.74.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 742 |
"model.mamba_layers.74.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 743 |
"model.mamba_layers.74.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 744 |
+
"model.mamba_layers.74.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 745 |
"model.mamba_layers.74.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 746 |
"model.mamba_layers.74.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 747 |
"model.mamba_layers.75.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 750 |
"model.mamba_layers.75.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 751 |
"model.mamba_layers.75.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 752 |
"model.mamba_layers.75.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 753 |
+
"model.mamba_layers.75.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 754 |
"model.mamba_layers.75.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 755 |
"model.mamba_layers.75.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 756 |
"model.mamba_layers.76.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 759 |
"model.mamba_layers.76.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 760 |
"model.mamba_layers.76.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 761 |
"model.mamba_layers.76.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 762 |
+
"model.mamba_layers.76.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 763 |
"model.mamba_layers.76.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 764 |
"model.mamba_layers.76.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 765 |
"model.mamba_layers.77.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 768 |
"model.mamba_layers.77.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 769 |
"model.mamba_layers.77.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 770 |
"model.mamba_layers.77.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 771 |
+
"model.mamba_layers.77.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 772 |
"model.mamba_layers.77.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 773 |
"model.mamba_layers.77.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 774 |
"model.mamba_layers.78.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 777 |
"model.mamba_layers.78.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 778 |
"model.mamba_layers.78.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 779 |
"model.mamba_layers.78.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 780 |
+
"model.mamba_layers.78.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 781 |
"model.mamba_layers.78.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 782 |
"model.mamba_layers.78.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 783 |
"model.mamba_layers.79.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 786 |
"model.mamba_layers.79.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 787 |
"model.mamba_layers.79.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 788 |
"model.mamba_layers.79.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 789 |
+
"model.mamba_layers.79.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 790 |
"model.mamba_layers.79.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 791 |
"model.mamba_layers.79.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 792 |
"model.mamba_layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 795 |
"model.mamba_layers.8.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 796 |
"model.mamba_layers.8.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 797 |
"model.mamba_layers.8.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 798 |
+
"model.mamba_layers.8.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 799 |
"model.mamba_layers.8.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 800 |
"model.mamba_layers.8.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 801 |
"model.mamba_layers.80.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 804 |
"model.mamba_layers.80.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
| 805 |
"model.mamba_layers.80.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 806 |
"model.mamba_layers.80.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
| 807 |
+
"model.mamba_layers.80.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
| 808 |
"model.mamba_layers.80.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
| 809 |
"model.mamba_layers.80.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 810 |
"model.mamba_layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 813 |
"model.mamba_layers.9.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
| 814 |
"model.mamba_layers.9.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 815 |
"model.mamba_layers.9.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
| 816 |
+
"model.mamba_layers.9.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
| 817 |
"model.mamba_layers.9.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
| 818 |
"model.mamba_layers.9.mamba.out_proj.weight": "model-00001-of-00004.safetensors"
|
| 819 |
}
|
| 820 |
+
}
|