Upload PhiForCausalLM
Browse files
model-00001-of-00003.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 sha256:79303c24a52ef750bed811626ed2c410c48d75e22ac71836e9bbdf9465d6f939
|
3 |
+
size 4982355512
|
model-00002-of-00003.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:f519aca82a13b5deae1bbc8904ca8da3591da2f4442bdca2d21dcd9ac52b8cca
|
3 |
+
size 4982541984
|
model-00003-of-00003.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 sha256:552a5498455c5a270bafc58f09c6914b76a474e3f75bcfcb39562d800f00b147
|
3 |
+
size 1153887616
|
model.safetensors.index.json
CHANGED
@@ -16,8 +16,12 @@
|
|
16 |
"model.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
17 |
"model.layers.0.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
18 |
"model.layers.0.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
19 |
-
"model.layers.0.self_attn.
|
20 |
-
"model.layers.0.self_attn.
|
|
|
|
|
|
|
|
|
21 |
"model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
22 |
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
23 |
"model.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -26,8 +30,12 @@
|
|
26 |
"model.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
27 |
"model.layers.1.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
28 |
"model.layers.1.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
29 |
-
"model.layers.1.self_attn.
|
30 |
-
"model.layers.1.self_attn.
|
|
|
|
|
|
|
|
|
31 |
"model.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
32 |
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
33 |
"model.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -36,8 +44,12 @@
|
|
36 |
"model.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
37 |
"model.layers.10.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
38 |
"model.layers.10.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
39 |
-
"model.layers.10.self_attn.
|
40 |
-
"model.layers.10.self_attn.
|
|
|
|
|
|
|
|
|
41 |
"model.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
42 |
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
43 |
"model.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -46,8 +58,12 @@
|
|
46 |
"model.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
47 |
"model.layers.11.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
48 |
"model.layers.11.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
49 |
-
"model.layers.11.self_attn.
|
50 |
-
"model.layers.11.self_attn.
|
|
|
|
|
|
|
|
|
51 |
"model.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
52 |
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
53 |
"model.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -56,8 +72,12 @@
|
|
56 |
"model.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
57 |
"model.layers.12.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
58 |
"model.layers.12.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
59 |
-
"model.layers.12.self_attn.
|
60 |
-
"model.layers.12.self_attn.
|
|
|
|
|
|
|
|
|
61 |
"model.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
62 |
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
63 |
"model.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -66,8 +86,12 @@
|
|
66 |
"model.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
67 |
"model.layers.13.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
68 |
"model.layers.13.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
69 |
-
"model.layers.13.self_attn.
|
70 |
-
"model.layers.13.self_attn.
|
|
|
|
|
|
|
|
|
71 |
"model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
72 |
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
73 |
"model.layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -76,8 +100,12 @@
|
|
76 |
"model.layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
77 |
"model.layers.14.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
78 |
"model.layers.14.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
79 |
-
"model.layers.14.self_attn.
|
80 |
-
"model.layers.14.self_attn.
|
|
|
|
|
|
|
|
|
81 |
"model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
82 |
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
83 |
"model.layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -86,8 +114,12 @@
|
|
86 |
"model.layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
87 |
"model.layers.15.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
88 |
"model.layers.15.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
89 |
-
"model.layers.15.self_attn.
|
90 |
-
"model.layers.15.self_attn.
|
|
|
|
|
|
|
|
|
91 |
"model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
92 |
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
93 |
"model.layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -96,8 +128,12 @@
|
|
96 |
"model.layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
97 |
"model.layers.16.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
98 |
"model.layers.16.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
99 |
-
"model.layers.16.self_attn.
|
100 |
-
"model.layers.16.self_attn.
|
|
|
|
|
|
|
|
|
101 |
"model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
102 |
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
103 |
"model.layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -106,8 +142,12 @@
|
|
106 |
"model.layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
107 |
"model.layers.17.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
108 |
"model.layers.17.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
109 |
-
"model.layers.17.self_attn.
|
110 |
-
"model.layers.17.self_attn.
|
|
|
|
|
|
|
|
|
111 |
"model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
112 |
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
113 |
"model.layers.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -116,8 +156,12 @@
|
|
116 |
"model.layers.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
117 |
"model.layers.18.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
118 |
"model.layers.18.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
119 |
-
"model.layers.18.self_attn.
|
120 |
-
"model.layers.18.self_attn.
|
|
|
|
|
|
|
|
|
121 |
"model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
122 |
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
123 |
"model.layers.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -126,8 +170,12 @@
|
|
126 |
"model.layers.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
127 |
"model.layers.19.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
128 |
"model.layers.19.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
129 |
-
"model.layers.19.self_attn.
|
130 |
-
"model.layers.19.self_attn.
|
|
|
|
|
|
|
|
|
131 |
"model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
132 |
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
133 |
"model.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -136,8 +184,12 @@
|
|
136 |
"model.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
137 |
"model.layers.2.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
138 |
"model.layers.2.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
139 |
-
"model.layers.2.self_attn.
|
140 |
-
"model.layers.2.self_attn.
|
|
|
|
|
|
|
|
|
141 |
"model.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
142 |
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
143 |
"model.layers.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -146,8 +198,12 @@
|
|
146 |
"model.layers.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
147 |
"model.layers.20.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
148 |
"model.layers.20.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
149 |
-
"model.layers.20.self_attn.
|
150 |
-
"model.layers.20.self_attn.
|
|
|
|
|
|
|
|
|
151 |
"model.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
152 |
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
153 |
"model.layers.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -156,8 +212,12 @@
|
|
156 |
"model.layers.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
157 |
"model.layers.21.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
158 |
"model.layers.21.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
159 |
-
"model.layers.21.self_attn.
|
160 |
-
"model.layers.21.self_attn.
|
|
|
|
|
|
|
|
|
161 |
"model.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
162 |
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
163 |
"model.layers.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -166,8 +226,12 @@
|
|
166 |
"model.layers.22.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
167 |
"model.layers.22.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
168 |
"model.layers.22.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
169 |
-
"model.layers.22.self_attn.
|
170 |
-
"model.layers.22.self_attn.
|
|
|
|
|
|
|
|
|
171 |
"model.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
172 |
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
173 |
"model.layers.23.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -176,8 +240,12 @@
|
|
176 |
"model.layers.23.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
177 |
"model.layers.23.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
178 |
"model.layers.23.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
179 |
-
"model.layers.23.self_attn.
|
180 |
-
"model.layers.23.self_attn.
|
|
|
|
|
|
|
|
|
181 |
"model.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
182 |
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
183 |
"model.layers.24.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -186,8 +254,12 @@
|
|
186 |
"model.layers.24.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
187 |
"model.layers.24.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
188 |
"model.layers.24.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
189 |
-
"model.layers.24.self_attn.
|
190 |
-
"model.layers.24.self_attn.
|
|
|
|
|
|
|
|
|
191 |
"model.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
192 |
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
193 |
"model.layers.25.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -196,8 +268,12 @@
|
|
196 |
"model.layers.25.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
197 |
"model.layers.25.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
198 |
"model.layers.25.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
199 |
-
"model.layers.25.self_attn.
|
200 |
-
"model.layers.25.self_attn.
|
|
|
|
|
|
|
|
|
201 |
"model.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
202 |
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
203 |
"model.layers.26.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -206,8 +282,12 @@
|
|
206 |
"model.layers.26.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
207 |
"model.layers.26.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
208 |
"model.layers.26.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
209 |
-
"model.layers.26.self_attn.
|
210 |
-
"model.layers.26.self_attn.
|
|
|
|
|
|
|
|
|
211 |
"model.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
212 |
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
213 |
"model.layers.27.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -216,8 +296,12 @@
|
|
216 |
"model.layers.27.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
217 |
"model.layers.27.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
218 |
"model.layers.27.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
219 |
-
"model.layers.27.self_attn.
|
220 |
-
"model.layers.27.self_attn.
|
|
|
|
|
|
|
|
|
221 |
"model.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
222 |
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
223 |
"model.layers.28.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
@@ -226,18 +310,26 @@
|
|
226 |
"model.layers.28.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
227 |
"model.layers.28.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
228 |
"model.layers.28.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
229 |
-
"model.layers.28.self_attn.
|
230 |
-
"model.layers.28.self_attn.
|
231 |
-
"model.layers.
|
232 |
-
"model.layers.
|
|
|
|
|
|
|
|
|
233 |
"model.layers.29.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
234 |
"model.layers.29.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
235 |
-
"model.layers.29.mlp.fc2.bias": "model-
|
236 |
-
"model.layers.29.mlp.fc2.weight": "model-
|
237 |
"model.layers.29.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
238 |
"model.layers.29.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
239 |
-
"model.layers.29.self_attn.
|
240 |
-
"model.layers.29.self_attn.
|
|
|
|
|
|
|
|
|
241 |
"model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
242 |
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
243 |
"model.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -246,8 +338,12 @@
|
|
246 |
"model.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
247 |
"model.layers.3.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
248 |
"model.layers.3.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
249 |
-
"model.layers.3.self_attn.
|
250 |
-
"model.layers.3.self_attn.
|
|
|
|
|
|
|
|
|
251 |
"model.layers.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
252 |
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
253 |
"model.layers.30.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
@@ -256,8 +352,12 @@
|
|
256 |
"model.layers.30.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
257 |
"model.layers.30.self_attn.dense.bias": "model-00003-of-00003.safetensors",
|
258 |
"model.layers.30.self_attn.dense.weight": "model-00003-of-00003.safetensors",
|
259 |
-
"model.layers.30.self_attn.
|
260 |
-
"model.layers.30.self_attn.
|
|
|
|
|
|
|
|
|
261 |
"model.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
262 |
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
263 |
"model.layers.31.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
@@ -266,8 +366,12 @@
|
|
266 |
"model.layers.31.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
267 |
"model.layers.31.self_attn.dense.bias": "model-00003-of-00003.safetensors",
|
268 |
"model.layers.31.self_attn.dense.weight": "model-00003-of-00003.safetensors",
|
269 |
-
"model.layers.31.self_attn.
|
270 |
-
"model.layers.31.self_attn.
|
|
|
|
|
|
|
|
|
271 |
"model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
272 |
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
273 |
"model.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -276,8 +380,12 @@
|
|
276 |
"model.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
277 |
"model.layers.4.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
278 |
"model.layers.4.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
279 |
-
"model.layers.4.self_attn.
|
280 |
-
"model.layers.4.self_attn.
|
|
|
|
|
|
|
|
|
281 |
"model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
282 |
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
283 |
"model.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -286,8 +394,12 @@
|
|
286 |
"model.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
287 |
"model.layers.5.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
288 |
"model.layers.5.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
289 |
-
"model.layers.5.self_attn.
|
290 |
-
"model.layers.5.self_attn.
|
|
|
|
|
|
|
|
|
291 |
"model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
292 |
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
293 |
"model.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -296,8 +408,12 @@
|
|
296 |
"model.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
297 |
"model.layers.6.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
298 |
"model.layers.6.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
299 |
-
"model.layers.6.self_attn.
|
300 |
-
"model.layers.6.self_attn.
|
|
|
|
|
|
|
|
|
301 |
"model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
302 |
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
303 |
"model.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -306,8 +422,12 @@
|
|
306 |
"model.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
307 |
"model.layers.7.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
308 |
"model.layers.7.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
309 |
-
"model.layers.7.self_attn.
|
310 |
-
"model.layers.7.self_attn.
|
|
|
|
|
|
|
|
|
311 |
"model.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
312 |
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
313 |
"model.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -316,8 +436,12 @@
|
|
316 |
"model.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
317 |
"model.layers.8.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
318 |
"model.layers.8.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
319 |
-
"model.layers.8.self_attn.
|
320 |
-
"model.layers.8.self_attn.
|
|
|
|
|
|
|
|
|
321 |
"model.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
322 |
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
323 |
"model.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
@@ -326,7 +450,11 @@
|
|
326 |
"model.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
327 |
"model.layers.9.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
328 |
"model.layers.9.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
329 |
-
"model.layers.9.self_attn.
|
330 |
-
"model.layers.9.self_attn.
|
|
|
|
|
|
|
|
|
331 |
}
|
332 |
}
|
|
|
16 |
"model.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
17 |
"model.layers.0.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
18 |
"model.layers.0.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
"model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
26 |
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
27 |
"model.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
30 |
"model.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
31 |
"model.layers.1.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
32 |
"model.layers.1.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
36 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
37 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
38 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
39 |
"model.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
40 |
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
41 |
"model.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
44 |
"model.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
45 |
"model.layers.10.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
46 |
"model.layers.10.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
47 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
48 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
49 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
50 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
51 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
52 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
53 |
"model.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
54 |
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
55 |
"model.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
58 |
"model.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
59 |
"model.layers.11.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
60 |
"model.layers.11.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
61 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
62 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
63 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
64 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
65 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
66 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
67 |
"model.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
68 |
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
69 |
"model.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
72 |
"model.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
73 |
"model.layers.12.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
74 |
"model.layers.12.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
75 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
76 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
77 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
78 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
79 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
80 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
81 |
"model.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
82 |
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
83 |
"model.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
86 |
"model.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
87 |
"model.layers.13.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
88 |
"model.layers.13.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
89 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
90 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
91 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
92 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
93 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
94 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
95 |
"model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
96 |
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
97 |
"model.layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
100 |
"model.layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
101 |
"model.layers.14.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
102 |
"model.layers.14.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
104 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
105 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
106 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
107 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
108 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
109 |
"model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
110 |
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
111 |
"model.layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
114 |
"model.layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
115 |
"model.layers.15.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
116 |
"model.layers.15.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
117 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
118 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
119 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
120 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
121 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
122 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
123 |
"model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
124 |
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
125 |
"model.layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
128 |
"model.layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
129 |
"model.layers.16.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
130 |
"model.layers.16.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
132 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
134 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
135 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
136 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
137 |
"model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
138 |
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
139 |
"model.layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
142 |
"model.layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
143 |
"model.layers.17.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
144 |
"model.layers.17.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
145 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
146 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
147 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
148 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
149 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
150 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
151 |
"model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
152 |
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
153 |
"model.layers.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
156 |
"model.layers.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
157 |
"model.layers.18.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
158 |
"model.layers.18.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
159 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
160 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
161 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
162 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
163 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
164 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
165 |
"model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
166 |
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
167 |
"model.layers.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
170 |
"model.layers.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
171 |
"model.layers.19.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
172 |
"model.layers.19.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
173 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
174 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
175 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
176 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
177 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
178 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
179 |
"model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
180 |
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
181 |
"model.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
184 |
"model.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
185 |
"model.layers.2.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
186 |
"model.layers.2.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
187 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
188 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
189 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
190 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
191 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
192 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
193 |
"model.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
194 |
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
195 |
"model.layers.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
198 |
"model.layers.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
199 |
"model.layers.20.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
200 |
"model.layers.20.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
201 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
202 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
203 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
204 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
205 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
206 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
207 |
"model.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
208 |
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
209 |
"model.layers.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
212 |
"model.layers.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
213 |
"model.layers.21.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
214 |
"model.layers.21.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
215 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
216 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
217 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
218 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
219 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
220 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
221 |
"model.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
222 |
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
223 |
"model.layers.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
226 |
"model.layers.22.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
227 |
"model.layers.22.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
228 |
"model.layers.22.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
229 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
230 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
231 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
232 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
233 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
234 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
235 |
"model.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
236 |
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
237 |
"model.layers.23.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
240 |
"model.layers.23.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
241 |
"model.layers.23.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
242 |
"model.layers.23.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
243 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
244 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
245 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
246 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
247 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
248 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
249 |
"model.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
250 |
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
251 |
"model.layers.24.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
254 |
"model.layers.24.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
255 |
"model.layers.24.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
256 |
"model.layers.24.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
257 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
258 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
259 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
260 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
261 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
262 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
263 |
"model.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
264 |
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
265 |
"model.layers.25.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
268 |
"model.layers.25.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
269 |
"model.layers.25.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
270 |
"model.layers.25.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
271 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
272 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
273 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
274 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
275 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
276 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
277 |
"model.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
278 |
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
279 |
"model.layers.26.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
282 |
"model.layers.26.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
283 |
"model.layers.26.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
284 |
"model.layers.26.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
285 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
286 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
287 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
288 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
289 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
290 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
291 |
"model.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
292 |
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
293 |
"model.layers.27.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
296 |
"model.layers.27.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
297 |
"model.layers.27.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
298 |
"model.layers.27.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
299 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
300 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
301 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
302 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
303 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
304 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
305 |
"model.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
306 |
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
307 |
"model.layers.28.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
|
|
310 |
"model.layers.28.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
311 |
"model.layers.28.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
312 |
"model.layers.28.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
313 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
314 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
315 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
316 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
317 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
318 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
319 |
+
"model.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
320 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
321 |
"model.layers.29.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
322 |
"model.layers.29.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
323 |
+
"model.layers.29.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
324 |
+
"model.layers.29.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
325 |
"model.layers.29.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
326 |
"model.layers.29.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
327 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
328 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
329 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
330 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
331 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
332 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
333 |
"model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
334 |
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
335 |
"model.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
338 |
"model.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
339 |
"model.layers.3.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
340 |
"model.layers.3.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
341 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
342 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
343 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
344 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
345 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
346 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
347 |
"model.layers.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
348 |
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
349 |
"model.layers.30.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
|
|
352 |
"model.layers.30.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
353 |
"model.layers.30.self_attn.dense.bias": "model-00003-of-00003.safetensors",
|
354 |
"model.layers.30.self_attn.dense.weight": "model-00003-of-00003.safetensors",
|
355 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
356 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
357 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
358 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
359 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
360 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
361 |
"model.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
362 |
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
363 |
"model.layers.31.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
|
|
366 |
"model.layers.31.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
367 |
"model.layers.31.self_attn.dense.bias": "model-00003-of-00003.safetensors",
|
368 |
"model.layers.31.self_attn.dense.weight": "model-00003-of-00003.safetensors",
|
369 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
370 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
371 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
372 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
373 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
374 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
375 |
"model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
376 |
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
377 |
"model.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
380 |
"model.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
381 |
"model.layers.4.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
382 |
"model.layers.4.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
383 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
384 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
385 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
386 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
387 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
388 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
389 |
"model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
390 |
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
391 |
"model.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
394 |
"model.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
395 |
"model.layers.5.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
396 |
"model.layers.5.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
397 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
398 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
399 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
400 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
401 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
402 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
403 |
"model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
404 |
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
405 |
"model.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
408 |
"model.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
409 |
"model.layers.6.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
410 |
"model.layers.6.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
411 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
412 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
413 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
414 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
415 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
416 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
417 |
"model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
418 |
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
419 |
"model.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
422 |
"model.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
423 |
"model.layers.7.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
424 |
"model.layers.7.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
425 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
426 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
427 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
428 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
429 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
430 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
431 |
"model.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
432 |
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
433 |
"model.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
436 |
"model.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
437 |
"model.layers.8.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
438 |
"model.layers.8.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
439 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
440 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
441 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
442 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
443 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
444 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
445 |
"model.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
446 |
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
447 |
"model.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
|
|
450 |
"model.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
451 |
"model.layers.9.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
452 |
"model.layers.9.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
453 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
454 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
455 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
456 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
457 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
458 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors"
|
459 |
}
|
460 |
}
|